# Pipelines ## Search Pipelines `IReadOnlyList Pipelines.List(PipelineListParams?parameters, CancellationTokencancellationToken = default)` **get** `/api/v1/pipelines` Search for pipelines by name, type, or project. ### Parameters - `PipelineListParams parameters` - `string? organizationID` - `string? pipelineName` - `PipelineType? pipelineType` Enum for representing the type of a pipeline - `string? projectID` - `string? projectName` ### Example ```csharp PipelineListParams parameters = new(); var pipelines = await client.Pipelines.List(parameters); Console.WriteLine(pipelines); ``` #### Response ```json [ { "id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "embedding_config": { "component": { "additional_kwargs": { "foo": "bar" }, "api_base": "api_base", "api_key": "api_key", "api_version": "api_version", "azure_deployment": "azure_deployment", "azure_endpoint": "azure_endpoint", "class_name": "class_name", "default_headers": { "foo": "string" }, "dimensions": 0, "embed_batch_size": 1, "max_retries": 0, "model_name": "model_name", "num_workers": 0, "reuse_client": true, "timeout": 0 }, "type": "AZURE_EMBEDDING" }, "name": "name", "project_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "config_hash": { "embedding_config_hash": "embedding_config_hash", "parsing_config_hash": "parsing_config_hash", "transform_config_hash": "transform_config_hash" }, "created_at": "2019-12-27T18:11:19.117Z", "data_sink": { "id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "component": { "foo": "bar" }, "name": "name", "project_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "sink_type": "ASTRA_DB", "created_at": "2019-12-27T18:11:19.117Z", "updated_at": "2019-12-27T18:11:19.117Z" }, "embedding_model_config": { "id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "embedding_config": { "component": { "additional_kwargs": { "foo": "bar" }, "api_base": "api_base", "api_key": "api_key", "api_version": "api_version", "azure_deployment": "azure_deployment", "azure_endpoint": "azure_endpoint", "class_name": "class_name", "default_headers": { "foo": "string" }, "dimensions": 0, "embed_batch_size": 1, "max_retries": 0, "model_name": "model_name", "num_workers": 0, "reuse_client": true, "timeout": 0 }, "type": "AZURE_EMBEDDING" }, "name": "name", "project_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "created_at": "2019-12-27T18:11:19.117Z", "updated_at": "2019-12-27T18:11:19.117Z" }, "embedding_model_config_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "llama_parse_parameters": { "adaptive_long_table": true, "aggressive_table_extraction": true, "annotate_links": true, "auto_mode": true, "auto_mode_configuration_json": "auto_mode_configuration_json", "auto_mode_trigger_on_image_in_page": true, "auto_mode_trigger_on_regexp_in_page": "auto_mode_trigger_on_regexp_in_page", "auto_mode_trigger_on_table_in_page": true, "auto_mode_trigger_on_text_in_page": "auto_mode_trigger_on_text_in_page", "azure_openai_api_version": "azure_openai_api_version", "azure_openai_deployment_name": "azure_openai_deployment_name", "azure_openai_endpoint": "azure_openai_endpoint", "azure_openai_key": "azure_openai_key", "bbox_bottom": 0, "bbox_left": 0, "bbox_right": 0, "bbox_top": 0, "bounding_box": "bounding_box", "compact_markdown_table": true, "complemental_formatting_instruction": "complemental_formatting_instruction", "confidence_score_effort": "confidence_score_effort", "content_guideline_instruction": "content_guideline_instruction", "continuous_mode": true, "disable_image_extraction": true, "disable_ocr": true, "disable_reconstruction": true, "do_not_cache": true, "do_not_unroll_columns": true, "enable_cost_optimizer": true, "extract_charts": true, "extract_layout": true, "extract_printed_page_number": true, "fast_mode": true, "formatting_instruction": "formatting_instruction", "gpt4o_api_key": "gpt4o_api_key", "gpt4o_mode": true, "guess_xlsx_sheet_name": true, "hide_footers": true, "hide_headers": true, "high_res_ocr": true, "html_make_all_elements_visible": true, "html_remove_fixed_elements": true, "html_remove_navigation_elements": true, "http_proxy": "http_proxy", "ignore_document_elements_for_layout_detection": true, "images_to_save": [ "embedded" ], "inline_images_in_markdown": true, "input_s3_path": "input_s3_path", "input_s3_region": "input_s3_region", "input_url": "input_url", "internal_is_screenshot_job": true, "invalidate_cache": true, "is_formatting_instruction": true, "job_timeout_extra_time_per_page_in_seconds": 0, "job_timeout_in_seconds": 0, "keep_page_separator_when_merging_tables": true, "languages": [ "abq" ], "layout_aware": true, "line_level_bounding_box": true, "markdown_table_multiline_header_separator": "markdown_table_multiline_header_separator", "max_pages": 0, "max_pages_enforced": 0, "merge_tables_across_pages_in_markdown": true, "model": "model", "outlined_table_extraction": true, "output_pdf_of_document": true, "output_s3_path_prefix": "output_s3_path_prefix", "output_s3_region": "output_s3_region", "output_tables_as_HTML": true, "page_error_tolerance": 0, "page_footer_prefix": "page_footer_prefix", "page_footer_suffix": "page_footer_suffix", "page_header_prefix": "page_header_prefix", "page_header_suffix": "page_header_suffix", "page_prefix": "page_prefix", "page_separator": "page_separator", "page_suffix": "page_suffix", "parse_mode": "parse_document_with_agent", "parsing_instruction": "parsing_instruction", "precise_bounding_box": true, "premium_mode": true, "presentation_out_of_bounds_content": true, "presentation_skip_embedded_data": true, "preserve_layout_alignment_across_pages": true, "preserve_very_small_text": true, "preset": "preset", "priority": "critical", "project_id": "project_id", "remove_hidden_text": true, "replace_failed_page_mode": "blank_page", "replace_failed_page_with_error_message_prefix": "replace_failed_page_with_error_message_prefix", "replace_failed_page_with_error_message_suffix": "replace_failed_page_with_error_message_suffix", "save_images": true, "skip_diagonal_text": true, "specialized_chart_parsing_agentic": true, "specialized_chart_parsing_efficient": true, "specialized_chart_parsing_plus": true, "specialized_image_parsing": true, "spreadsheet_extract_sub_tables": true, "spreadsheet_force_formula_computation": true, "spreadsheet_include_hidden_sheets": true, "strict_mode_buggy_font": true, "strict_mode_image_extraction": true, "strict_mode_image_ocr": true, "strict_mode_reconstruction": true, "structured_output": true, "structured_output_json_schema": "structured_output_json_schema", "structured_output_json_schema_name": "structured_output_json_schema_name", "system_prompt": "system_prompt", "system_prompt_append": "system_prompt_append", "take_screenshot": true, "target_pages": "target_pages", "tier": "tier", "use_vendor_multimodal_model": true, "user_prompt": "user_prompt", "vendor_multimodal_api_key": "vendor_multimodal_api_key", "vendor_multimodal_model_name": "vendor_multimodal_model_name", "version": "version", "webhook_configurations": [ { "webhook_events": [ "parse.success", "parse.error" ], "webhook_headers": { "Authorization": "Bearer sk-..." }, "webhook_output_format": "json", "webhook_signing_secret": "whsec_...", "webhook_url": "https://example.com/webhooks/llamacloud" } ], "webhook_url": "webhook_url" }, "managed_pipeline_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "metadata_config": { "excluded_embed_metadata_keys": [ "string" ], "excluded_llm_metadata_keys": [ "string" ] }, "pipeline_type": "MANAGED", "preset_retrieval_parameters": { "alpha": 0, "class_name": "class_name", "dense_similarity_cutoff": 0, "dense_similarity_top_k": 1, "enable_reranking": true, "files_top_k": 1, "rerank_top_n": 1, "retrieval_mode": "auto_routed", "retrieve_image_nodes": true, "retrieve_page_figure_nodes": true, "retrieve_page_screenshot_nodes": true, "search_filters": { "filters": [ { "key": "key", "value": 0, "operator": "!=" } ], "condition": "and" }, "search_filters_inference_schema": { "foo": { "foo": "bar" } }, "sparse_similarity_top_k": 1 }, "sparse_model_config": { "class_name": "class_name", "model_type": "auto" }, "status": "CREATED", "transform_config": { "chunk_overlap": 0, "chunk_size": 1, "mode": "auto" }, "updated_at": "2019-12-27T18:11:19.117Z" } ] ``` ## Create Pipeline `Pipeline Pipelines.Create(PipelineCreateParamsparameters, CancellationTokencancellationToken = default)` **post** `/api/v1/pipelines` Create a new managed ingestion pipeline. A pipeline connects data sources to a vector store for RAG. After creation, call `POST /pipelines/{id}/sync` to start ingesting documents. ### Parameters - `PipelineCreateParams parameters` - `required string name` Body param - `string? organizationID` Query param - `string? projectID` Query param - `DataSinkCreate? dataSink` Body param: Schema for creating a data sink. - `string? dataSinkID` Body param: Data sink ID. When provided instead of data_sink, the data sink will be looked up by ID. - `EmbeddingConfig? embeddingConfig` Body param - `class AzureOpenAIEmbeddingConfig:` - `AzureOpenAIEmbedding Component` Configuration for the Azure OpenAI embedding model. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the OpenAI API. - `string ApiBase` The base URL for Azure deployment. - `string? ApiKey` The OpenAI API key. - `string ApiVersion` The version for Azure OpenAI API. - `string? AzureDeployment` The Azure deployment to use. - `string? AzureEndpoint` The Azure endpoint to use. - `string ClassName` - `IReadOnlyDictionary? DefaultHeaders` The default headers for API requests. - `Long? Dimensions` The number of dimensions on the output embedding vectors. Works only with v3 embedding models. - `Long EmbedBatchSize` The batch size for embedding calls. - `Long MaxRetries` Maximum number of retries. - `string ModelName` The name of the OpenAI embedding model. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Boolean ReuseClient` Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability. - `Double Timeout` Timeout for each request. - `Type Type` Type of the embedding model. - `"AZURE_EMBEDDING"AzureEmbedding` - `class BedrockEmbeddingConfig:` - `BedrockEmbedding Component` Configuration for the Bedrock embedding model. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the bedrock client. - `string? AwsAccessKeyID` AWS Access Key ID to use - `string? AwsSecretAccessKey` AWS Secret Access Key to use - `string? AwsSessionToken` AWS Session Token to use - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `Long MaxRetries` The maximum number of API retries. - `string ModelName` The modelId of the Bedrock model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `string? ProfileName` The name of aws profile to use. If not given, then the default profile is used. - `string? RegionName` AWS region name to use. Uses region configured in AWS CLI if not passed - `Double Timeout` The timeout for the Bedrock API request in seconds. It will be used for both connect and read timeouts. - `Type Type` Type of the embedding model. - `"BEDROCK_EMBEDDING"BedrockEmbedding` - `class CohereEmbeddingConfig:` - `CohereEmbedding Component` Configuration for the Cohere embedding model. - `required string? ApiKey` The Cohere API key. - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `string EmbeddingType` Embedding type. If not provided float embedding_type is used when needed. - `string? InputType` Model Input type. If not provided, search_document and search_query are used when needed. - `string ModelName` The modelId of the Cohere model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `string Truncate` Truncation type - START/ END/ NONE - `Type Type` Type of the embedding model. - `"COHERE_EMBEDDING"CohereEmbedding` - `class GeminiEmbeddingConfig:` - `GeminiEmbedding Component` Configuration for the Gemini embedding model. - `string? ApiBase` API base to access the model. Defaults to None. - `string? ApiKey` API key to access the model. Defaults to None. - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `string ModelName` The modelId of the Gemini model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Long? OutputDimensionality` Optional reduced dimension for output embeddings. Supported by models/text-embedding-004 and newer (e.g. gemini-embedding-001). Not supported by models/embedding-001. - `string? TaskType` The task for embedding model. - `string? Title` Title is only applicable for retrieval_document tasks, and is used to represent a document title. For other tasks, title is invalid. - `string? Transport` Transport to access the model. Defaults to None. - `Type Type` Type of the embedding model. - `"GEMINI_EMBEDDING"GeminiEmbedding` - `class HuggingFaceInferenceApiEmbeddingConfig:` - `HuggingFaceInferenceApiEmbedding Component` Configuration for the HuggingFace Inference API embedding model. - `Token? Token` Hugging Face token. Will default to the locally saved token. Pass token=False if you don’t want to send your token to the server. - `string` - `Boolean` - `string ClassName` - `IReadOnlyDictionary? Cookies` Additional cookies to send to the server. - `Long EmbedBatchSize` The batch size for embedding calls. - `IReadOnlyDictionary? Headers` Additional headers to send to the server. By default only the authorization and user-agent headers are sent. Values in this dictionary will override the default values. - `string? ModelName` Hugging Face model name. If None, the task will be used. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Pooling? Pooling` Enum of possible pooling choices with pooling behaviors. - `"cls"Cls` - `"last"Last` - `"mean"Mean` - `string? QueryInstruction` Instruction to prepend during query embedding. - `string? Task` Optional task to pick Hugging Face's recommended model, used when model_name is left as default of None. - `string? TextInstruction` Instruction to prepend during text embedding. - `Double? Timeout` The maximum number of seconds to wait for a response from the server. Loading a new model in Inference API can take up to several minutes. Defaults to None, meaning it will loop until the server is available. - `Type Type` Type of the embedding model. - `"HUGGINGFACE_API_EMBEDDING"HuggingfaceApiEmbedding` - `class OpenAIEmbeddingConfig:` - `OpenAIEmbedding Component` Configuration for the OpenAI embedding model. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the OpenAI API. - `string? ApiBase` The base URL for OpenAI API. - `string? ApiKey` The OpenAI API key. - `string? ApiVersion` The version for OpenAI API. - `string ClassName` - `IReadOnlyDictionary? DefaultHeaders` The default headers for API requests. - `Long? Dimensions` The number of dimensions on the output embedding vectors. Works only with v3 embedding models. - `Long EmbedBatchSize` The batch size for embedding calls. - `Long MaxRetries` Maximum number of retries. - `string ModelName` The name of the OpenAI embedding model. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Boolean ReuseClient` Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability. - `Double Timeout` Timeout for each request. - `Type Type` Type of the embedding model. - `"OPENAI_EMBEDDING"OpenAIEmbedding` - `class VertexAIEmbeddingConfig:` - `VertexTextEmbedding Component` Configuration for the VertexAI embedding model. - `required string? ClientEmail` The client email for the VertexAI credentials. - `required string Location` The default location to use when making API calls. - `required string? PrivateKey` The private key for the VertexAI credentials. - `required string? PrivateKeyID` The private key ID for the VertexAI credentials. - `required string Project` The default GCP project to use when making Vertex API calls. - `required string? TokenUri` The token URI for the VertexAI credentials. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the Vertex. - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `EmbedMode EmbedMode` The embedding mode to use. - `"classification"Classification` - `"clustering"Clustering` - `"default"Default` - `"retrieval"Retrieval` - `"similarity"Similarity` - `string ModelName` The modelId of the VertexAI model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Type Type` Type of the embedding model. - `"VERTEXAI_EMBEDDING"VertexaiEmbedding` - `string? embeddingModelConfigID` Body param: Embedding model config ID. When provided instead of embedding_config, the embedding model config will be looked up by ID. - `LlamaParseParameters llamaParseParameters` Body param: Settings that can be configured for how to use LlamaParse to parse files within a LlamaCloud pipeline. - `string? managedPipelineID` Body param: The ID of the ManagedPipeline this playground pipeline is linked to. - `PipelineMetadataConfig? metadataConfig` Body param: Metadata configuration for the pipeline. - `PipelineType pipelineType` Body param: Type of pipeline. Either PLAYGROUND or MANAGED. - `PresetRetrievalParams presetRetrievalParameters` Body param: Preset retrieval parameters for the pipeline. - `SparseModelConfig? sparseModelConfig` Body param: Configuration for sparse embedding models used in hybrid search. This allows users to choose between Splade and BM25 models for sparse retrieval in managed data sinks. - `string? status` Body param: Status of the pipeline deployment. - `TransformConfig? transformConfig` Body param: Configuration for the transformation. - `class AutoTransformConfig:` - `Long ChunkOverlap` Chunk overlap for the transformation. - `Long ChunkSize` Chunk size for the transformation. - `Mode Mode` - `"auto"Auto` - `class AdvancedModeTransformConfig:` - `ChunkingConfig ChunkingConfig` Configuration for the chunking. - `class NoneChunkingConfig:` - `Mode Mode` - `"none"None` - `class CharacterChunkingConfig:` - `Long ChunkOverlap` - `Long ChunkSize` - `Mode Mode` - `"character"Character` - `class TokenChunkingConfig:` - `Long ChunkOverlap` - `Long ChunkSize` - `Mode Mode` - `"token"Token` - `string Separator` - `class SentenceChunkingConfig:` - `Long ChunkOverlap` - `Long ChunkSize` - `Mode Mode` - `"sentence"Sentence` - `string ParagraphSeparator` - `string Separator` - `class SemanticChunkingConfig:` - `Long BreakpointPercentileThreshold` - `Long BufferSize` - `Mode Mode` - `"semantic"Semantic` - `Mode Mode` - `"advanced"Advanced` - `SegmentationConfig SegmentationConfig` Configuration for the segmentation. - `class NoneSegmentationConfig:` - `Mode Mode` - `"none"None` - `class PageSegmentationConfig:` - `Mode Mode` - `"page"Page` - `string PageSeparator` - `class ElementSegmentationConfig:` - `Mode Mode` - `"element"Element` ### Returns - `class Pipeline:` Schema for a pipeline. - `required string ID` Unique identifier - `required EmbeddingConfig EmbeddingConfig` - `class AzureOpenAIEmbeddingConfig:` - `AzureOpenAIEmbedding Component` Configuration for the Azure OpenAI embedding model. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the OpenAI API. - `string ApiBase` The base URL for Azure deployment. - `string? ApiKey` The OpenAI API key. - `string ApiVersion` The version for Azure OpenAI API. - `string? AzureDeployment` The Azure deployment to use. - `string? AzureEndpoint` The Azure endpoint to use. - `string ClassName` - `IReadOnlyDictionary? DefaultHeaders` The default headers for API requests. - `Long? Dimensions` The number of dimensions on the output embedding vectors. Works only with v3 embedding models. - `Long EmbedBatchSize` The batch size for embedding calls. - `Long MaxRetries` Maximum number of retries. - `string ModelName` The name of the OpenAI embedding model. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Boolean ReuseClient` Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability. - `Double Timeout` Timeout for each request. - `Type Type` Type of the embedding model. - `"AZURE_EMBEDDING"AzureEmbedding` - `class BedrockEmbeddingConfig:` - `BedrockEmbedding Component` Configuration for the Bedrock embedding model. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the bedrock client. - `string? AwsAccessKeyID` AWS Access Key ID to use - `string? AwsSecretAccessKey` AWS Secret Access Key to use - `string? AwsSessionToken` AWS Session Token to use - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `Long MaxRetries` The maximum number of API retries. - `string ModelName` The modelId of the Bedrock model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `string? ProfileName` The name of aws profile to use. If not given, then the default profile is used. - `string? RegionName` AWS region name to use. Uses region configured in AWS CLI if not passed - `Double Timeout` The timeout for the Bedrock API request in seconds. It will be used for both connect and read timeouts. - `Type Type` Type of the embedding model. - `"BEDROCK_EMBEDDING"BedrockEmbedding` - `class CohereEmbeddingConfig:` - `CohereEmbedding Component` Configuration for the Cohere embedding model. - `required string? ApiKey` The Cohere API key. - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `string EmbeddingType` Embedding type. If not provided float embedding_type is used when needed. - `string? InputType` Model Input type. If not provided, search_document and search_query are used when needed. - `string ModelName` The modelId of the Cohere model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `string Truncate` Truncation type - START/ END/ NONE - `Type Type` Type of the embedding model. - `"COHERE_EMBEDDING"CohereEmbedding` - `class GeminiEmbeddingConfig:` - `GeminiEmbedding Component` Configuration for the Gemini embedding model. - `string? ApiBase` API base to access the model. Defaults to None. - `string? ApiKey` API key to access the model. Defaults to None. - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `string ModelName` The modelId of the Gemini model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Long? OutputDimensionality` Optional reduced dimension for output embeddings. Supported by models/text-embedding-004 and newer (e.g. gemini-embedding-001). Not supported by models/embedding-001. - `string? TaskType` The task for embedding model. - `string? Title` Title is only applicable for retrieval_document tasks, and is used to represent a document title. For other tasks, title is invalid. - `string? Transport` Transport to access the model. Defaults to None. - `Type Type` Type of the embedding model. - `"GEMINI_EMBEDDING"GeminiEmbedding` - `class HuggingFaceInferenceApiEmbeddingConfig:` - `HuggingFaceInferenceApiEmbedding Component` Configuration for the HuggingFace Inference API embedding model. - `Token? Token` Hugging Face token. Will default to the locally saved token. Pass token=False if you don’t want to send your token to the server. - `string` - `Boolean` - `string ClassName` - `IReadOnlyDictionary? Cookies` Additional cookies to send to the server. - `Long EmbedBatchSize` The batch size for embedding calls. - `IReadOnlyDictionary? Headers` Additional headers to send to the server. By default only the authorization and user-agent headers are sent. Values in this dictionary will override the default values. - `string? ModelName` Hugging Face model name. If None, the task will be used. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Pooling? Pooling` Enum of possible pooling choices with pooling behaviors. - `"cls"Cls` - `"last"Last` - `"mean"Mean` - `string? QueryInstruction` Instruction to prepend during query embedding. - `string? Task` Optional task to pick Hugging Face's recommended model, used when model_name is left as default of None. - `string? TextInstruction` Instruction to prepend during text embedding. - `Double? Timeout` The maximum number of seconds to wait for a response from the server. Loading a new model in Inference API can take up to several minutes. Defaults to None, meaning it will loop until the server is available. - `Type Type` Type of the embedding model. - `"HUGGINGFACE_API_EMBEDDING"HuggingfaceApiEmbedding` - `class ManagedOpenAIEmbedding:` - `Component Component` Configuration for the Managed OpenAI embedding model. - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `ModelName ModelName` The name of the OpenAI embedding model. - `"openai-text-embedding-3-small"OpenAITextEmbedding3Small` - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Type Type` Type of the embedding model. - `"MANAGED_OPENAI_EMBEDDING"ManagedOpenAIEmbedding` - `class OpenAIEmbeddingConfig:` - `OpenAIEmbedding Component` Configuration for the OpenAI embedding model. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the OpenAI API. - `string? ApiBase` The base URL for OpenAI API. - `string? ApiKey` The OpenAI API key. - `string? ApiVersion` The version for OpenAI API. - `string ClassName` - `IReadOnlyDictionary? DefaultHeaders` The default headers for API requests. - `Long? Dimensions` The number of dimensions on the output embedding vectors. Works only with v3 embedding models. - `Long EmbedBatchSize` The batch size for embedding calls. - `Long MaxRetries` Maximum number of retries. - `string ModelName` The name of the OpenAI embedding model. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Boolean ReuseClient` Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability. - `Double Timeout` Timeout for each request. - `Type Type` Type of the embedding model. - `"OPENAI_EMBEDDING"OpenAIEmbedding` - `class VertexAIEmbeddingConfig:` - `VertexTextEmbedding Component` Configuration for the VertexAI embedding model. - `required string? ClientEmail` The client email for the VertexAI credentials. - `required string Location` The default location to use when making API calls. - `required string? PrivateKey` The private key for the VertexAI credentials. - `required string? PrivateKeyID` The private key ID for the VertexAI credentials. - `required string Project` The default GCP project to use when making Vertex API calls. - `required string? TokenUri` The token URI for the VertexAI credentials. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the Vertex. - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `EmbedMode EmbedMode` The embedding mode to use. - `"classification"Classification` - `"clustering"Clustering` - `"default"Default` - `"retrieval"Retrieval` - `"similarity"Similarity` - `string ModelName` The modelId of the VertexAI model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Type Type` Type of the embedding model. - `"VERTEXAI_EMBEDDING"VertexaiEmbedding` - `required string Name` - `required string ProjectID` - `ConfigHash? ConfigHash` Hashes for the configuration of a pipeline. - `string? EmbeddingConfigHash` Hash of the embedding config. - `string? ParsingConfigHash` Hash of the llama parse parameters. - `string? TransformConfigHash` Hash of the transform config. - `DateTimeOffset? CreatedAt` Creation datetime - `DataSink? DataSink` Schema for a data sink. - `required string ID` Unique identifier - `required Component Component` Component that implements the data sink - `IReadOnlyDictionary` - `class CloudPineconeVectorStore:` Cloud Pinecone Vector Store. This class is used to store the configuration for a Pinecone vector store, so that it can be created and used in LlamaCloud. Args: api_key (str): API key for authenticating with Pinecone index_name (str): name of the Pinecone index namespace (optional[str]): namespace to use in the Pinecone index insert_kwargs (optional[dict]): additional kwargs to pass during insertion - `required string ApiKey` The API key for authenticating with Pinecone - `required string IndexName` - `string ClassName` - `IReadOnlyDictionary? InsertKwargs` - `string? Namespace` - `SupportsNestedMetadataFilters SupportsNestedMetadataFilters` - `trueTrue` - `class CloudPostgresVectorStore:` - `required string Database` - `required Long EmbedDim` - `required string Host` - `required string Password` - `required Long Port` - `required string SchemaName` - `required string TableName` - `required string User` - `string ClassName` - `PgVectorHnswSettings? HnswSettings` HNSW settings for PGVector. - `DistanceMethod DistanceMethod` The distance method to use. - `"cosine"Cosine` - `"hamming"Hamming` - `"ip"IP` - `"jaccard"Jaccard` - `"l1"L1` - `"l2"L2` - `Long EfConstruction` The number of edges to use during the construction phase. - `Long EfSearch` The number of edges to use during the search phase. - `Long M` The number of bi-directional links created for each new element. - `VectorType VectorType` The type of vector to use. - `"bit"Bit` - `"half_vec"HalfVec` - `"sparse_vec"SparseVec` - `"vector"Vector` - `Boolean? HybridSearch` - `Boolean PerformSetup` - `Boolean SupportsNestedMetadataFilters` - `class CloudQdrantVectorStore:` Cloud Qdrant Vector Store. This class is used to store the configuration for a Qdrant vector store, so that it can be created and used in LlamaCloud. Args: collection_name (str): name of the Qdrant collection url (str): url of the Qdrant instance api_key (str): API key for authenticating with Qdrant max_retries (int): maximum number of retries in case of a failure. Defaults to 3 client_kwargs (dict): additional kwargs to pass to the Qdrant client - `required string ApiKey` - `required string CollectionName` - `required string Url` - `string ClassName` - `IReadOnlyDictionary ClientKwargs` - `Long MaxRetries` - `SupportsNestedMetadataFilters SupportsNestedMetadataFilters` - `trueTrue` - `class CloudAzureAISearchVectorStore:` Cloud Azure AI Search Vector Store. - `required string SearchServiceApiKey` - `required string SearchServiceEndpoint` - `string ClassName` - `string? ClientID` - `string? ClientSecret` - `Long? EmbeddingDimension` - `IReadOnlyDictionary? FilterableMetadataFieldKeys` - `string? IndexName` - `string? SearchServiceApiVersion` - `SupportsNestedMetadataFilters SupportsNestedMetadataFilters` - `trueTrue` - `string? TenantID` - `class CloudMongoDBAtlasVectorSearch:` Cloud MongoDB Atlas Vector Store. This class is used to store the configuration for a MongoDB Atlas vector store, so that it can be created and used in LlamaCloud. Args: mongodb_uri (str): URI for connecting to MongoDB Atlas db_name (str): name of the MongoDB database collection_name (str): name of the MongoDB collection vector_index_name (str): name of the MongoDB Atlas vector index fulltext_index_name (str): name of the MongoDB Atlas full-text index - `required string CollectionName` - `required string DBName` - `required string MongoDBUri` - `string ClassName` - `Long? EmbeddingDimension` - `string? FulltextIndexName` - `Boolean SupportsNestedMetadataFilters` - `string? VectorIndexName` - `class CloudMilvusVectorStore:` Cloud Milvus Vector Store. - `required string Uri` - `string? Token` - `string ClassName` - `string? CollectionName` - `Long? EmbeddingDimension` - `Boolean SupportsNestedMetadataFilters` - `class CloudAstraDBVectorStore:` Cloud AstraDB Vector Store. This class is used to store the configuration for an AstraDB vector store, so that it can be created and used in LlamaCloud. Args: token (str): The Astra DB Application Token to use. api_endpoint (str): The Astra DB JSON API endpoint for your database. collection_name (str): Collection name to use. If not existing, it will be created. embedding_dimension (int): Length of the embedding vectors in use. keyspace (optional[str]): The keyspace to use. If not provided, 'default_keyspace' - `required string Token` The Astra DB Application Token to use - `required string ApiEndpoint` The Astra DB JSON API endpoint for your database - `required string CollectionName` Collection name to use. If not existing, it will be created - `required Long EmbeddingDimension` Length of the embedding vectors in use - `string ClassName` - `string? Keyspace` The keyspace to use. If not provided, 'default_keyspace' - `SupportsNestedMetadataFilters SupportsNestedMetadataFilters` - `trueTrue` - `required string Name` The name of the data sink. - `required string ProjectID` - `required SinkType SinkType` - `"ASTRA_DB"AstraDB` - `"AZUREAI_SEARCH"AzureaiSearch` - `"MILVUS"Milvus` - `"MONGODB_ATLAS"MongoDBAtlas` - `"PINECONE"Pinecone` - `"POSTGRES"Postgres` - `"QDRANT"Qdrant` - `DateTimeOffset? CreatedAt` Creation datetime - `DateTimeOffset? UpdatedAt` Update datetime - `EmbeddingModelConfig? EmbeddingModelConfig` Schema for an embedding model config. - `required string ID` Unique identifier - `required EmbeddingConfig EmbeddingConfig` The embedding configuration for the embedding model config. - `class AzureOpenAIEmbeddingConfig:` - `class BedrockEmbeddingConfig:` - `class CohereEmbeddingConfig:` - `class GeminiEmbeddingConfig:` - `class HuggingFaceInferenceApiEmbeddingConfig:` - `class OpenAIEmbeddingConfig:` - `class VertexAIEmbeddingConfig:` - `required string Name` The name of the embedding model config. - `required string ProjectID` - `DateTimeOffset? CreatedAt` Creation datetime - `DateTimeOffset? UpdatedAt` Update datetime - `string? EmbeddingModelConfigID` The ID of the EmbeddingModelConfig this pipeline is using. - `LlamaParseParameters? LlamaParseParameters` Settings that can be configured for how to use LlamaParse to parse files within a LlamaCloud pipeline. - `Boolean? AdaptiveLongTable` - `Boolean? AggressiveTableExtraction` - `Boolean? AnnotateLinks` - `Boolean? AutoMode` - `string? AutoModeConfigurationJson` - `Boolean? AutoModeTriggerOnImageInPage` - `string? AutoModeTriggerOnRegexpInPage` - `Boolean? AutoModeTriggerOnTableInPage` - `string? AutoModeTriggerOnTextInPage` - `string? AzureOpenAIApiVersion` - `string? AzureOpenAIDeploymentName` - `string? AzureOpenAIEndpoint` - `string? AzureOpenAIKey` - `Double? BboxBottom` - `Double? BboxLeft` - `Double? BboxRight` - `Double? BboxTop` - `string? BoundingBox` - `Boolean? CompactMarkdownTable` - `string? ComplementalFormattingInstruction` - `string? ConfidenceScoreEffort` - `string? ContentGuidelineInstruction` - `Boolean? ContinuousMode` - `Boolean? DisableImageExtraction` - `Boolean? DisableOcr` - `Boolean? DisableReconstruction` - `Boolean? DoNotCache` - `Boolean? DoNotUnrollColumns` - `Boolean? EnableCostOptimizer` - `Boolean? ExtractCharts` - `Boolean? ExtractLayout` - `Boolean? ExtractPrintedPageNumber` - `Boolean? FastMode` - `string? FormattingInstruction` - `string? Gpt4oApiKey` - `Boolean? Gpt4oMode` - `Boolean? GuessXlsxSheetName` - `Boolean? HideFooters` - `Boolean? HideHeaders` - `Boolean? HighResOcr` - `Boolean? HtmlMakeAllElementsVisible` - `Boolean? HtmlRemoveFixedElements` - `Boolean? HtmlRemoveNavigationElements` - `string? HttpProxy` - `Boolean? IgnoreDocumentElementsForLayoutDetection` - `IReadOnlyList? ImagesToSave` - `"embedded"Embedded` - `"layout"Layout` - `"screenshot"Screenshot` - `Boolean? InlineImagesInMarkdown` - `string? InputS3Path` - `string? InputS3Region` - `string? InputUrl` - `Boolean? InternalIsScreenshotJob` - `Boolean? InvalidateCache` - `Boolean? IsFormattingInstruction` - `Double? JobTimeoutExtraTimePerPageInSeconds` - `Double? JobTimeoutInSeconds` - `Boolean? KeepPageSeparatorWhenMergingTables` - `IReadOnlyList Languages` - `"abq"Abq` - `"ady"Ady` - `"af"Af` - `"ang"Ang` - `"ar"Ar` - `"as"As` - `"ava"Ava` - `"az"Az` - `"be"Be` - `"bg"Bg` - `"bgc"Bgc` - `"bh"Bh` - `"bho"Bho` - `"bn"Bn` - `"bs"Bs` - `"ch_sim"ChSim` - `"ch_tra"ChTra` - `"che"Che` - `"cs"Cs` - `"cy"Cy` - `"da"Da` - `"dar"Dar` - `"de"De` - `"en"En` - `"es"Es` - `"et"Et` - `"fa"Fa` - `"fr"Fr` - `"ga"Ga` - `"gom"Gom` - `"hi"Hi` - `"hr"Hr` - `"hu"Hu` - `"id"ID` - `"inh"Inh` - `"is"Is` - `"it"It` - `"ja"Ja` - `"kbd"Kbd` - `"kn"Kn` - `"ko"Ko` - `"ku"Ku` - `"la"La` - `"lbe"Lbe` - `"lez"Lez` - `"lt"Lt` - `"lv"Lv` - `"mah"Mah` - `"mai"Mai` - `"mi"Mi` - `"mn"Mn` - `"mni"Mni` - `"mr"Mr` - `"ms"Ms` - `"mt"Mt` - `"ne"Ne` - `"new"New` - `"nl"Nl` - `"no"No` - `"oc"Oc` - `"pi"Pi` - `"pl"Pl` - `"pt"Pt` - `"ro"Ro` - `"rs_cyrillic"RsCyrillic` - `"rs_latin"RsLatin` - `"ru"Ru` - `"sa"Sa` - `"sck"Sck` - `"sk"Sk` - `"sl"Sl` - `"sq"Sq` - `"sv"Sv` - `"sw"Sw` - `"ta"Ta` - `"tab"Tab` - `"te"Te` - `"th"Th` - `"tjk"Tjk` - `"tl"Tl` - `"tr"Tr` - `"ug"Ug` - `"uk"Uk` - `"ur"Ur` - `"uz"Uz` - `"vi"Vi` - `Boolean? LayoutAware` - `Boolean? LineLevelBoundingBox` - `string? MarkdownTableMultilineHeaderSeparator` - `Long? MaxPages` - `Long? MaxPagesEnforced` - `Boolean? MergeTablesAcrossPagesInMarkdown` - `string? Model` - `Boolean? OutlinedTableExtraction` - `Boolean? OutputPdfOfDocument` - `string? OutputS3PathPrefix` - `string? OutputS3Region` - `Boolean? OutputTablesAsHtml` - `Double? PageErrorTolerance` - `string? PageFooterPrefix` - `string? PageFooterSuffix` - `string? PageHeaderPrefix` - `string? PageHeaderSuffix` - `string? PagePrefix` - `string? PageSeparator` - `string? PageSuffix` - `ParsingMode? ParseMode` Enum for representing the mode of parsing to be used. - `"parse_document_with_agent"ParseDocumentWithAgent` - `"parse_document_with_llm"ParseDocumentWithLlm` - `"parse_document_with_lvm"ParseDocumentWithLvm` - `"parse_page_with_agent"ParsePageWithAgent` - `"parse_page_with_layout_agent"ParsePageWithLayoutAgent` - `"parse_page_with_llm"ParsePageWithLlm` - `"parse_page_with_lvm"ParsePageWithLvm` - `"parse_page_without_llm"ParsePageWithoutLlm` - `string? ParsingInstruction` - `Boolean? PreciseBoundingBox` - `Boolean? PremiumMode` - `Boolean? PresentationOutOfBoundsContent` - `Boolean? PresentationSkipEmbeddedData` - `Boolean? PreserveLayoutAlignmentAcrossPages` - `Boolean? PreserveVerySmallText` - `string? Preset` - `Priority? Priority` The priority for the request. This field may be ignored or overwritten depending on the organization tier. - `"critical"Critical` - `"high"High` - `"low"Low` - `"medium"Medium` - `string? ProjectID` - `Boolean? RemoveHiddenText` - `FailPageMode? ReplaceFailedPageMode` Enum for representing the different available page error handling modes. - `"blank_page"BlankPage` - `"error_message"ErrorMessage` - `"raw_text"RawText` - `string? ReplaceFailedPageWithErrorMessagePrefix` - `string? ReplaceFailedPageWithErrorMessageSuffix` - `Boolean? SaveImages` - `Boolean? SkipDiagonalText` - `Boolean? SpecializedChartParsingAgentic` - `Boolean? SpecializedChartParsingEfficient` - `Boolean? SpecializedChartParsingPlus` - `Boolean? SpecializedImageParsing` - `Boolean? SpreadsheetExtractSubTables` - `Boolean? SpreadsheetForceFormulaComputation` - `Boolean? SpreadsheetIncludeHiddenSheets` - `Boolean? StrictModeBuggyFont` - `Boolean? StrictModeImageExtraction` - `Boolean? StrictModeImageOcr` - `Boolean? StrictModeReconstruction` - `Boolean? StructuredOutput` - `string? StructuredOutputJsonSchema` - `string? StructuredOutputJsonSchemaName` - `string? SystemPrompt` - `string? SystemPromptAppend` - `Boolean? TakeScreenshot` - `string? TargetPages` - `string? Tier` - `Boolean? UseVendorMultimodalModel` - `string? UserPrompt` - `string? VendorMultimodalApiKey` - `string? VendorMultimodalModelName` - `string? Version` - `IReadOnlyList? WebhookConfigurations` Outbound webhook endpoints to notify on job status changes - `IReadOnlyList? WebhookEvents` Events to subscribe to (e.g. 'parse.success', 'extract.error'). If null, all events are delivered. - `"classify.cancelled"ClassifyCancelled` - `"classify.error"ClassifyError` - `"classify.partial_success"ClassifyPartialSuccess` - `"classify.pending"ClassifyPending` - `"classify.running"ClassifyRunning` - `"classify.success"ClassifySuccess` - `"extract.cancelled"ExtractCancelled` - `"extract.error"ExtractError` - `"extract.partial_success"ExtractPartialSuccess` - `"extract.pending"ExtractPending` - `"extract.success"ExtractSuccess` - `"parse.cancelled"ParseCancelled` - `"parse.error"ParseError` - `"parse.partial_success"ParsePartialSuccess` - `"parse.pending"ParsePending` - `"parse.running"ParseRunning` - `"parse.success"ParseSuccess` - `"sheets.cancelled"SheetsCancelled` - `"sheets.error"SheetsError` - `"sheets.partial_success"SheetsPartialSuccess` - `"sheets.pending"SheetsPending` - `"sheets.success"SheetsSuccess` - `"split.cancelled"SplitCancelled` - `"split.error"SplitError` - `"split.pending"SplitPending` - `"split.processing"SplitProcessing` - `"split.success"SplitSuccess` - `"unmapped_event"UnmappedEvent` - `IReadOnlyDictionary? WebhookHeaders` Custom HTTP headers sent with each webhook request (e.g. auth tokens) - `string? WebhookOutputFormat` Response format sent to the webhook: 'string' (default) or 'json' - `string? WebhookSigningSecret` Shared signing secret used to sign webhook deliveries. When set, each request includes an HMAC-SHA256 signature of the request body in the 'LC-Signature' header (value 'sha256='). Recompute the HMAC over the raw request body with this secret to verify the delivery is authentic. - `string? WebhookUrl` URL to receive webhook POST notifications - `string? WebhookUrl` - `string? ManagedPipelineID` The ID of the ManagedPipeline this playground pipeline is linked to. - `PipelineMetadataConfig? MetadataConfig` Metadata configuration for the pipeline. - `IReadOnlyList ExcludedEmbedMetadataKeys` List of metadata keys to exclude from embeddings - `IReadOnlyList ExcludedLlmMetadataKeys` List of metadata keys to exclude from LLM during retrieval - `PipelineType PipelineType` Type of pipeline. Either PLAYGROUND or MANAGED. - `"MANAGED"Managed` - `"PLAYGROUND"Playground` - `PresetRetrievalParams PresetRetrievalParameters` Preset retrieval parameters for the pipeline. - `Double? Alpha` Alpha value for hybrid retrieval to determine the weights between dense and sparse retrieval. 0 is sparse retrieval and 1 is dense retrieval. - `string ClassName` - `Double? DenseSimilarityCutoff` Minimum similarity score wrt query for retrieval - `Long? DenseSimilarityTopK` Number of nodes for dense retrieval. - `Boolean? EnableReranking` Enable reranking for retrieval - `Long? FilesTopK` Number of files to retrieve (only for retrieval mode files_via_metadata and files_via_content). - `Long? RerankTopN` Number of reranked nodes for returning. - `RetrievalMode RetrievalMode` The retrieval mode for the query. - `"auto_routed"AutoRouted` - `"chunks"Chunks` - `"files_via_content"FilesViaContent` - `"files_via_metadata"FilesViaMetadata` - `Boolean RetrieveImageNodes` Whether to retrieve image nodes. - `Boolean RetrievePageFigureNodes` Whether to retrieve page figure nodes. - `Boolean RetrievePageScreenshotNodes` Whether to retrieve page screenshot nodes. - `MetadataFilters? SearchFilters` Metadata filters for vector stores. - `required IReadOnlyList Filters` - `class MetadataFilter:` Comprehensive metadata filter for vector stores to support more operators. Value uses Strict types, as int, float and str are compatible types and were all converted to string before. See: https://docs.pydantic.dev/latest/usage/types/#strict-types - `required string Key` - `required Value? Value` - `Double` - `string` - `IReadOnlyList` - `IReadOnlyList` - `IReadOnlyList` - `Operator Operator` Vector store filter operator. - `"!="` - `"<"` - `"<="` - `"=="` - `">"` - `">="` - `"all"All` - `"any"Any` - `"contains"Contains` - `"in"In` - `"is_empty"IsEmpty` - `"nin"Nin` - `"text_match"TextMatch` - `"text_match_insensitive"TextMatchInsensitive` - `class MetadataFilters:` Metadata filters for vector stores. - `Condition? Condition` Vector store filter conditions to combine different filters. - `"and"And` - `"not"Not` - `"or"Or` - `IReadOnlyDictionary? SearchFiltersInferenceSchema` JSON Schema that will be used to infer search_filters. Omit or leave as null to skip inference. - `IReadOnlyDictionary` - `IReadOnlyList` - `string` - `Double` - `Boolean` - `Long? SparseSimilarityTopK` Number of nodes for sparse retrieval. - `SparseModelConfig? SparseModelConfig` Configuration for sparse embedding models used in hybrid search. This allows users to choose between Splade and BM25 models for sparse retrieval in managed data sinks. - `string ClassName` - `ModelType ModelType` The sparse model type to use. 'bm25' uses Qdrant's FastEmbed BM25 model (default for new pipelines), 'splade' uses HuggingFace Splade model, 'auto' selects based on deployment mode (BYOC uses term frequency, Cloud uses Splade). - `"auto"Auto` - `"bm25"Bm25` - `"splade"Splade` - `Status? Status` Status of the pipeline. - `"CREATED"Created` - `"DELETING"Deleting` - `TransformConfig TransformConfig` Configuration for the transformation. - `class AutoTransformConfig:` - `Long ChunkOverlap` Chunk overlap for the transformation. - `Long ChunkSize` Chunk size for the transformation. - `Mode Mode` - `"auto"Auto` - `class AdvancedModeTransformConfig:` - `ChunkingConfig ChunkingConfig` Configuration for the chunking. - `class NoneChunkingConfig:` - `Mode Mode` - `"none"None` - `class CharacterChunkingConfig:` - `Long ChunkOverlap` - `Long ChunkSize` - `Mode Mode` - `"character"Character` - `class TokenChunkingConfig:` - `Long ChunkOverlap` - `Long ChunkSize` - `Mode Mode` - `"token"Token` - `string Separator` - `class SentenceChunkingConfig:` - `Long ChunkOverlap` - `Long ChunkSize` - `Mode Mode` - `"sentence"Sentence` - `string ParagraphSeparator` - `string Separator` - `class SemanticChunkingConfig:` - `Long BreakpointPercentileThreshold` - `Long BufferSize` - `Mode Mode` - `"semantic"Semantic` - `Mode Mode` - `"advanced"Advanced` - `SegmentationConfig SegmentationConfig` Configuration for the segmentation. - `class NoneSegmentationConfig:` - `Mode Mode` - `"none"None` - `class PageSegmentationConfig:` - `Mode Mode` - `"page"Page` - `string PageSeparator` - `class ElementSegmentationConfig:` - `Mode Mode` - `"element"Element` - `DateTimeOffset? UpdatedAt` Update datetime ### Example ```csharp PipelineCreateParams parameters = new() { Name = "x" }; var pipeline = await client.Pipelines.Create(parameters); Console.WriteLine(pipeline); ``` #### Response ```json { "id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "embedding_config": { "component": { "additional_kwargs": { "foo": "bar" }, "api_base": "api_base", "api_key": "api_key", "api_version": "api_version", "azure_deployment": "azure_deployment", "azure_endpoint": "azure_endpoint", "class_name": "class_name", "default_headers": { "foo": "string" }, "dimensions": 0, "embed_batch_size": 1, "max_retries": 0, "model_name": "model_name", "num_workers": 0, "reuse_client": true, "timeout": 0 }, "type": "AZURE_EMBEDDING" }, "name": "name", "project_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "config_hash": { "embedding_config_hash": "embedding_config_hash", "parsing_config_hash": "parsing_config_hash", "transform_config_hash": "transform_config_hash" }, "created_at": "2019-12-27T18:11:19.117Z", "data_sink": { "id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "component": { "foo": "bar" }, "name": "name", "project_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "sink_type": "ASTRA_DB", "created_at": "2019-12-27T18:11:19.117Z", "updated_at": "2019-12-27T18:11:19.117Z" }, "embedding_model_config": { "id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "embedding_config": { "component": { "additional_kwargs": { "foo": "bar" }, "api_base": "api_base", "api_key": "api_key", "api_version": "api_version", "azure_deployment": "azure_deployment", "azure_endpoint": "azure_endpoint", "class_name": "class_name", "default_headers": { "foo": "string" }, "dimensions": 0, "embed_batch_size": 1, "max_retries": 0, "model_name": "model_name", "num_workers": 0, "reuse_client": true, "timeout": 0 }, "type": "AZURE_EMBEDDING" }, "name": "name", "project_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "created_at": "2019-12-27T18:11:19.117Z", "updated_at": "2019-12-27T18:11:19.117Z" }, "embedding_model_config_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "llama_parse_parameters": { "adaptive_long_table": true, "aggressive_table_extraction": true, "annotate_links": true, "auto_mode": true, "auto_mode_configuration_json": "auto_mode_configuration_json", "auto_mode_trigger_on_image_in_page": true, "auto_mode_trigger_on_regexp_in_page": "auto_mode_trigger_on_regexp_in_page", "auto_mode_trigger_on_table_in_page": true, "auto_mode_trigger_on_text_in_page": "auto_mode_trigger_on_text_in_page", "azure_openai_api_version": "azure_openai_api_version", "azure_openai_deployment_name": "azure_openai_deployment_name", "azure_openai_endpoint": "azure_openai_endpoint", "azure_openai_key": "azure_openai_key", "bbox_bottom": 0, "bbox_left": 0, "bbox_right": 0, "bbox_top": 0, "bounding_box": "bounding_box", "compact_markdown_table": true, "complemental_formatting_instruction": "complemental_formatting_instruction", "confidence_score_effort": "confidence_score_effort", "content_guideline_instruction": "content_guideline_instruction", "continuous_mode": true, "disable_image_extraction": true, "disable_ocr": true, "disable_reconstruction": true, "do_not_cache": true, "do_not_unroll_columns": true, "enable_cost_optimizer": true, "extract_charts": true, "extract_layout": true, "extract_printed_page_number": true, "fast_mode": true, "formatting_instruction": "formatting_instruction", "gpt4o_api_key": "gpt4o_api_key", "gpt4o_mode": true, "guess_xlsx_sheet_name": true, "hide_footers": true, "hide_headers": true, "high_res_ocr": true, "html_make_all_elements_visible": true, "html_remove_fixed_elements": true, "html_remove_navigation_elements": true, "http_proxy": "http_proxy", "ignore_document_elements_for_layout_detection": true, "images_to_save": [ "embedded" ], "inline_images_in_markdown": true, "input_s3_path": "input_s3_path", "input_s3_region": "input_s3_region", "input_url": "input_url", "internal_is_screenshot_job": true, "invalidate_cache": true, "is_formatting_instruction": true, "job_timeout_extra_time_per_page_in_seconds": 0, "job_timeout_in_seconds": 0, "keep_page_separator_when_merging_tables": true, "languages": [ "abq" ], "layout_aware": true, "line_level_bounding_box": true, "markdown_table_multiline_header_separator": "markdown_table_multiline_header_separator", "max_pages": 0, "max_pages_enforced": 0, "merge_tables_across_pages_in_markdown": true, "model": "model", "outlined_table_extraction": true, "output_pdf_of_document": true, "output_s3_path_prefix": "output_s3_path_prefix", "output_s3_region": "output_s3_region", "output_tables_as_HTML": true, "page_error_tolerance": 0, "page_footer_prefix": "page_footer_prefix", "page_footer_suffix": "page_footer_suffix", "page_header_prefix": "page_header_prefix", "page_header_suffix": "page_header_suffix", "page_prefix": "page_prefix", "page_separator": "page_separator", "page_suffix": "page_suffix", "parse_mode": "parse_document_with_agent", "parsing_instruction": "parsing_instruction", "precise_bounding_box": true, "premium_mode": true, "presentation_out_of_bounds_content": true, "presentation_skip_embedded_data": true, "preserve_layout_alignment_across_pages": true, "preserve_very_small_text": true, "preset": "preset", "priority": "critical", "project_id": "project_id", "remove_hidden_text": true, "replace_failed_page_mode": "blank_page", "replace_failed_page_with_error_message_prefix": "replace_failed_page_with_error_message_prefix", "replace_failed_page_with_error_message_suffix": "replace_failed_page_with_error_message_suffix", "save_images": true, "skip_diagonal_text": true, "specialized_chart_parsing_agentic": true, "specialized_chart_parsing_efficient": true, "specialized_chart_parsing_plus": true, "specialized_image_parsing": true, "spreadsheet_extract_sub_tables": true, "spreadsheet_force_formula_computation": true, "spreadsheet_include_hidden_sheets": true, "strict_mode_buggy_font": true, "strict_mode_image_extraction": true, "strict_mode_image_ocr": true, "strict_mode_reconstruction": true, "structured_output": true, "structured_output_json_schema": "structured_output_json_schema", "structured_output_json_schema_name": "structured_output_json_schema_name", "system_prompt": "system_prompt", "system_prompt_append": "system_prompt_append", "take_screenshot": true, "target_pages": "target_pages", "tier": "tier", "use_vendor_multimodal_model": true, "user_prompt": "user_prompt", "vendor_multimodal_api_key": "vendor_multimodal_api_key", "vendor_multimodal_model_name": "vendor_multimodal_model_name", "version": "version", "webhook_configurations": [ { "webhook_events": [ "parse.success", "parse.error" ], "webhook_headers": { "Authorization": "Bearer sk-..." }, "webhook_output_format": "json", "webhook_signing_secret": "whsec_...", "webhook_url": "https://example.com/webhooks/llamacloud" } ], "webhook_url": "webhook_url" }, "managed_pipeline_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "metadata_config": { "excluded_embed_metadata_keys": [ "string" ], "excluded_llm_metadata_keys": [ "string" ] }, "pipeline_type": "MANAGED", "preset_retrieval_parameters": { "alpha": 0, "class_name": "class_name", "dense_similarity_cutoff": 0, "dense_similarity_top_k": 1, "enable_reranking": true, "files_top_k": 1, "rerank_top_n": 1, "retrieval_mode": "auto_routed", "retrieve_image_nodes": true, "retrieve_page_figure_nodes": true, "retrieve_page_screenshot_nodes": true, "search_filters": { "filters": [ { "key": "key", "value": 0, "operator": "!=" } ], "condition": "and" }, "search_filters_inference_schema": { "foo": { "foo": "bar" } }, "sparse_similarity_top_k": 1 }, "sparse_model_config": { "class_name": "class_name", "model_type": "auto" }, "status": "CREATED", "transform_config": { "chunk_overlap": 0, "chunk_size": 1, "mode": "auto" }, "updated_at": "2019-12-27T18:11:19.117Z" } ``` ## Get Pipeline `Pipeline Pipelines.Get(PipelineGetParamsparameters, CancellationTokencancellationToken = default)` **get** `/api/v1/pipelines/{pipeline_id}` Get a pipeline by ID. ### Parameters - `PipelineGetParams parameters` - `required string pipelineID` ### Returns - `class Pipeline:` Schema for a pipeline. - `required string ID` Unique identifier - `required EmbeddingConfig EmbeddingConfig` - `class AzureOpenAIEmbeddingConfig:` - `AzureOpenAIEmbedding Component` Configuration for the Azure OpenAI embedding model. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the OpenAI API. - `string ApiBase` The base URL for Azure deployment. - `string? ApiKey` The OpenAI API key. - `string ApiVersion` The version for Azure OpenAI API. - `string? AzureDeployment` The Azure deployment to use. - `string? AzureEndpoint` The Azure endpoint to use. - `string ClassName` - `IReadOnlyDictionary? DefaultHeaders` The default headers for API requests. - `Long? Dimensions` The number of dimensions on the output embedding vectors. Works only with v3 embedding models. - `Long EmbedBatchSize` The batch size for embedding calls. - `Long MaxRetries` Maximum number of retries. - `string ModelName` The name of the OpenAI embedding model. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Boolean ReuseClient` Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability. - `Double Timeout` Timeout for each request. - `Type Type` Type of the embedding model. - `"AZURE_EMBEDDING"AzureEmbedding` - `class BedrockEmbeddingConfig:` - `BedrockEmbedding Component` Configuration for the Bedrock embedding model. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the bedrock client. - `string? AwsAccessKeyID` AWS Access Key ID to use - `string? AwsSecretAccessKey` AWS Secret Access Key to use - `string? AwsSessionToken` AWS Session Token to use - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `Long MaxRetries` The maximum number of API retries. - `string ModelName` The modelId of the Bedrock model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `string? ProfileName` The name of aws profile to use. If not given, then the default profile is used. - `string? RegionName` AWS region name to use. Uses region configured in AWS CLI if not passed - `Double Timeout` The timeout for the Bedrock API request in seconds. It will be used for both connect and read timeouts. - `Type Type` Type of the embedding model. - `"BEDROCK_EMBEDDING"BedrockEmbedding` - `class CohereEmbeddingConfig:` - `CohereEmbedding Component` Configuration for the Cohere embedding model. - `required string? ApiKey` The Cohere API key. - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `string EmbeddingType` Embedding type. If not provided float embedding_type is used when needed. - `string? InputType` Model Input type. If not provided, search_document and search_query are used when needed. - `string ModelName` The modelId of the Cohere model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `string Truncate` Truncation type - START/ END/ NONE - `Type Type` Type of the embedding model. - `"COHERE_EMBEDDING"CohereEmbedding` - `class GeminiEmbeddingConfig:` - `GeminiEmbedding Component` Configuration for the Gemini embedding model. - `string? ApiBase` API base to access the model. Defaults to None. - `string? ApiKey` API key to access the model. Defaults to None. - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `string ModelName` The modelId of the Gemini model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Long? OutputDimensionality` Optional reduced dimension for output embeddings. Supported by models/text-embedding-004 and newer (e.g. gemini-embedding-001). Not supported by models/embedding-001. - `string? TaskType` The task for embedding model. - `string? Title` Title is only applicable for retrieval_document tasks, and is used to represent a document title. For other tasks, title is invalid. - `string? Transport` Transport to access the model. Defaults to None. - `Type Type` Type of the embedding model. - `"GEMINI_EMBEDDING"GeminiEmbedding` - `class HuggingFaceInferenceApiEmbeddingConfig:` - `HuggingFaceInferenceApiEmbedding Component` Configuration for the HuggingFace Inference API embedding model. - `Token? Token` Hugging Face token. Will default to the locally saved token. Pass token=False if you don’t want to send your token to the server. - `string` - `Boolean` - `string ClassName` - `IReadOnlyDictionary? Cookies` Additional cookies to send to the server. - `Long EmbedBatchSize` The batch size for embedding calls. - `IReadOnlyDictionary? Headers` Additional headers to send to the server. By default only the authorization and user-agent headers are sent. Values in this dictionary will override the default values. - `string? ModelName` Hugging Face model name. If None, the task will be used. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Pooling? Pooling` Enum of possible pooling choices with pooling behaviors. - `"cls"Cls` - `"last"Last` - `"mean"Mean` - `string? QueryInstruction` Instruction to prepend during query embedding. - `string? Task` Optional task to pick Hugging Face's recommended model, used when model_name is left as default of None. - `string? TextInstruction` Instruction to prepend during text embedding. - `Double? Timeout` The maximum number of seconds to wait for a response from the server. Loading a new model in Inference API can take up to several minutes. Defaults to None, meaning it will loop until the server is available. - `Type Type` Type of the embedding model. - `"HUGGINGFACE_API_EMBEDDING"HuggingfaceApiEmbedding` - `class ManagedOpenAIEmbedding:` - `Component Component` Configuration for the Managed OpenAI embedding model. - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `ModelName ModelName` The name of the OpenAI embedding model. - `"openai-text-embedding-3-small"OpenAITextEmbedding3Small` - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Type Type` Type of the embedding model. - `"MANAGED_OPENAI_EMBEDDING"ManagedOpenAIEmbedding` - `class OpenAIEmbeddingConfig:` - `OpenAIEmbedding Component` Configuration for the OpenAI embedding model. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the OpenAI API. - `string? ApiBase` The base URL for OpenAI API. - `string? ApiKey` The OpenAI API key. - `string? ApiVersion` The version for OpenAI API. - `string ClassName` - `IReadOnlyDictionary? DefaultHeaders` The default headers for API requests. - `Long? Dimensions` The number of dimensions on the output embedding vectors. Works only with v3 embedding models. - `Long EmbedBatchSize` The batch size for embedding calls. - `Long MaxRetries` Maximum number of retries. - `string ModelName` The name of the OpenAI embedding model. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Boolean ReuseClient` Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability. - `Double Timeout` Timeout for each request. - `Type Type` Type of the embedding model. - `"OPENAI_EMBEDDING"OpenAIEmbedding` - `class VertexAIEmbeddingConfig:` - `VertexTextEmbedding Component` Configuration for the VertexAI embedding model. - `required string? ClientEmail` The client email for the VertexAI credentials. - `required string Location` The default location to use when making API calls. - `required string? PrivateKey` The private key for the VertexAI credentials. - `required string? PrivateKeyID` The private key ID for the VertexAI credentials. - `required string Project` The default GCP project to use when making Vertex API calls. - `required string? TokenUri` The token URI for the VertexAI credentials. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the Vertex. - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `EmbedMode EmbedMode` The embedding mode to use. - `"classification"Classification` - `"clustering"Clustering` - `"default"Default` - `"retrieval"Retrieval` - `"similarity"Similarity` - `string ModelName` The modelId of the VertexAI model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Type Type` Type of the embedding model. - `"VERTEXAI_EMBEDDING"VertexaiEmbedding` - `required string Name` - `required string ProjectID` - `ConfigHash? ConfigHash` Hashes for the configuration of a pipeline. - `string? EmbeddingConfigHash` Hash of the embedding config. - `string? ParsingConfigHash` Hash of the llama parse parameters. - `string? TransformConfigHash` Hash of the transform config. - `DateTimeOffset? CreatedAt` Creation datetime - `DataSink? DataSink` Schema for a data sink. - `required string ID` Unique identifier - `required Component Component` Component that implements the data sink - `IReadOnlyDictionary` - `class CloudPineconeVectorStore:` Cloud Pinecone Vector Store. This class is used to store the configuration for a Pinecone vector store, so that it can be created and used in LlamaCloud. Args: api_key (str): API key for authenticating with Pinecone index_name (str): name of the Pinecone index namespace (optional[str]): namespace to use in the Pinecone index insert_kwargs (optional[dict]): additional kwargs to pass during insertion - `required string ApiKey` The API key for authenticating with Pinecone - `required string IndexName` - `string ClassName` - `IReadOnlyDictionary? InsertKwargs` - `string? Namespace` - `SupportsNestedMetadataFilters SupportsNestedMetadataFilters` - `trueTrue` - `class CloudPostgresVectorStore:` - `required string Database` - `required Long EmbedDim` - `required string Host` - `required string Password` - `required Long Port` - `required string SchemaName` - `required string TableName` - `required string User` - `string ClassName` - `PgVectorHnswSettings? HnswSettings` HNSW settings for PGVector. - `DistanceMethod DistanceMethod` The distance method to use. - `"cosine"Cosine` - `"hamming"Hamming` - `"ip"IP` - `"jaccard"Jaccard` - `"l1"L1` - `"l2"L2` - `Long EfConstruction` The number of edges to use during the construction phase. - `Long EfSearch` The number of edges to use during the search phase. - `Long M` The number of bi-directional links created for each new element. - `VectorType VectorType` The type of vector to use. - `"bit"Bit` - `"half_vec"HalfVec` - `"sparse_vec"SparseVec` - `"vector"Vector` - `Boolean? HybridSearch` - `Boolean PerformSetup` - `Boolean SupportsNestedMetadataFilters` - `class CloudQdrantVectorStore:` Cloud Qdrant Vector Store. This class is used to store the configuration for a Qdrant vector store, so that it can be created and used in LlamaCloud. Args: collection_name (str): name of the Qdrant collection url (str): url of the Qdrant instance api_key (str): API key for authenticating with Qdrant max_retries (int): maximum number of retries in case of a failure. Defaults to 3 client_kwargs (dict): additional kwargs to pass to the Qdrant client - `required string ApiKey` - `required string CollectionName` - `required string Url` - `string ClassName` - `IReadOnlyDictionary ClientKwargs` - `Long MaxRetries` - `SupportsNestedMetadataFilters SupportsNestedMetadataFilters` - `trueTrue` - `class CloudAzureAISearchVectorStore:` Cloud Azure AI Search Vector Store. - `required string SearchServiceApiKey` - `required string SearchServiceEndpoint` - `string ClassName` - `string? ClientID` - `string? ClientSecret` - `Long? EmbeddingDimension` - `IReadOnlyDictionary? FilterableMetadataFieldKeys` - `string? IndexName` - `string? SearchServiceApiVersion` - `SupportsNestedMetadataFilters SupportsNestedMetadataFilters` - `trueTrue` - `string? TenantID` - `class CloudMongoDBAtlasVectorSearch:` Cloud MongoDB Atlas Vector Store. This class is used to store the configuration for a MongoDB Atlas vector store, so that it can be created and used in LlamaCloud. Args: mongodb_uri (str): URI for connecting to MongoDB Atlas db_name (str): name of the MongoDB database collection_name (str): name of the MongoDB collection vector_index_name (str): name of the MongoDB Atlas vector index fulltext_index_name (str): name of the MongoDB Atlas full-text index - `required string CollectionName` - `required string DBName` - `required string MongoDBUri` - `string ClassName` - `Long? EmbeddingDimension` - `string? FulltextIndexName` - `Boolean SupportsNestedMetadataFilters` - `string? VectorIndexName` - `class CloudMilvusVectorStore:` Cloud Milvus Vector Store. - `required string Uri` - `string? Token` - `string ClassName` - `string? CollectionName` - `Long? EmbeddingDimension` - `Boolean SupportsNestedMetadataFilters` - `class CloudAstraDBVectorStore:` Cloud AstraDB Vector Store. This class is used to store the configuration for an AstraDB vector store, so that it can be created and used in LlamaCloud. Args: token (str): The Astra DB Application Token to use. api_endpoint (str): The Astra DB JSON API endpoint for your database. collection_name (str): Collection name to use. If not existing, it will be created. embedding_dimension (int): Length of the embedding vectors in use. keyspace (optional[str]): The keyspace to use. If not provided, 'default_keyspace' - `required string Token` The Astra DB Application Token to use - `required string ApiEndpoint` The Astra DB JSON API endpoint for your database - `required string CollectionName` Collection name to use. If not existing, it will be created - `required Long EmbeddingDimension` Length of the embedding vectors in use - `string ClassName` - `string? Keyspace` The keyspace to use. If not provided, 'default_keyspace' - `SupportsNestedMetadataFilters SupportsNestedMetadataFilters` - `trueTrue` - `required string Name` The name of the data sink. - `required string ProjectID` - `required SinkType SinkType` - `"ASTRA_DB"AstraDB` - `"AZUREAI_SEARCH"AzureaiSearch` - `"MILVUS"Milvus` - `"MONGODB_ATLAS"MongoDBAtlas` - `"PINECONE"Pinecone` - `"POSTGRES"Postgres` - `"QDRANT"Qdrant` - `DateTimeOffset? CreatedAt` Creation datetime - `DateTimeOffset? UpdatedAt` Update datetime - `EmbeddingModelConfig? EmbeddingModelConfig` Schema for an embedding model config. - `required string ID` Unique identifier - `required EmbeddingConfig EmbeddingConfig` The embedding configuration for the embedding model config. - `class AzureOpenAIEmbeddingConfig:` - `class BedrockEmbeddingConfig:` - `class CohereEmbeddingConfig:` - `class GeminiEmbeddingConfig:` - `class HuggingFaceInferenceApiEmbeddingConfig:` - `class OpenAIEmbeddingConfig:` - `class VertexAIEmbeddingConfig:` - `required string Name` The name of the embedding model config. - `required string ProjectID` - `DateTimeOffset? CreatedAt` Creation datetime - `DateTimeOffset? UpdatedAt` Update datetime - `string? EmbeddingModelConfigID` The ID of the EmbeddingModelConfig this pipeline is using. - `LlamaParseParameters? LlamaParseParameters` Settings that can be configured for how to use LlamaParse to parse files within a LlamaCloud pipeline. - `Boolean? AdaptiveLongTable` - `Boolean? AggressiveTableExtraction` - `Boolean? AnnotateLinks` - `Boolean? AutoMode` - `string? AutoModeConfigurationJson` - `Boolean? AutoModeTriggerOnImageInPage` - `string? AutoModeTriggerOnRegexpInPage` - `Boolean? AutoModeTriggerOnTableInPage` - `string? AutoModeTriggerOnTextInPage` - `string? AzureOpenAIApiVersion` - `string? AzureOpenAIDeploymentName` - `string? AzureOpenAIEndpoint` - `string? AzureOpenAIKey` - `Double? BboxBottom` - `Double? BboxLeft` - `Double? BboxRight` - `Double? BboxTop` - `string? BoundingBox` - `Boolean? CompactMarkdownTable` - `string? ComplementalFormattingInstruction` - `string? ConfidenceScoreEffort` - `string? ContentGuidelineInstruction` - `Boolean? ContinuousMode` - `Boolean? DisableImageExtraction` - `Boolean? DisableOcr` - `Boolean? DisableReconstruction` - `Boolean? DoNotCache` - `Boolean? DoNotUnrollColumns` - `Boolean? EnableCostOptimizer` - `Boolean? ExtractCharts` - `Boolean? ExtractLayout` - `Boolean? ExtractPrintedPageNumber` - `Boolean? FastMode` - `string? FormattingInstruction` - `string? Gpt4oApiKey` - `Boolean? Gpt4oMode` - `Boolean? GuessXlsxSheetName` - `Boolean? HideFooters` - `Boolean? HideHeaders` - `Boolean? HighResOcr` - `Boolean? HtmlMakeAllElementsVisible` - `Boolean? HtmlRemoveFixedElements` - `Boolean? HtmlRemoveNavigationElements` - `string? HttpProxy` - `Boolean? IgnoreDocumentElementsForLayoutDetection` - `IReadOnlyList? ImagesToSave` - `"embedded"Embedded` - `"layout"Layout` - `"screenshot"Screenshot` - `Boolean? InlineImagesInMarkdown` - `string? InputS3Path` - `string? InputS3Region` - `string? InputUrl` - `Boolean? InternalIsScreenshotJob` - `Boolean? InvalidateCache` - `Boolean? IsFormattingInstruction` - `Double? JobTimeoutExtraTimePerPageInSeconds` - `Double? JobTimeoutInSeconds` - `Boolean? KeepPageSeparatorWhenMergingTables` - `IReadOnlyList Languages` - `"abq"Abq` - `"ady"Ady` - `"af"Af` - `"ang"Ang` - `"ar"Ar` - `"as"As` - `"ava"Ava` - `"az"Az` - `"be"Be` - `"bg"Bg` - `"bgc"Bgc` - `"bh"Bh` - `"bho"Bho` - `"bn"Bn` - `"bs"Bs` - `"ch_sim"ChSim` - `"ch_tra"ChTra` - `"che"Che` - `"cs"Cs` - `"cy"Cy` - `"da"Da` - `"dar"Dar` - `"de"De` - `"en"En` - `"es"Es` - `"et"Et` - `"fa"Fa` - `"fr"Fr` - `"ga"Ga` - `"gom"Gom` - `"hi"Hi` - `"hr"Hr` - `"hu"Hu` - `"id"ID` - `"inh"Inh` - `"is"Is` - `"it"It` - `"ja"Ja` - `"kbd"Kbd` - `"kn"Kn` - `"ko"Ko` - `"ku"Ku` - `"la"La` - `"lbe"Lbe` - `"lez"Lez` - `"lt"Lt` - `"lv"Lv` - `"mah"Mah` - `"mai"Mai` - `"mi"Mi` - `"mn"Mn` - `"mni"Mni` - `"mr"Mr` - `"ms"Ms` - `"mt"Mt` - `"ne"Ne` - `"new"New` - `"nl"Nl` - `"no"No` - `"oc"Oc` - `"pi"Pi` - `"pl"Pl` - `"pt"Pt` - `"ro"Ro` - `"rs_cyrillic"RsCyrillic` - `"rs_latin"RsLatin` - `"ru"Ru` - `"sa"Sa` - `"sck"Sck` - `"sk"Sk` - `"sl"Sl` - `"sq"Sq` - `"sv"Sv` - `"sw"Sw` - `"ta"Ta` - `"tab"Tab` - `"te"Te` - `"th"Th` - `"tjk"Tjk` - `"tl"Tl` - `"tr"Tr` - `"ug"Ug` - `"uk"Uk` - `"ur"Ur` - `"uz"Uz` - `"vi"Vi` - `Boolean? LayoutAware` - `Boolean? LineLevelBoundingBox` - `string? MarkdownTableMultilineHeaderSeparator` - `Long? MaxPages` - `Long? MaxPagesEnforced` - `Boolean? MergeTablesAcrossPagesInMarkdown` - `string? Model` - `Boolean? OutlinedTableExtraction` - `Boolean? OutputPdfOfDocument` - `string? OutputS3PathPrefix` - `string? OutputS3Region` - `Boolean? OutputTablesAsHtml` - `Double? PageErrorTolerance` - `string? PageFooterPrefix` - `string? PageFooterSuffix` - `string? PageHeaderPrefix` - `string? PageHeaderSuffix` - `string? PagePrefix` - `string? PageSeparator` - `string? PageSuffix` - `ParsingMode? ParseMode` Enum for representing the mode of parsing to be used. - `"parse_document_with_agent"ParseDocumentWithAgent` - `"parse_document_with_llm"ParseDocumentWithLlm` - `"parse_document_with_lvm"ParseDocumentWithLvm` - `"parse_page_with_agent"ParsePageWithAgent` - `"parse_page_with_layout_agent"ParsePageWithLayoutAgent` - `"parse_page_with_llm"ParsePageWithLlm` - `"parse_page_with_lvm"ParsePageWithLvm` - `"parse_page_without_llm"ParsePageWithoutLlm` - `string? ParsingInstruction` - `Boolean? PreciseBoundingBox` - `Boolean? PremiumMode` - `Boolean? PresentationOutOfBoundsContent` - `Boolean? PresentationSkipEmbeddedData` - `Boolean? PreserveLayoutAlignmentAcrossPages` - `Boolean? PreserveVerySmallText` - `string? Preset` - `Priority? Priority` The priority for the request. This field may be ignored or overwritten depending on the organization tier. - `"critical"Critical` - `"high"High` - `"low"Low` - `"medium"Medium` - `string? ProjectID` - `Boolean? RemoveHiddenText` - `FailPageMode? ReplaceFailedPageMode` Enum for representing the different available page error handling modes. - `"blank_page"BlankPage` - `"error_message"ErrorMessage` - `"raw_text"RawText` - `string? ReplaceFailedPageWithErrorMessagePrefix` - `string? ReplaceFailedPageWithErrorMessageSuffix` - `Boolean? SaveImages` - `Boolean? SkipDiagonalText` - `Boolean? SpecializedChartParsingAgentic` - `Boolean? SpecializedChartParsingEfficient` - `Boolean? SpecializedChartParsingPlus` - `Boolean? SpecializedImageParsing` - `Boolean? SpreadsheetExtractSubTables` - `Boolean? SpreadsheetForceFormulaComputation` - `Boolean? SpreadsheetIncludeHiddenSheets` - `Boolean? StrictModeBuggyFont` - `Boolean? StrictModeImageExtraction` - `Boolean? StrictModeImageOcr` - `Boolean? StrictModeReconstruction` - `Boolean? StructuredOutput` - `string? StructuredOutputJsonSchema` - `string? StructuredOutputJsonSchemaName` - `string? SystemPrompt` - `string? SystemPromptAppend` - `Boolean? TakeScreenshot` - `string? TargetPages` - `string? Tier` - `Boolean? UseVendorMultimodalModel` - `string? UserPrompt` - `string? VendorMultimodalApiKey` - `string? VendorMultimodalModelName` - `string? Version` - `IReadOnlyList? WebhookConfigurations` Outbound webhook endpoints to notify on job status changes - `IReadOnlyList? WebhookEvents` Events to subscribe to (e.g. 'parse.success', 'extract.error'). If null, all events are delivered. - `"classify.cancelled"ClassifyCancelled` - `"classify.error"ClassifyError` - `"classify.partial_success"ClassifyPartialSuccess` - `"classify.pending"ClassifyPending` - `"classify.running"ClassifyRunning` - `"classify.success"ClassifySuccess` - `"extract.cancelled"ExtractCancelled` - `"extract.error"ExtractError` - `"extract.partial_success"ExtractPartialSuccess` - `"extract.pending"ExtractPending` - `"extract.success"ExtractSuccess` - `"parse.cancelled"ParseCancelled` - `"parse.error"ParseError` - `"parse.partial_success"ParsePartialSuccess` - `"parse.pending"ParsePending` - `"parse.running"ParseRunning` - `"parse.success"ParseSuccess` - `"sheets.cancelled"SheetsCancelled` - `"sheets.error"SheetsError` - `"sheets.partial_success"SheetsPartialSuccess` - `"sheets.pending"SheetsPending` - `"sheets.success"SheetsSuccess` - `"split.cancelled"SplitCancelled` - `"split.error"SplitError` - `"split.pending"SplitPending` - `"split.processing"SplitProcessing` - `"split.success"SplitSuccess` - `"unmapped_event"UnmappedEvent` - `IReadOnlyDictionary? WebhookHeaders` Custom HTTP headers sent with each webhook request (e.g. auth tokens) - `string? WebhookOutputFormat` Response format sent to the webhook: 'string' (default) or 'json' - `string? WebhookSigningSecret` Shared signing secret used to sign webhook deliveries. When set, each request includes an HMAC-SHA256 signature of the request body in the 'LC-Signature' header (value 'sha256='). Recompute the HMAC over the raw request body with this secret to verify the delivery is authentic. - `string? WebhookUrl` URL to receive webhook POST notifications - `string? WebhookUrl` - `string? ManagedPipelineID` The ID of the ManagedPipeline this playground pipeline is linked to. - `PipelineMetadataConfig? MetadataConfig` Metadata configuration for the pipeline. - `IReadOnlyList ExcludedEmbedMetadataKeys` List of metadata keys to exclude from embeddings - `IReadOnlyList ExcludedLlmMetadataKeys` List of metadata keys to exclude from LLM during retrieval - `PipelineType PipelineType` Type of pipeline. Either PLAYGROUND or MANAGED. - `"MANAGED"Managed` - `"PLAYGROUND"Playground` - `PresetRetrievalParams PresetRetrievalParameters` Preset retrieval parameters for the pipeline. - `Double? Alpha` Alpha value for hybrid retrieval to determine the weights between dense and sparse retrieval. 0 is sparse retrieval and 1 is dense retrieval. - `string ClassName` - `Double? DenseSimilarityCutoff` Minimum similarity score wrt query for retrieval - `Long? DenseSimilarityTopK` Number of nodes for dense retrieval. - `Boolean? EnableReranking` Enable reranking for retrieval - `Long? FilesTopK` Number of files to retrieve (only for retrieval mode files_via_metadata and files_via_content). - `Long? RerankTopN` Number of reranked nodes for returning. - `RetrievalMode RetrievalMode` The retrieval mode for the query. - `"auto_routed"AutoRouted` - `"chunks"Chunks` - `"files_via_content"FilesViaContent` - `"files_via_metadata"FilesViaMetadata` - `Boolean RetrieveImageNodes` Whether to retrieve image nodes. - `Boolean RetrievePageFigureNodes` Whether to retrieve page figure nodes. - `Boolean RetrievePageScreenshotNodes` Whether to retrieve page screenshot nodes. - `MetadataFilters? SearchFilters` Metadata filters for vector stores. - `required IReadOnlyList Filters` - `class MetadataFilter:` Comprehensive metadata filter for vector stores to support more operators. Value uses Strict types, as int, float and str are compatible types and were all converted to string before. See: https://docs.pydantic.dev/latest/usage/types/#strict-types - `required string Key` - `required Value? Value` - `Double` - `string` - `IReadOnlyList` - `IReadOnlyList` - `IReadOnlyList` - `Operator Operator` Vector store filter operator. - `"!="` - `"<"` - `"<="` - `"=="` - `">"` - `">="` - `"all"All` - `"any"Any` - `"contains"Contains` - `"in"In` - `"is_empty"IsEmpty` - `"nin"Nin` - `"text_match"TextMatch` - `"text_match_insensitive"TextMatchInsensitive` - `class MetadataFilters:` Metadata filters for vector stores. - `Condition? Condition` Vector store filter conditions to combine different filters. - `"and"And` - `"not"Not` - `"or"Or` - `IReadOnlyDictionary? SearchFiltersInferenceSchema` JSON Schema that will be used to infer search_filters. Omit or leave as null to skip inference. - `IReadOnlyDictionary` - `IReadOnlyList` - `string` - `Double` - `Boolean` - `Long? SparseSimilarityTopK` Number of nodes for sparse retrieval. - `SparseModelConfig? SparseModelConfig` Configuration for sparse embedding models used in hybrid search. This allows users to choose between Splade and BM25 models for sparse retrieval in managed data sinks. - `string ClassName` - `ModelType ModelType` The sparse model type to use. 'bm25' uses Qdrant's FastEmbed BM25 model (default for new pipelines), 'splade' uses HuggingFace Splade model, 'auto' selects based on deployment mode (BYOC uses term frequency, Cloud uses Splade). - `"auto"Auto` - `"bm25"Bm25` - `"splade"Splade` - `Status? Status` Status of the pipeline. - `"CREATED"Created` - `"DELETING"Deleting` - `TransformConfig TransformConfig` Configuration for the transformation. - `class AutoTransformConfig:` - `Long ChunkOverlap` Chunk overlap for the transformation. - `Long ChunkSize` Chunk size for the transformation. - `Mode Mode` - `"auto"Auto` - `class AdvancedModeTransformConfig:` - `ChunkingConfig ChunkingConfig` Configuration for the chunking. - `class NoneChunkingConfig:` - `Mode Mode` - `"none"None` - `class CharacterChunkingConfig:` - `Long ChunkOverlap` - `Long ChunkSize` - `Mode Mode` - `"character"Character` - `class TokenChunkingConfig:` - `Long ChunkOverlap` - `Long ChunkSize` - `Mode Mode` - `"token"Token` - `string Separator` - `class SentenceChunkingConfig:` - `Long ChunkOverlap` - `Long ChunkSize` - `Mode Mode` - `"sentence"Sentence` - `string ParagraphSeparator` - `string Separator` - `class SemanticChunkingConfig:` - `Long BreakpointPercentileThreshold` - `Long BufferSize` - `Mode Mode` - `"semantic"Semantic` - `Mode Mode` - `"advanced"Advanced` - `SegmentationConfig SegmentationConfig` Configuration for the segmentation. - `class NoneSegmentationConfig:` - `Mode Mode` - `"none"None` - `class PageSegmentationConfig:` - `Mode Mode` - `"page"Page` - `string PageSeparator` - `class ElementSegmentationConfig:` - `Mode Mode` - `"element"Element` - `DateTimeOffset? UpdatedAt` Update datetime ### Example ```csharp PipelineGetParams parameters = new() { PipelineID = "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e" }; var pipeline = await client.Pipelines.Get(parameters); Console.WriteLine(pipeline); ``` #### Response ```json { "id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "embedding_config": { "component": { "additional_kwargs": { "foo": "bar" }, "api_base": "api_base", "api_key": "api_key", "api_version": "api_version", "azure_deployment": "azure_deployment", "azure_endpoint": "azure_endpoint", "class_name": "class_name", "default_headers": { "foo": "string" }, "dimensions": 0, "embed_batch_size": 1, "max_retries": 0, "model_name": "model_name", "num_workers": 0, "reuse_client": true, "timeout": 0 }, "type": "AZURE_EMBEDDING" }, "name": "name", "project_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "config_hash": { "embedding_config_hash": "embedding_config_hash", "parsing_config_hash": "parsing_config_hash", "transform_config_hash": "transform_config_hash" }, "created_at": "2019-12-27T18:11:19.117Z", "data_sink": { "id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "component": { "foo": "bar" }, "name": "name", "project_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "sink_type": "ASTRA_DB", "created_at": "2019-12-27T18:11:19.117Z", "updated_at": "2019-12-27T18:11:19.117Z" }, "embedding_model_config": { "id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "embedding_config": { "component": { "additional_kwargs": { "foo": "bar" }, "api_base": "api_base", "api_key": "api_key", "api_version": "api_version", "azure_deployment": "azure_deployment", "azure_endpoint": "azure_endpoint", "class_name": "class_name", "default_headers": { "foo": "string" }, "dimensions": 0, "embed_batch_size": 1, "max_retries": 0, "model_name": "model_name", "num_workers": 0, "reuse_client": true, "timeout": 0 }, "type": "AZURE_EMBEDDING" }, "name": "name", "project_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "created_at": "2019-12-27T18:11:19.117Z", "updated_at": "2019-12-27T18:11:19.117Z" }, "embedding_model_config_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "llama_parse_parameters": { "adaptive_long_table": true, "aggressive_table_extraction": true, "annotate_links": true, "auto_mode": true, "auto_mode_configuration_json": "auto_mode_configuration_json", "auto_mode_trigger_on_image_in_page": true, "auto_mode_trigger_on_regexp_in_page": "auto_mode_trigger_on_regexp_in_page", "auto_mode_trigger_on_table_in_page": true, "auto_mode_trigger_on_text_in_page": "auto_mode_trigger_on_text_in_page", "azure_openai_api_version": "azure_openai_api_version", "azure_openai_deployment_name": "azure_openai_deployment_name", "azure_openai_endpoint": "azure_openai_endpoint", "azure_openai_key": "azure_openai_key", "bbox_bottom": 0, "bbox_left": 0, "bbox_right": 0, "bbox_top": 0, "bounding_box": "bounding_box", "compact_markdown_table": true, "complemental_formatting_instruction": "complemental_formatting_instruction", "confidence_score_effort": "confidence_score_effort", "content_guideline_instruction": "content_guideline_instruction", "continuous_mode": true, "disable_image_extraction": true, "disable_ocr": true, "disable_reconstruction": true, "do_not_cache": true, "do_not_unroll_columns": true, "enable_cost_optimizer": true, "extract_charts": true, "extract_layout": true, "extract_printed_page_number": true, "fast_mode": true, "formatting_instruction": "formatting_instruction", "gpt4o_api_key": "gpt4o_api_key", "gpt4o_mode": true, "guess_xlsx_sheet_name": true, "hide_footers": true, "hide_headers": true, "high_res_ocr": true, "html_make_all_elements_visible": true, "html_remove_fixed_elements": true, "html_remove_navigation_elements": true, "http_proxy": "http_proxy", "ignore_document_elements_for_layout_detection": true, "images_to_save": [ "embedded" ], "inline_images_in_markdown": true, "input_s3_path": "input_s3_path", "input_s3_region": "input_s3_region", "input_url": "input_url", "internal_is_screenshot_job": true, "invalidate_cache": true, "is_formatting_instruction": true, "job_timeout_extra_time_per_page_in_seconds": 0, "job_timeout_in_seconds": 0, "keep_page_separator_when_merging_tables": true, "languages": [ "abq" ], "layout_aware": true, "line_level_bounding_box": true, "markdown_table_multiline_header_separator": "markdown_table_multiline_header_separator", "max_pages": 0, "max_pages_enforced": 0, "merge_tables_across_pages_in_markdown": true, "model": "model", "outlined_table_extraction": true, "output_pdf_of_document": true, "output_s3_path_prefix": "output_s3_path_prefix", "output_s3_region": "output_s3_region", "output_tables_as_HTML": true, "page_error_tolerance": 0, "page_footer_prefix": "page_footer_prefix", "page_footer_suffix": "page_footer_suffix", "page_header_prefix": "page_header_prefix", "page_header_suffix": "page_header_suffix", "page_prefix": "page_prefix", "page_separator": "page_separator", "page_suffix": "page_suffix", "parse_mode": "parse_document_with_agent", "parsing_instruction": "parsing_instruction", "precise_bounding_box": true, "premium_mode": true, "presentation_out_of_bounds_content": true, "presentation_skip_embedded_data": true, "preserve_layout_alignment_across_pages": true, "preserve_very_small_text": true, "preset": "preset", "priority": "critical", "project_id": "project_id", "remove_hidden_text": true, "replace_failed_page_mode": "blank_page", "replace_failed_page_with_error_message_prefix": "replace_failed_page_with_error_message_prefix", "replace_failed_page_with_error_message_suffix": "replace_failed_page_with_error_message_suffix", "save_images": true, "skip_diagonal_text": true, "specialized_chart_parsing_agentic": true, "specialized_chart_parsing_efficient": true, "specialized_chart_parsing_plus": true, "specialized_image_parsing": true, "spreadsheet_extract_sub_tables": true, "spreadsheet_force_formula_computation": true, "spreadsheet_include_hidden_sheets": true, "strict_mode_buggy_font": true, "strict_mode_image_extraction": true, "strict_mode_image_ocr": true, "strict_mode_reconstruction": true, "structured_output": true, "structured_output_json_schema": "structured_output_json_schema", "structured_output_json_schema_name": "structured_output_json_schema_name", "system_prompt": "system_prompt", "system_prompt_append": "system_prompt_append", "take_screenshot": true, "target_pages": "target_pages", "tier": "tier", "use_vendor_multimodal_model": true, "user_prompt": "user_prompt", "vendor_multimodal_api_key": "vendor_multimodal_api_key", "vendor_multimodal_model_name": "vendor_multimodal_model_name", "version": "version", "webhook_configurations": [ { "webhook_events": [ "parse.success", "parse.error" ], "webhook_headers": { "Authorization": "Bearer sk-..." }, "webhook_output_format": "json", "webhook_signing_secret": "whsec_...", "webhook_url": "https://example.com/webhooks/llamacloud" } ], "webhook_url": "webhook_url" }, "managed_pipeline_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "metadata_config": { "excluded_embed_metadata_keys": [ "string" ], "excluded_llm_metadata_keys": [ "string" ] }, "pipeline_type": "MANAGED", "preset_retrieval_parameters": { "alpha": 0, "class_name": "class_name", "dense_similarity_cutoff": 0, "dense_similarity_top_k": 1, "enable_reranking": true, "files_top_k": 1, "rerank_top_n": 1, "retrieval_mode": "auto_routed", "retrieve_image_nodes": true, "retrieve_page_figure_nodes": true, "retrieve_page_screenshot_nodes": true, "search_filters": { "filters": [ { "key": "key", "value": 0, "operator": "!=" } ], "condition": "and" }, "search_filters_inference_schema": { "foo": { "foo": "bar" } }, "sparse_similarity_top_k": 1 }, "sparse_model_config": { "class_name": "class_name", "model_type": "auto" }, "status": "CREATED", "transform_config": { "chunk_overlap": 0, "chunk_size": 1, "mode": "auto" }, "updated_at": "2019-12-27T18:11:19.117Z" } ``` ## Update Existing Pipeline `Pipeline Pipelines.Update(PipelineUpdateParamsparameters, CancellationTokencancellationToken = default)` **put** `/api/v1/pipelines/{pipeline_id}` Update an existing pipeline's configuration. ### Parameters - `PipelineUpdateParams parameters` - `required string pipelineID` - `DataSinkCreate? dataSink` Schema for creating a data sink. - `string? dataSinkID` Data sink ID. When provided instead of data_sink, the data sink will be looked up by ID. - `EmbeddingConfig? embeddingConfig` - `class AzureOpenAIEmbeddingConfig:` - `AzureOpenAIEmbedding Component` Configuration for the Azure OpenAI embedding model. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the OpenAI API. - `string ApiBase` The base URL for Azure deployment. - `string? ApiKey` The OpenAI API key. - `string ApiVersion` The version for Azure OpenAI API. - `string? AzureDeployment` The Azure deployment to use. - `string? AzureEndpoint` The Azure endpoint to use. - `string ClassName` - `IReadOnlyDictionary? DefaultHeaders` The default headers for API requests. - `Long? Dimensions` The number of dimensions on the output embedding vectors. Works only with v3 embedding models. - `Long EmbedBatchSize` The batch size for embedding calls. - `Long MaxRetries` Maximum number of retries. - `string ModelName` The name of the OpenAI embedding model. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Boolean ReuseClient` Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability. - `Double Timeout` Timeout for each request. - `Type Type` Type of the embedding model. - `"AZURE_EMBEDDING"AzureEmbedding` - `class BedrockEmbeddingConfig:` - `BedrockEmbedding Component` Configuration for the Bedrock embedding model. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the bedrock client. - `string? AwsAccessKeyID` AWS Access Key ID to use - `string? AwsSecretAccessKey` AWS Secret Access Key to use - `string? AwsSessionToken` AWS Session Token to use - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `Long MaxRetries` The maximum number of API retries. - `string ModelName` The modelId of the Bedrock model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `string? ProfileName` The name of aws profile to use. If not given, then the default profile is used. - `string? RegionName` AWS region name to use. Uses region configured in AWS CLI if not passed - `Double Timeout` The timeout for the Bedrock API request in seconds. It will be used for both connect and read timeouts. - `Type Type` Type of the embedding model. - `"BEDROCK_EMBEDDING"BedrockEmbedding` - `class CohereEmbeddingConfig:` - `CohereEmbedding Component` Configuration for the Cohere embedding model. - `required string? ApiKey` The Cohere API key. - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `string EmbeddingType` Embedding type. If not provided float embedding_type is used when needed. - `string? InputType` Model Input type. If not provided, search_document and search_query are used when needed. - `string ModelName` The modelId of the Cohere model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `string Truncate` Truncation type - START/ END/ NONE - `Type Type` Type of the embedding model. - `"COHERE_EMBEDDING"CohereEmbedding` - `class GeminiEmbeddingConfig:` - `GeminiEmbedding Component` Configuration for the Gemini embedding model. - `string? ApiBase` API base to access the model. Defaults to None. - `string? ApiKey` API key to access the model. Defaults to None. - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `string ModelName` The modelId of the Gemini model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Long? OutputDimensionality` Optional reduced dimension for output embeddings. Supported by models/text-embedding-004 and newer (e.g. gemini-embedding-001). Not supported by models/embedding-001. - `string? TaskType` The task for embedding model. - `string? Title` Title is only applicable for retrieval_document tasks, and is used to represent a document title. For other tasks, title is invalid. - `string? Transport` Transport to access the model. Defaults to None. - `Type Type` Type of the embedding model. - `"GEMINI_EMBEDDING"GeminiEmbedding` - `class HuggingFaceInferenceApiEmbeddingConfig:` - `HuggingFaceInferenceApiEmbedding Component` Configuration for the HuggingFace Inference API embedding model. - `Token? Token` Hugging Face token. Will default to the locally saved token. Pass token=False if you don’t want to send your token to the server. - `string` - `Boolean` - `string ClassName` - `IReadOnlyDictionary? Cookies` Additional cookies to send to the server. - `Long EmbedBatchSize` The batch size for embedding calls. - `IReadOnlyDictionary? Headers` Additional headers to send to the server. By default only the authorization and user-agent headers are sent. Values in this dictionary will override the default values. - `string? ModelName` Hugging Face model name. If None, the task will be used. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Pooling? Pooling` Enum of possible pooling choices with pooling behaviors. - `"cls"Cls` - `"last"Last` - `"mean"Mean` - `string? QueryInstruction` Instruction to prepend during query embedding. - `string? Task` Optional task to pick Hugging Face's recommended model, used when model_name is left as default of None. - `string? TextInstruction` Instruction to prepend during text embedding. - `Double? Timeout` The maximum number of seconds to wait for a response from the server. Loading a new model in Inference API can take up to several minutes. Defaults to None, meaning it will loop until the server is available. - `Type Type` Type of the embedding model. - `"HUGGINGFACE_API_EMBEDDING"HuggingfaceApiEmbedding` - `class OpenAIEmbeddingConfig:` - `OpenAIEmbedding Component` Configuration for the OpenAI embedding model. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the OpenAI API. - `string? ApiBase` The base URL for OpenAI API. - `string? ApiKey` The OpenAI API key. - `string? ApiVersion` The version for OpenAI API. - `string ClassName` - `IReadOnlyDictionary? DefaultHeaders` The default headers for API requests. - `Long? Dimensions` The number of dimensions on the output embedding vectors. Works only with v3 embedding models. - `Long EmbedBatchSize` The batch size for embedding calls. - `Long MaxRetries` Maximum number of retries. - `string ModelName` The name of the OpenAI embedding model. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Boolean ReuseClient` Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability. - `Double Timeout` Timeout for each request. - `Type Type` Type of the embedding model. - `"OPENAI_EMBEDDING"OpenAIEmbedding` - `class VertexAIEmbeddingConfig:` - `VertexTextEmbedding Component` Configuration for the VertexAI embedding model. - `required string? ClientEmail` The client email for the VertexAI credentials. - `required string Location` The default location to use when making API calls. - `required string? PrivateKey` The private key for the VertexAI credentials. - `required string? PrivateKeyID` The private key ID for the VertexAI credentials. - `required string Project` The default GCP project to use when making Vertex API calls. - `required string? TokenUri` The token URI for the VertexAI credentials. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the Vertex. - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `EmbedMode EmbedMode` The embedding mode to use. - `"classification"Classification` - `"clustering"Clustering` - `"default"Default` - `"retrieval"Retrieval` - `"similarity"Similarity` - `string ModelName` The modelId of the VertexAI model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Type Type` Type of the embedding model. - `"VERTEXAI_EMBEDDING"VertexaiEmbedding` - `string? embeddingModelConfigID` Embedding model config ID. When provided instead of embedding_config, the embedding model config will be looked up by ID. - `LlamaParseParameters? llamaParseParameters` Settings that can be configured for how to use LlamaParse to parse files within a LlamaCloud pipeline. - `string? managedPipelineID` The ID of the ManagedPipeline this playground pipeline is linked to. - `PipelineMetadataConfig? metadataConfig` Metadata configuration for the pipeline. - `string? name` - `PresetRetrievalParams? presetRetrievalParameters` Schema for the search params for an retrieval execution that can be preset for a pipeline. - `SparseModelConfig? sparseModelConfig` Configuration for sparse embedding models used in hybrid search. This allows users to choose between Splade and BM25 models for sparse retrieval in managed data sinks. - `string? status` Status of the pipeline deployment. - `TransformConfig? transformConfig` Configuration for the transformation. - `class AutoTransformConfig:` - `Long ChunkOverlap` Chunk overlap for the transformation. - `Long ChunkSize` Chunk size for the transformation. - `Mode Mode` - `"auto"Auto` - `class AdvancedModeTransformConfig:` - `ChunkingConfig ChunkingConfig` Configuration for the chunking. - `class NoneChunkingConfig:` - `Mode Mode` - `"none"None` - `class CharacterChunkingConfig:` - `Long ChunkOverlap` - `Long ChunkSize` - `Mode Mode` - `"character"Character` - `class TokenChunkingConfig:` - `Long ChunkOverlap` - `Long ChunkSize` - `Mode Mode` - `"token"Token` - `string Separator` - `class SentenceChunkingConfig:` - `Long ChunkOverlap` - `Long ChunkSize` - `Mode Mode` - `"sentence"Sentence` - `string ParagraphSeparator` - `string Separator` - `class SemanticChunkingConfig:` - `Long BreakpointPercentileThreshold` - `Long BufferSize` - `Mode Mode` - `"semantic"Semantic` - `Mode Mode` - `"advanced"Advanced` - `SegmentationConfig SegmentationConfig` Configuration for the segmentation. - `class NoneSegmentationConfig:` - `Mode Mode` - `"none"None` - `class PageSegmentationConfig:` - `Mode Mode` - `"page"Page` - `string PageSeparator` - `class ElementSegmentationConfig:` - `Mode Mode` - `"element"Element` ### Returns - `class Pipeline:` Schema for a pipeline. - `required string ID` Unique identifier - `required EmbeddingConfig EmbeddingConfig` - `class AzureOpenAIEmbeddingConfig:` - `AzureOpenAIEmbedding Component` Configuration for the Azure OpenAI embedding model. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the OpenAI API. - `string ApiBase` The base URL for Azure deployment. - `string? ApiKey` The OpenAI API key. - `string ApiVersion` The version for Azure OpenAI API. - `string? AzureDeployment` The Azure deployment to use. - `string? AzureEndpoint` The Azure endpoint to use. - `string ClassName` - `IReadOnlyDictionary? DefaultHeaders` The default headers for API requests. - `Long? Dimensions` The number of dimensions on the output embedding vectors. Works only with v3 embedding models. - `Long EmbedBatchSize` The batch size for embedding calls. - `Long MaxRetries` Maximum number of retries. - `string ModelName` The name of the OpenAI embedding model. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Boolean ReuseClient` Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability. - `Double Timeout` Timeout for each request. - `Type Type` Type of the embedding model. - `"AZURE_EMBEDDING"AzureEmbedding` - `class BedrockEmbeddingConfig:` - `BedrockEmbedding Component` Configuration for the Bedrock embedding model. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the bedrock client. - `string? AwsAccessKeyID` AWS Access Key ID to use - `string? AwsSecretAccessKey` AWS Secret Access Key to use - `string? AwsSessionToken` AWS Session Token to use - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `Long MaxRetries` The maximum number of API retries. - `string ModelName` The modelId of the Bedrock model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `string? ProfileName` The name of aws profile to use. If not given, then the default profile is used. - `string? RegionName` AWS region name to use. Uses region configured in AWS CLI if not passed - `Double Timeout` The timeout for the Bedrock API request in seconds. It will be used for both connect and read timeouts. - `Type Type` Type of the embedding model. - `"BEDROCK_EMBEDDING"BedrockEmbedding` - `class CohereEmbeddingConfig:` - `CohereEmbedding Component` Configuration for the Cohere embedding model. - `required string? ApiKey` The Cohere API key. - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `string EmbeddingType` Embedding type. If not provided float embedding_type is used when needed. - `string? InputType` Model Input type. If not provided, search_document and search_query are used when needed. - `string ModelName` The modelId of the Cohere model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `string Truncate` Truncation type - START/ END/ NONE - `Type Type` Type of the embedding model. - `"COHERE_EMBEDDING"CohereEmbedding` - `class GeminiEmbeddingConfig:` - `GeminiEmbedding Component` Configuration for the Gemini embedding model. - `string? ApiBase` API base to access the model. Defaults to None. - `string? ApiKey` API key to access the model. Defaults to None. - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `string ModelName` The modelId of the Gemini model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Long? OutputDimensionality` Optional reduced dimension for output embeddings. Supported by models/text-embedding-004 and newer (e.g. gemini-embedding-001). Not supported by models/embedding-001. - `string? TaskType` The task for embedding model. - `string? Title` Title is only applicable for retrieval_document tasks, and is used to represent a document title. For other tasks, title is invalid. - `string? Transport` Transport to access the model. Defaults to None. - `Type Type` Type of the embedding model. - `"GEMINI_EMBEDDING"GeminiEmbedding` - `class HuggingFaceInferenceApiEmbeddingConfig:` - `HuggingFaceInferenceApiEmbedding Component` Configuration for the HuggingFace Inference API embedding model. - `Token? Token` Hugging Face token. Will default to the locally saved token. Pass token=False if you don’t want to send your token to the server. - `string` - `Boolean` - `string ClassName` - `IReadOnlyDictionary? Cookies` Additional cookies to send to the server. - `Long EmbedBatchSize` The batch size for embedding calls. - `IReadOnlyDictionary? Headers` Additional headers to send to the server. By default only the authorization and user-agent headers are sent. Values in this dictionary will override the default values. - `string? ModelName` Hugging Face model name. If None, the task will be used. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Pooling? Pooling` Enum of possible pooling choices with pooling behaviors. - `"cls"Cls` - `"last"Last` - `"mean"Mean` - `string? QueryInstruction` Instruction to prepend during query embedding. - `string? Task` Optional task to pick Hugging Face's recommended model, used when model_name is left as default of None. - `string? TextInstruction` Instruction to prepend during text embedding. - `Double? Timeout` The maximum number of seconds to wait for a response from the server. Loading a new model in Inference API can take up to several minutes. Defaults to None, meaning it will loop until the server is available. - `Type Type` Type of the embedding model. - `"HUGGINGFACE_API_EMBEDDING"HuggingfaceApiEmbedding` - `class ManagedOpenAIEmbedding:` - `Component Component` Configuration for the Managed OpenAI embedding model. - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `ModelName ModelName` The name of the OpenAI embedding model. - `"openai-text-embedding-3-small"OpenAITextEmbedding3Small` - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Type Type` Type of the embedding model. - `"MANAGED_OPENAI_EMBEDDING"ManagedOpenAIEmbedding` - `class OpenAIEmbeddingConfig:` - `OpenAIEmbedding Component` Configuration for the OpenAI embedding model. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the OpenAI API. - `string? ApiBase` The base URL for OpenAI API. - `string? ApiKey` The OpenAI API key. - `string? ApiVersion` The version for OpenAI API. - `string ClassName` - `IReadOnlyDictionary? DefaultHeaders` The default headers for API requests. - `Long? Dimensions` The number of dimensions on the output embedding vectors. Works only with v3 embedding models. - `Long EmbedBatchSize` The batch size for embedding calls. - `Long MaxRetries` Maximum number of retries. - `string ModelName` The name of the OpenAI embedding model. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Boolean ReuseClient` Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability. - `Double Timeout` Timeout for each request. - `Type Type` Type of the embedding model. - `"OPENAI_EMBEDDING"OpenAIEmbedding` - `class VertexAIEmbeddingConfig:` - `VertexTextEmbedding Component` Configuration for the VertexAI embedding model. - `required string? ClientEmail` The client email for the VertexAI credentials. - `required string Location` The default location to use when making API calls. - `required string? PrivateKey` The private key for the VertexAI credentials. - `required string? PrivateKeyID` The private key ID for the VertexAI credentials. - `required string Project` The default GCP project to use when making Vertex API calls. - `required string? TokenUri` The token URI for the VertexAI credentials. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the Vertex. - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `EmbedMode EmbedMode` The embedding mode to use. - `"classification"Classification` - `"clustering"Clustering` - `"default"Default` - `"retrieval"Retrieval` - `"similarity"Similarity` - `string ModelName` The modelId of the VertexAI model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Type Type` Type of the embedding model. - `"VERTEXAI_EMBEDDING"VertexaiEmbedding` - `required string Name` - `required string ProjectID` - `ConfigHash? ConfigHash` Hashes for the configuration of a pipeline. - `string? EmbeddingConfigHash` Hash of the embedding config. - `string? ParsingConfigHash` Hash of the llama parse parameters. - `string? TransformConfigHash` Hash of the transform config. - `DateTimeOffset? CreatedAt` Creation datetime - `DataSink? DataSink` Schema for a data sink. - `required string ID` Unique identifier - `required Component Component` Component that implements the data sink - `IReadOnlyDictionary` - `class CloudPineconeVectorStore:` Cloud Pinecone Vector Store. This class is used to store the configuration for a Pinecone vector store, so that it can be created and used in LlamaCloud. Args: api_key (str): API key for authenticating with Pinecone index_name (str): name of the Pinecone index namespace (optional[str]): namespace to use in the Pinecone index insert_kwargs (optional[dict]): additional kwargs to pass during insertion - `required string ApiKey` The API key for authenticating with Pinecone - `required string IndexName` - `string ClassName` - `IReadOnlyDictionary? InsertKwargs` - `string? Namespace` - `SupportsNestedMetadataFilters SupportsNestedMetadataFilters` - `trueTrue` - `class CloudPostgresVectorStore:` - `required string Database` - `required Long EmbedDim` - `required string Host` - `required string Password` - `required Long Port` - `required string SchemaName` - `required string TableName` - `required string User` - `string ClassName` - `PgVectorHnswSettings? HnswSettings` HNSW settings for PGVector. - `DistanceMethod DistanceMethod` The distance method to use. - `"cosine"Cosine` - `"hamming"Hamming` - `"ip"IP` - `"jaccard"Jaccard` - `"l1"L1` - `"l2"L2` - `Long EfConstruction` The number of edges to use during the construction phase. - `Long EfSearch` The number of edges to use during the search phase. - `Long M` The number of bi-directional links created for each new element. - `VectorType VectorType` The type of vector to use. - `"bit"Bit` - `"half_vec"HalfVec` - `"sparse_vec"SparseVec` - `"vector"Vector` - `Boolean? HybridSearch` - `Boolean PerformSetup` - `Boolean SupportsNestedMetadataFilters` - `class CloudQdrantVectorStore:` Cloud Qdrant Vector Store. This class is used to store the configuration for a Qdrant vector store, so that it can be created and used in LlamaCloud. Args: collection_name (str): name of the Qdrant collection url (str): url of the Qdrant instance api_key (str): API key for authenticating with Qdrant max_retries (int): maximum number of retries in case of a failure. Defaults to 3 client_kwargs (dict): additional kwargs to pass to the Qdrant client - `required string ApiKey` - `required string CollectionName` - `required string Url` - `string ClassName` - `IReadOnlyDictionary ClientKwargs` - `Long MaxRetries` - `SupportsNestedMetadataFilters SupportsNestedMetadataFilters` - `trueTrue` - `class CloudAzureAISearchVectorStore:` Cloud Azure AI Search Vector Store. - `required string SearchServiceApiKey` - `required string SearchServiceEndpoint` - `string ClassName` - `string? ClientID` - `string? ClientSecret` - `Long? EmbeddingDimension` - `IReadOnlyDictionary? FilterableMetadataFieldKeys` - `string? IndexName` - `string? SearchServiceApiVersion` - `SupportsNestedMetadataFilters SupportsNestedMetadataFilters` - `trueTrue` - `string? TenantID` - `class CloudMongoDBAtlasVectorSearch:` Cloud MongoDB Atlas Vector Store. This class is used to store the configuration for a MongoDB Atlas vector store, so that it can be created and used in LlamaCloud. Args: mongodb_uri (str): URI for connecting to MongoDB Atlas db_name (str): name of the MongoDB database collection_name (str): name of the MongoDB collection vector_index_name (str): name of the MongoDB Atlas vector index fulltext_index_name (str): name of the MongoDB Atlas full-text index - `required string CollectionName` - `required string DBName` - `required string MongoDBUri` - `string ClassName` - `Long? EmbeddingDimension` - `string? FulltextIndexName` - `Boolean SupportsNestedMetadataFilters` - `string? VectorIndexName` - `class CloudMilvusVectorStore:` Cloud Milvus Vector Store. - `required string Uri` - `string? Token` - `string ClassName` - `string? CollectionName` - `Long? EmbeddingDimension` - `Boolean SupportsNestedMetadataFilters` - `class CloudAstraDBVectorStore:` Cloud AstraDB Vector Store. This class is used to store the configuration for an AstraDB vector store, so that it can be created and used in LlamaCloud. Args: token (str): The Astra DB Application Token to use. api_endpoint (str): The Astra DB JSON API endpoint for your database. collection_name (str): Collection name to use. If not existing, it will be created. embedding_dimension (int): Length of the embedding vectors in use. keyspace (optional[str]): The keyspace to use. If not provided, 'default_keyspace' - `required string Token` The Astra DB Application Token to use - `required string ApiEndpoint` The Astra DB JSON API endpoint for your database - `required string CollectionName` Collection name to use. If not existing, it will be created - `required Long EmbeddingDimension` Length of the embedding vectors in use - `string ClassName` - `string? Keyspace` The keyspace to use. If not provided, 'default_keyspace' - `SupportsNestedMetadataFilters SupportsNestedMetadataFilters` - `trueTrue` - `required string Name` The name of the data sink. - `required string ProjectID` - `required SinkType SinkType` - `"ASTRA_DB"AstraDB` - `"AZUREAI_SEARCH"AzureaiSearch` - `"MILVUS"Milvus` - `"MONGODB_ATLAS"MongoDBAtlas` - `"PINECONE"Pinecone` - `"POSTGRES"Postgres` - `"QDRANT"Qdrant` - `DateTimeOffset? CreatedAt` Creation datetime - `DateTimeOffset? UpdatedAt` Update datetime - `EmbeddingModelConfig? EmbeddingModelConfig` Schema for an embedding model config. - `required string ID` Unique identifier - `required EmbeddingConfig EmbeddingConfig` The embedding configuration for the embedding model config. - `class AzureOpenAIEmbeddingConfig:` - `class BedrockEmbeddingConfig:` - `class CohereEmbeddingConfig:` - `class GeminiEmbeddingConfig:` - `class HuggingFaceInferenceApiEmbeddingConfig:` - `class OpenAIEmbeddingConfig:` - `class VertexAIEmbeddingConfig:` - `required string Name` The name of the embedding model config. - `required string ProjectID` - `DateTimeOffset? CreatedAt` Creation datetime - `DateTimeOffset? UpdatedAt` Update datetime - `string? EmbeddingModelConfigID` The ID of the EmbeddingModelConfig this pipeline is using. - `LlamaParseParameters? LlamaParseParameters` Settings that can be configured for how to use LlamaParse to parse files within a LlamaCloud pipeline. - `Boolean? AdaptiveLongTable` - `Boolean? AggressiveTableExtraction` - `Boolean? AnnotateLinks` - `Boolean? AutoMode` - `string? AutoModeConfigurationJson` - `Boolean? AutoModeTriggerOnImageInPage` - `string? AutoModeTriggerOnRegexpInPage` - `Boolean? AutoModeTriggerOnTableInPage` - `string? AutoModeTriggerOnTextInPage` - `string? AzureOpenAIApiVersion` - `string? AzureOpenAIDeploymentName` - `string? AzureOpenAIEndpoint` - `string? AzureOpenAIKey` - `Double? BboxBottom` - `Double? BboxLeft` - `Double? BboxRight` - `Double? BboxTop` - `string? BoundingBox` - `Boolean? CompactMarkdownTable` - `string? ComplementalFormattingInstruction` - `string? ConfidenceScoreEffort` - `string? ContentGuidelineInstruction` - `Boolean? ContinuousMode` - `Boolean? DisableImageExtraction` - `Boolean? DisableOcr` - `Boolean? DisableReconstruction` - `Boolean? DoNotCache` - `Boolean? DoNotUnrollColumns` - `Boolean? EnableCostOptimizer` - `Boolean? ExtractCharts` - `Boolean? ExtractLayout` - `Boolean? ExtractPrintedPageNumber` - `Boolean? FastMode` - `string? FormattingInstruction` - `string? Gpt4oApiKey` - `Boolean? Gpt4oMode` - `Boolean? GuessXlsxSheetName` - `Boolean? HideFooters` - `Boolean? HideHeaders` - `Boolean? HighResOcr` - `Boolean? HtmlMakeAllElementsVisible` - `Boolean? HtmlRemoveFixedElements` - `Boolean? HtmlRemoveNavigationElements` - `string? HttpProxy` - `Boolean? IgnoreDocumentElementsForLayoutDetection` - `IReadOnlyList? ImagesToSave` - `"embedded"Embedded` - `"layout"Layout` - `"screenshot"Screenshot` - `Boolean? InlineImagesInMarkdown` - `string? InputS3Path` - `string? InputS3Region` - `string? InputUrl` - `Boolean? InternalIsScreenshotJob` - `Boolean? InvalidateCache` - `Boolean? IsFormattingInstruction` - `Double? JobTimeoutExtraTimePerPageInSeconds` - `Double? JobTimeoutInSeconds` - `Boolean? KeepPageSeparatorWhenMergingTables` - `IReadOnlyList Languages` - `"abq"Abq` - `"ady"Ady` - `"af"Af` - `"ang"Ang` - `"ar"Ar` - `"as"As` - `"ava"Ava` - `"az"Az` - `"be"Be` - `"bg"Bg` - `"bgc"Bgc` - `"bh"Bh` - `"bho"Bho` - `"bn"Bn` - `"bs"Bs` - `"ch_sim"ChSim` - `"ch_tra"ChTra` - `"che"Che` - `"cs"Cs` - `"cy"Cy` - `"da"Da` - `"dar"Dar` - `"de"De` - `"en"En` - `"es"Es` - `"et"Et` - `"fa"Fa` - `"fr"Fr` - `"ga"Ga` - `"gom"Gom` - `"hi"Hi` - `"hr"Hr` - `"hu"Hu` - `"id"ID` - `"inh"Inh` - `"is"Is` - `"it"It` - `"ja"Ja` - `"kbd"Kbd` - `"kn"Kn` - `"ko"Ko` - `"ku"Ku` - `"la"La` - `"lbe"Lbe` - `"lez"Lez` - `"lt"Lt` - `"lv"Lv` - `"mah"Mah` - `"mai"Mai` - `"mi"Mi` - `"mn"Mn` - `"mni"Mni` - `"mr"Mr` - `"ms"Ms` - `"mt"Mt` - `"ne"Ne` - `"new"New` - `"nl"Nl` - `"no"No` - `"oc"Oc` - `"pi"Pi` - `"pl"Pl` - `"pt"Pt` - `"ro"Ro` - `"rs_cyrillic"RsCyrillic` - `"rs_latin"RsLatin` - `"ru"Ru` - `"sa"Sa` - `"sck"Sck` - `"sk"Sk` - `"sl"Sl` - `"sq"Sq` - `"sv"Sv` - `"sw"Sw` - `"ta"Ta` - `"tab"Tab` - `"te"Te` - `"th"Th` - `"tjk"Tjk` - `"tl"Tl` - `"tr"Tr` - `"ug"Ug` - `"uk"Uk` - `"ur"Ur` - `"uz"Uz` - `"vi"Vi` - `Boolean? LayoutAware` - `Boolean? LineLevelBoundingBox` - `string? MarkdownTableMultilineHeaderSeparator` - `Long? MaxPages` - `Long? MaxPagesEnforced` - `Boolean? MergeTablesAcrossPagesInMarkdown` - `string? Model` - `Boolean? OutlinedTableExtraction` - `Boolean? OutputPdfOfDocument` - `string? OutputS3PathPrefix` - `string? OutputS3Region` - `Boolean? OutputTablesAsHtml` - `Double? PageErrorTolerance` - `string? PageFooterPrefix` - `string? PageFooterSuffix` - `string? PageHeaderPrefix` - `string? PageHeaderSuffix` - `string? PagePrefix` - `string? PageSeparator` - `string? PageSuffix` - `ParsingMode? ParseMode` Enum for representing the mode of parsing to be used. - `"parse_document_with_agent"ParseDocumentWithAgent` - `"parse_document_with_llm"ParseDocumentWithLlm` - `"parse_document_with_lvm"ParseDocumentWithLvm` - `"parse_page_with_agent"ParsePageWithAgent` - `"parse_page_with_layout_agent"ParsePageWithLayoutAgent` - `"parse_page_with_llm"ParsePageWithLlm` - `"parse_page_with_lvm"ParsePageWithLvm` - `"parse_page_without_llm"ParsePageWithoutLlm` - `string? ParsingInstruction` - `Boolean? PreciseBoundingBox` - `Boolean? PremiumMode` - `Boolean? PresentationOutOfBoundsContent` - `Boolean? PresentationSkipEmbeddedData` - `Boolean? PreserveLayoutAlignmentAcrossPages` - `Boolean? PreserveVerySmallText` - `string? Preset` - `Priority? Priority` The priority for the request. This field may be ignored or overwritten depending on the organization tier. - `"critical"Critical` - `"high"High` - `"low"Low` - `"medium"Medium` - `string? ProjectID` - `Boolean? RemoveHiddenText` - `FailPageMode? ReplaceFailedPageMode` Enum for representing the different available page error handling modes. - `"blank_page"BlankPage` - `"error_message"ErrorMessage` - `"raw_text"RawText` - `string? ReplaceFailedPageWithErrorMessagePrefix` - `string? ReplaceFailedPageWithErrorMessageSuffix` - `Boolean? SaveImages` - `Boolean? SkipDiagonalText` - `Boolean? SpecializedChartParsingAgentic` - `Boolean? SpecializedChartParsingEfficient` - `Boolean? SpecializedChartParsingPlus` - `Boolean? SpecializedImageParsing` - `Boolean? SpreadsheetExtractSubTables` - `Boolean? SpreadsheetForceFormulaComputation` - `Boolean? SpreadsheetIncludeHiddenSheets` - `Boolean? StrictModeBuggyFont` - `Boolean? StrictModeImageExtraction` - `Boolean? StrictModeImageOcr` - `Boolean? StrictModeReconstruction` - `Boolean? StructuredOutput` - `string? StructuredOutputJsonSchema` - `string? StructuredOutputJsonSchemaName` - `string? SystemPrompt` - `string? SystemPromptAppend` - `Boolean? TakeScreenshot` - `string? TargetPages` - `string? Tier` - `Boolean? UseVendorMultimodalModel` - `string? UserPrompt` - `string? VendorMultimodalApiKey` - `string? VendorMultimodalModelName` - `string? Version` - `IReadOnlyList? WebhookConfigurations` Outbound webhook endpoints to notify on job status changes - `IReadOnlyList? WebhookEvents` Events to subscribe to (e.g. 'parse.success', 'extract.error'). If null, all events are delivered. - `"classify.cancelled"ClassifyCancelled` - `"classify.error"ClassifyError` - `"classify.partial_success"ClassifyPartialSuccess` - `"classify.pending"ClassifyPending` - `"classify.running"ClassifyRunning` - `"classify.success"ClassifySuccess` - `"extract.cancelled"ExtractCancelled` - `"extract.error"ExtractError` - `"extract.partial_success"ExtractPartialSuccess` - `"extract.pending"ExtractPending` - `"extract.success"ExtractSuccess` - `"parse.cancelled"ParseCancelled` - `"parse.error"ParseError` - `"parse.partial_success"ParsePartialSuccess` - `"parse.pending"ParsePending` - `"parse.running"ParseRunning` - `"parse.success"ParseSuccess` - `"sheets.cancelled"SheetsCancelled` - `"sheets.error"SheetsError` - `"sheets.partial_success"SheetsPartialSuccess` - `"sheets.pending"SheetsPending` - `"sheets.success"SheetsSuccess` - `"split.cancelled"SplitCancelled` - `"split.error"SplitError` - `"split.pending"SplitPending` - `"split.processing"SplitProcessing` - `"split.success"SplitSuccess` - `"unmapped_event"UnmappedEvent` - `IReadOnlyDictionary? WebhookHeaders` Custom HTTP headers sent with each webhook request (e.g. auth tokens) - `string? WebhookOutputFormat` Response format sent to the webhook: 'string' (default) or 'json' - `string? WebhookSigningSecret` Shared signing secret used to sign webhook deliveries. When set, each request includes an HMAC-SHA256 signature of the request body in the 'LC-Signature' header (value 'sha256='). Recompute the HMAC over the raw request body with this secret to verify the delivery is authentic. - `string? WebhookUrl` URL to receive webhook POST notifications - `string? WebhookUrl` - `string? ManagedPipelineID` The ID of the ManagedPipeline this playground pipeline is linked to. - `PipelineMetadataConfig? MetadataConfig` Metadata configuration for the pipeline. - `IReadOnlyList ExcludedEmbedMetadataKeys` List of metadata keys to exclude from embeddings - `IReadOnlyList ExcludedLlmMetadataKeys` List of metadata keys to exclude from LLM during retrieval - `PipelineType PipelineType` Type of pipeline. Either PLAYGROUND or MANAGED. - `"MANAGED"Managed` - `"PLAYGROUND"Playground` - `PresetRetrievalParams PresetRetrievalParameters` Preset retrieval parameters for the pipeline. - `Double? Alpha` Alpha value for hybrid retrieval to determine the weights between dense and sparse retrieval. 0 is sparse retrieval and 1 is dense retrieval. - `string ClassName` - `Double? DenseSimilarityCutoff` Minimum similarity score wrt query for retrieval - `Long? DenseSimilarityTopK` Number of nodes for dense retrieval. - `Boolean? EnableReranking` Enable reranking for retrieval - `Long? FilesTopK` Number of files to retrieve (only for retrieval mode files_via_metadata and files_via_content). - `Long? RerankTopN` Number of reranked nodes for returning. - `RetrievalMode RetrievalMode` The retrieval mode for the query. - `"auto_routed"AutoRouted` - `"chunks"Chunks` - `"files_via_content"FilesViaContent` - `"files_via_metadata"FilesViaMetadata` - `Boolean RetrieveImageNodes` Whether to retrieve image nodes. - `Boolean RetrievePageFigureNodes` Whether to retrieve page figure nodes. - `Boolean RetrievePageScreenshotNodes` Whether to retrieve page screenshot nodes. - `MetadataFilters? SearchFilters` Metadata filters for vector stores. - `required IReadOnlyList Filters` - `class MetadataFilter:` Comprehensive metadata filter for vector stores to support more operators. Value uses Strict types, as int, float and str are compatible types and were all converted to string before. See: https://docs.pydantic.dev/latest/usage/types/#strict-types - `required string Key` - `required Value? Value` - `Double` - `string` - `IReadOnlyList` - `IReadOnlyList` - `IReadOnlyList` - `Operator Operator` Vector store filter operator. - `"!="` - `"<"` - `"<="` - `"=="` - `">"` - `">="` - `"all"All` - `"any"Any` - `"contains"Contains` - `"in"In` - `"is_empty"IsEmpty` - `"nin"Nin` - `"text_match"TextMatch` - `"text_match_insensitive"TextMatchInsensitive` - `class MetadataFilters:` Metadata filters for vector stores. - `Condition? Condition` Vector store filter conditions to combine different filters. - `"and"And` - `"not"Not` - `"or"Or` - `IReadOnlyDictionary? SearchFiltersInferenceSchema` JSON Schema that will be used to infer search_filters. Omit or leave as null to skip inference. - `IReadOnlyDictionary` - `IReadOnlyList` - `string` - `Double` - `Boolean` - `Long? SparseSimilarityTopK` Number of nodes for sparse retrieval. - `SparseModelConfig? SparseModelConfig` Configuration for sparse embedding models used in hybrid search. This allows users to choose between Splade and BM25 models for sparse retrieval in managed data sinks. - `string ClassName` - `ModelType ModelType` The sparse model type to use. 'bm25' uses Qdrant's FastEmbed BM25 model (default for new pipelines), 'splade' uses HuggingFace Splade model, 'auto' selects based on deployment mode (BYOC uses term frequency, Cloud uses Splade). - `"auto"Auto` - `"bm25"Bm25` - `"splade"Splade` - `Status? Status` Status of the pipeline. - `"CREATED"Created` - `"DELETING"Deleting` - `TransformConfig TransformConfig` Configuration for the transformation. - `class AutoTransformConfig:` - `Long ChunkOverlap` Chunk overlap for the transformation. - `Long ChunkSize` Chunk size for the transformation. - `Mode Mode` - `"auto"Auto` - `class AdvancedModeTransformConfig:` - `ChunkingConfig ChunkingConfig` Configuration for the chunking. - `class NoneChunkingConfig:` - `Mode Mode` - `"none"None` - `class CharacterChunkingConfig:` - `Long ChunkOverlap` - `Long ChunkSize` - `Mode Mode` - `"character"Character` - `class TokenChunkingConfig:` - `Long ChunkOverlap` - `Long ChunkSize` - `Mode Mode` - `"token"Token` - `string Separator` - `class SentenceChunkingConfig:` - `Long ChunkOverlap` - `Long ChunkSize` - `Mode Mode` - `"sentence"Sentence` - `string ParagraphSeparator` - `string Separator` - `class SemanticChunkingConfig:` - `Long BreakpointPercentileThreshold` - `Long BufferSize` - `Mode Mode` - `"semantic"Semantic` - `Mode Mode` - `"advanced"Advanced` - `SegmentationConfig SegmentationConfig` Configuration for the segmentation. - `class NoneSegmentationConfig:` - `Mode Mode` - `"none"None` - `class PageSegmentationConfig:` - `Mode Mode` - `"page"Page` - `string PageSeparator` - `class ElementSegmentationConfig:` - `Mode Mode` - `"element"Element` - `DateTimeOffset? UpdatedAt` Update datetime ### Example ```csharp PipelineUpdateParams parameters = new() { PipelineID = "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e" }; var pipeline = await client.Pipelines.Update(parameters); Console.WriteLine(pipeline); ``` #### Response ```json { "id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "embedding_config": { "component": { "additional_kwargs": { "foo": "bar" }, "api_base": "api_base", "api_key": "api_key", "api_version": "api_version", "azure_deployment": "azure_deployment", "azure_endpoint": "azure_endpoint", "class_name": "class_name", "default_headers": { "foo": "string" }, "dimensions": 0, "embed_batch_size": 1, "max_retries": 0, "model_name": "model_name", "num_workers": 0, "reuse_client": true, "timeout": 0 }, "type": "AZURE_EMBEDDING" }, "name": "name", "project_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "config_hash": { "embedding_config_hash": "embedding_config_hash", "parsing_config_hash": "parsing_config_hash", "transform_config_hash": "transform_config_hash" }, "created_at": "2019-12-27T18:11:19.117Z", "data_sink": { "id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "component": { "foo": "bar" }, "name": "name", "project_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "sink_type": "ASTRA_DB", "created_at": "2019-12-27T18:11:19.117Z", "updated_at": "2019-12-27T18:11:19.117Z" }, "embedding_model_config": { "id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "embedding_config": { "component": { "additional_kwargs": { "foo": "bar" }, "api_base": "api_base", "api_key": "api_key", "api_version": "api_version", "azure_deployment": "azure_deployment", "azure_endpoint": "azure_endpoint", "class_name": "class_name", "default_headers": { "foo": "string" }, "dimensions": 0, "embed_batch_size": 1, "max_retries": 0, "model_name": "model_name", "num_workers": 0, "reuse_client": true, "timeout": 0 }, "type": "AZURE_EMBEDDING" }, "name": "name", "project_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "created_at": "2019-12-27T18:11:19.117Z", "updated_at": "2019-12-27T18:11:19.117Z" }, "embedding_model_config_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "llama_parse_parameters": { "adaptive_long_table": true, "aggressive_table_extraction": true, "annotate_links": true, "auto_mode": true, "auto_mode_configuration_json": "auto_mode_configuration_json", "auto_mode_trigger_on_image_in_page": true, "auto_mode_trigger_on_regexp_in_page": "auto_mode_trigger_on_regexp_in_page", "auto_mode_trigger_on_table_in_page": true, "auto_mode_trigger_on_text_in_page": "auto_mode_trigger_on_text_in_page", "azure_openai_api_version": "azure_openai_api_version", "azure_openai_deployment_name": "azure_openai_deployment_name", "azure_openai_endpoint": "azure_openai_endpoint", "azure_openai_key": "azure_openai_key", "bbox_bottom": 0, "bbox_left": 0, "bbox_right": 0, "bbox_top": 0, "bounding_box": "bounding_box", "compact_markdown_table": true, "complemental_formatting_instruction": "complemental_formatting_instruction", "confidence_score_effort": "confidence_score_effort", "content_guideline_instruction": "content_guideline_instruction", "continuous_mode": true, "disable_image_extraction": true, "disable_ocr": true, "disable_reconstruction": true, "do_not_cache": true, "do_not_unroll_columns": true, "enable_cost_optimizer": true, "extract_charts": true, "extract_layout": true, "extract_printed_page_number": true, "fast_mode": true, "formatting_instruction": "formatting_instruction", "gpt4o_api_key": "gpt4o_api_key", "gpt4o_mode": true, "guess_xlsx_sheet_name": true, "hide_footers": true, "hide_headers": true, "high_res_ocr": true, "html_make_all_elements_visible": true, "html_remove_fixed_elements": true, "html_remove_navigation_elements": true, "http_proxy": "http_proxy", "ignore_document_elements_for_layout_detection": true, "images_to_save": [ "embedded" ], "inline_images_in_markdown": true, "input_s3_path": "input_s3_path", "input_s3_region": "input_s3_region", "input_url": "input_url", "internal_is_screenshot_job": true, "invalidate_cache": true, "is_formatting_instruction": true, "job_timeout_extra_time_per_page_in_seconds": 0, "job_timeout_in_seconds": 0, "keep_page_separator_when_merging_tables": true, "languages": [ "abq" ], "layout_aware": true, "line_level_bounding_box": true, "markdown_table_multiline_header_separator": "markdown_table_multiline_header_separator", "max_pages": 0, "max_pages_enforced": 0, "merge_tables_across_pages_in_markdown": true, "model": "model", "outlined_table_extraction": true, "output_pdf_of_document": true, "output_s3_path_prefix": "output_s3_path_prefix", "output_s3_region": "output_s3_region", "output_tables_as_HTML": true, "page_error_tolerance": 0, "page_footer_prefix": "page_footer_prefix", "page_footer_suffix": "page_footer_suffix", "page_header_prefix": "page_header_prefix", "page_header_suffix": "page_header_suffix", "page_prefix": "page_prefix", "page_separator": "page_separator", "page_suffix": "page_suffix", "parse_mode": "parse_document_with_agent", "parsing_instruction": "parsing_instruction", "precise_bounding_box": true, "premium_mode": true, "presentation_out_of_bounds_content": true, "presentation_skip_embedded_data": true, "preserve_layout_alignment_across_pages": true, "preserve_very_small_text": true, "preset": "preset", "priority": "critical", "project_id": "project_id", "remove_hidden_text": true, "replace_failed_page_mode": "blank_page", "replace_failed_page_with_error_message_prefix": "replace_failed_page_with_error_message_prefix", "replace_failed_page_with_error_message_suffix": "replace_failed_page_with_error_message_suffix", "save_images": true, "skip_diagonal_text": true, "specialized_chart_parsing_agentic": true, "specialized_chart_parsing_efficient": true, "specialized_chart_parsing_plus": true, "specialized_image_parsing": true, "spreadsheet_extract_sub_tables": true, "spreadsheet_force_formula_computation": true, "spreadsheet_include_hidden_sheets": true, "strict_mode_buggy_font": true, "strict_mode_image_extraction": true, "strict_mode_image_ocr": true, "strict_mode_reconstruction": true, "structured_output": true, "structured_output_json_schema": "structured_output_json_schema", "structured_output_json_schema_name": "structured_output_json_schema_name", "system_prompt": "system_prompt", "system_prompt_append": "system_prompt_append", "take_screenshot": true, "target_pages": "target_pages", "tier": "tier", "use_vendor_multimodal_model": true, "user_prompt": "user_prompt", "vendor_multimodal_api_key": "vendor_multimodal_api_key", "vendor_multimodal_model_name": "vendor_multimodal_model_name", "version": "version", "webhook_configurations": [ { "webhook_events": [ "parse.success", "parse.error" ], "webhook_headers": { "Authorization": "Bearer sk-..." }, "webhook_output_format": "json", "webhook_signing_secret": "whsec_...", "webhook_url": "https://example.com/webhooks/llamacloud" } ], "webhook_url": "webhook_url" }, "managed_pipeline_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "metadata_config": { "excluded_embed_metadata_keys": [ "string" ], "excluded_llm_metadata_keys": [ "string" ] }, "pipeline_type": "MANAGED", "preset_retrieval_parameters": { "alpha": 0, "class_name": "class_name", "dense_similarity_cutoff": 0, "dense_similarity_top_k": 1, "enable_reranking": true, "files_top_k": 1, "rerank_top_n": 1, "retrieval_mode": "auto_routed", "retrieve_image_nodes": true, "retrieve_page_figure_nodes": true, "retrieve_page_screenshot_nodes": true, "search_filters": { "filters": [ { "key": "key", "value": 0, "operator": "!=" } ], "condition": "and" }, "search_filters_inference_schema": { "foo": { "foo": "bar" } }, "sparse_similarity_top_k": 1 }, "sparse_model_config": { "class_name": "class_name", "model_type": "auto" }, "status": "CREATED", "transform_config": { "chunk_overlap": 0, "chunk_size": 1, "mode": "auto" }, "updated_at": "2019-12-27T18:11:19.117Z" } ``` ## Delete Pipeline `Pipelines.Delete(PipelineDeleteParamsparameters, CancellationTokencancellationToken = default)` **delete** `/api/v1/pipelines/{pipeline_id}` Delete a pipeline and all associated resources. Removes pipeline files, data sources, and vector store data. This operation is irreversible. ### Parameters - `PipelineDeleteParams parameters` - `required string pipelineID` ### Example ```csharp PipelineDeleteParams parameters = new() { PipelineID = "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e" }; await client.Pipelines.Delete(parameters); ``` ## Get Pipeline Status `ManagedIngestionStatusResponse Pipelines.GetStatus(PipelineGetStatusParamsparameters, CancellationTokencancellationToken = default)` **get** `/api/v1/pipelines/{pipeline_id}/status` Get the ingestion status of a managed pipeline. Returns document counts, sync progress, and the last effective timestamp. Only available for managed pipelines. ### Parameters - `PipelineGetStatusParams parameters` - `required string pipelineID` - `Boolean? fullDetails` ### Returns - `class ManagedIngestionStatusResponse:` - `required Status Status` Status of the ingestion. - `"CANCELLED"Cancelled` - `"ERROR"Error` - `"IN_PROGRESS"InProgress` - `"NOT_STARTED"NotStarted` - `"PARTIAL_SUCCESS"PartialSuccess` - `"SUCCESS"Success` - `DateTimeOffset? DeploymentDate` Date of the deployment. - `DateTimeOffset? EffectiveAt` When the status is effective - `IReadOnlyList? Error` List of errors that occurred during ingestion. - `required string JobID` ID of the job that failed. - `required string Message` List of errors that occurred during ingestion. - `required Step Step` Name of the job that failed. - `"DATA_SOURCE"DataSource` - `"FILE_UPDATER"FileUpdater` - `"INGESTION"Ingestion` - `"MANAGED_INGESTION"ManagedIngestion` - `"METADATA_UPDATE"MetadataUpdate` - `"PARSE"Parse` - `"TRANSFORM"Transform` - `string? JobID` ID of the latest job. ### Example ```csharp PipelineGetStatusParams parameters = new() { PipelineID = "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e" }; var managedIngestionStatusResponse = await client.Pipelines.GetStatus(parameters); Console.WriteLine(managedIngestionStatusResponse); ``` #### Response ```json { "status": "CANCELLED", "deployment_date": "2019-12-27T18:11:19.117Z", "effective_at": "2019-12-27T18:11:19.117Z", "error": [ { "job_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "message": "message", "step": "DATA_SOURCE" } ], "job_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e" } ``` ## Upsert Pipeline `Pipeline Pipelines.Upsert(PipelineUpsertParamsparameters, CancellationTokencancellationToken = default)` **put** `/api/v1/pipelines` Upsert a pipeline. Updates the pipeline if one with the same name and project already exists, otherwise creates a new one. ### Parameters - `PipelineUpsertParams parameters` - `required string name` Body param - `string? organizationID` Query param - `string? projectID` Query param - `DataSinkCreate? dataSink` Body param: Schema for creating a data sink. - `string? dataSinkID` Body param: Data sink ID. When provided instead of data_sink, the data sink will be looked up by ID. - `EmbeddingConfig? embeddingConfig` Body param - `class AzureOpenAIEmbeddingConfig:` - `AzureOpenAIEmbedding Component` Configuration for the Azure OpenAI embedding model. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the OpenAI API. - `string ApiBase` The base URL for Azure deployment. - `string? ApiKey` The OpenAI API key. - `string ApiVersion` The version for Azure OpenAI API. - `string? AzureDeployment` The Azure deployment to use. - `string? AzureEndpoint` The Azure endpoint to use. - `string ClassName` - `IReadOnlyDictionary? DefaultHeaders` The default headers for API requests. - `Long? Dimensions` The number of dimensions on the output embedding vectors. Works only with v3 embedding models. - `Long EmbedBatchSize` The batch size for embedding calls. - `Long MaxRetries` Maximum number of retries. - `string ModelName` The name of the OpenAI embedding model. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Boolean ReuseClient` Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability. - `Double Timeout` Timeout for each request. - `Type Type` Type of the embedding model. - `"AZURE_EMBEDDING"AzureEmbedding` - `class BedrockEmbeddingConfig:` - `BedrockEmbedding Component` Configuration for the Bedrock embedding model. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the bedrock client. - `string? AwsAccessKeyID` AWS Access Key ID to use - `string? AwsSecretAccessKey` AWS Secret Access Key to use - `string? AwsSessionToken` AWS Session Token to use - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `Long MaxRetries` The maximum number of API retries. - `string ModelName` The modelId of the Bedrock model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `string? ProfileName` The name of aws profile to use. If not given, then the default profile is used. - `string? RegionName` AWS region name to use. Uses region configured in AWS CLI if not passed - `Double Timeout` The timeout for the Bedrock API request in seconds. It will be used for both connect and read timeouts. - `Type Type` Type of the embedding model. - `"BEDROCK_EMBEDDING"BedrockEmbedding` - `class CohereEmbeddingConfig:` - `CohereEmbedding Component` Configuration for the Cohere embedding model. - `required string? ApiKey` The Cohere API key. - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `string EmbeddingType` Embedding type. If not provided float embedding_type is used when needed. - `string? InputType` Model Input type. If not provided, search_document and search_query are used when needed. - `string ModelName` The modelId of the Cohere model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `string Truncate` Truncation type - START/ END/ NONE - `Type Type` Type of the embedding model. - `"COHERE_EMBEDDING"CohereEmbedding` - `class GeminiEmbeddingConfig:` - `GeminiEmbedding Component` Configuration for the Gemini embedding model. - `string? ApiBase` API base to access the model. Defaults to None. - `string? ApiKey` API key to access the model. Defaults to None. - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `string ModelName` The modelId of the Gemini model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Long? OutputDimensionality` Optional reduced dimension for output embeddings. Supported by models/text-embedding-004 and newer (e.g. gemini-embedding-001). Not supported by models/embedding-001. - `string? TaskType` The task for embedding model. - `string? Title` Title is only applicable for retrieval_document tasks, and is used to represent a document title. For other tasks, title is invalid. - `string? Transport` Transport to access the model. Defaults to None. - `Type Type` Type of the embedding model. - `"GEMINI_EMBEDDING"GeminiEmbedding` - `class HuggingFaceInferenceApiEmbeddingConfig:` - `HuggingFaceInferenceApiEmbedding Component` Configuration for the HuggingFace Inference API embedding model. - `Token? Token` Hugging Face token. Will default to the locally saved token. Pass token=False if you don’t want to send your token to the server. - `string` - `Boolean` - `string ClassName` - `IReadOnlyDictionary? Cookies` Additional cookies to send to the server. - `Long EmbedBatchSize` The batch size for embedding calls. - `IReadOnlyDictionary? Headers` Additional headers to send to the server. By default only the authorization and user-agent headers are sent. Values in this dictionary will override the default values. - `string? ModelName` Hugging Face model name. If None, the task will be used. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Pooling? Pooling` Enum of possible pooling choices with pooling behaviors. - `"cls"Cls` - `"last"Last` - `"mean"Mean` - `string? QueryInstruction` Instruction to prepend during query embedding. - `string? Task` Optional task to pick Hugging Face's recommended model, used when model_name is left as default of None. - `string? TextInstruction` Instruction to prepend during text embedding. - `Double? Timeout` The maximum number of seconds to wait for a response from the server. Loading a new model in Inference API can take up to several minutes. Defaults to None, meaning it will loop until the server is available. - `Type Type` Type of the embedding model. - `"HUGGINGFACE_API_EMBEDDING"HuggingfaceApiEmbedding` - `class OpenAIEmbeddingConfig:` - `OpenAIEmbedding Component` Configuration for the OpenAI embedding model. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the OpenAI API. - `string? ApiBase` The base URL for OpenAI API. - `string? ApiKey` The OpenAI API key. - `string? ApiVersion` The version for OpenAI API. - `string ClassName` - `IReadOnlyDictionary? DefaultHeaders` The default headers for API requests. - `Long? Dimensions` The number of dimensions on the output embedding vectors. Works only with v3 embedding models. - `Long EmbedBatchSize` The batch size for embedding calls. - `Long MaxRetries` Maximum number of retries. - `string ModelName` The name of the OpenAI embedding model. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Boolean ReuseClient` Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability. - `Double Timeout` Timeout for each request. - `Type Type` Type of the embedding model. - `"OPENAI_EMBEDDING"OpenAIEmbedding` - `class VertexAIEmbeddingConfig:` - `VertexTextEmbedding Component` Configuration for the VertexAI embedding model. - `required string? ClientEmail` The client email for the VertexAI credentials. - `required string Location` The default location to use when making API calls. - `required string? PrivateKey` The private key for the VertexAI credentials. - `required string? PrivateKeyID` The private key ID for the VertexAI credentials. - `required string Project` The default GCP project to use when making Vertex API calls. - `required string? TokenUri` The token URI for the VertexAI credentials. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the Vertex. - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `EmbedMode EmbedMode` The embedding mode to use. - `"classification"Classification` - `"clustering"Clustering` - `"default"Default` - `"retrieval"Retrieval` - `"similarity"Similarity` - `string ModelName` The modelId of the VertexAI model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Type Type` Type of the embedding model. - `"VERTEXAI_EMBEDDING"VertexaiEmbedding` - `string? embeddingModelConfigID` Body param: Embedding model config ID. When provided instead of embedding_config, the embedding model config will be looked up by ID. - `LlamaParseParameters llamaParseParameters` Body param: Settings that can be configured for how to use LlamaParse to parse files within a LlamaCloud pipeline. - `string? managedPipelineID` Body param: The ID of the ManagedPipeline this playground pipeline is linked to. - `PipelineMetadataConfig? metadataConfig` Body param: Metadata configuration for the pipeline. - `PipelineType pipelineType` Body param: Type of pipeline. Either PLAYGROUND or MANAGED. - `PresetRetrievalParams presetRetrievalParameters` Body param: Preset retrieval parameters for the pipeline. - `SparseModelConfig? sparseModelConfig` Body param: Configuration for sparse embedding models used in hybrid search. This allows users to choose between Splade and BM25 models for sparse retrieval in managed data sinks. - `string? status` Body param: Status of the pipeline deployment. - `TransformConfig? transformConfig` Body param: Configuration for the transformation. - `class AutoTransformConfig:` - `Long ChunkOverlap` Chunk overlap for the transformation. - `Long ChunkSize` Chunk size for the transformation. - `Mode Mode` - `"auto"Auto` - `class AdvancedModeTransformConfig:` - `ChunkingConfig ChunkingConfig` Configuration for the chunking. - `class NoneChunkingConfig:` - `Mode Mode` - `"none"None` - `class CharacterChunkingConfig:` - `Long ChunkOverlap` - `Long ChunkSize` - `Mode Mode` - `"character"Character` - `class TokenChunkingConfig:` - `Long ChunkOverlap` - `Long ChunkSize` - `Mode Mode` - `"token"Token` - `string Separator` - `class SentenceChunkingConfig:` - `Long ChunkOverlap` - `Long ChunkSize` - `Mode Mode` - `"sentence"Sentence` - `string ParagraphSeparator` - `string Separator` - `class SemanticChunkingConfig:` - `Long BreakpointPercentileThreshold` - `Long BufferSize` - `Mode Mode` - `"semantic"Semantic` - `Mode Mode` - `"advanced"Advanced` - `SegmentationConfig SegmentationConfig` Configuration for the segmentation. - `class NoneSegmentationConfig:` - `Mode Mode` - `"none"None` - `class PageSegmentationConfig:` - `Mode Mode` - `"page"Page` - `string PageSeparator` - `class ElementSegmentationConfig:` - `Mode Mode` - `"element"Element` ### Returns - `class Pipeline:` Schema for a pipeline. - `required string ID` Unique identifier - `required EmbeddingConfig EmbeddingConfig` - `class AzureOpenAIEmbeddingConfig:` - `AzureOpenAIEmbedding Component` Configuration for the Azure OpenAI embedding model. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the OpenAI API. - `string ApiBase` The base URL for Azure deployment. - `string? ApiKey` The OpenAI API key. - `string ApiVersion` The version for Azure OpenAI API. - `string? AzureDeployment` The Azure deployment to use. - `string? AzureEndpoint` The Azure endpoint to use. - `string ClassName` - `IReadOnlyDictionary? DefaultHeaders` The default headers for API requests. - `Long? Dimensions` The number of dimensions on the output embedding vectors. Works only with v3 embedding models. - `Long EmbedBatchSize` The batch size for embedding calls. - `Long MaxRetries` Maximum number of retries. - `string ModelName` The name of the OpenAI embedding model. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Boolean ReuseClient` Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability. - `Double Timeout` Timeout for each request. - `Type Type` Type of the embedding model. - `"AZURE_EMBEDDING"AzureEmbedding` - `class BedrockEmbeddingConfig:` - `BedrockEmbedding Component` Configuration for the Bedrock embedding model. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the bedrock client. - `string? AwsAccessKeyID` AWS Access Key ID to use - `string? AwsSecretAccessKey` AWS Secret Access Key to use - `string? AwsSessionToken` AWS Session Token to use - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `Long MaxRetries` The maximum number of API retries. - `string ModelName` The modelId of the Bedrock model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `string? ProfileName` The name of aws profile to use. If not given, then the default profile is used. - `string? RegionName` AWS region name to use. Uses region configured in AWS CLI if not passed - `Double Timeout` The timeout for the Bedrock API request in seconds. It will be used for both connect and read timeouts. - `Type Type` Type of the embedding model. - `"BEDROCK_EMBEDDING"BedrockEmbedding` - `class CohereEmbeddingConfig:` - `CohereEmbedding Component` Configuration for the Cohere embedding model. - `required string? ApiKey` The Cohere API key. - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `string EmbeddingType` Embedding type. If not provided float embedding_type is used when needed. - `string? InputType` Model Input type. If not provided, search_document and search_query are used when needed. - `string ModelName` The modelId of the Cohere model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `string Truncate` Truncation type - START/ END/ NONE - `Type Type` Type of the embedding model. - `"COHERE_EMBEDDING"CohereEmbedding` - `class GeminiEmbeddingConfig:` - `GeminiEmbedding Component` Configuration for the Gemini embedding model. - `string? ApiBase` API base to access the model. Defaults to None. - `string? ApiKey` API key to access the model. Defaults to None. - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `string ModelName` The modelId of the Gemini model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Long? OutputDimensionality` Optional reduced dimension for output embeddings. Supported by models/text-embedding-004 and newer (e.g. gemini-embedding-001). Not supported by models/embedding-001. - `string? TaskType` The task for embedding model. - `string? Title` Title is only applicable for retrieval_document tasks, and is used to represent a document title. For other tasks, title is invalid. - `string? Transport` Transport to access the model. Defaults to None. - `Type Type` Type of the embedding model. - `"GEMINI_EMBEDDING"GeminiEmbedding` - `class HuggingFaceInferenceApiEmbeddingConfig:` - `HuggingFaceInferenceApiEmbedding Component` Configuration for the HuggingFace Inference API embedding model. - `Token? Token` Hugging Face token. Will default to the locally saved token. Pass token=False if you don’t want to send your token to the server. - `string` - `Boolean` - `string ClassName` - `IReadOnlyDictionary? Cookies` Additional cookies to send to the server. - `Long EmbedBatchSize` The batch size for embedding calls. - `IReadOnlyDictionary? Headers` Additional headers to send to the server. By default only the authorization and user-agent headers are sent. Values in this dictionary will override the default values. - `string? ModelName` Hugging Face model name. If None, the task will be used. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Pooling? Pooling` Enum of possible pooling choices with pooling behaviors. - `"cls"Cls` - `"last"Last` - `"mean"Mean` - `string? QueryInstruction` Instruction to prepend during query embedding. - `string? Task` Optional task to pick Hugging Face's recommended model, used when model_name is left as default of None. - `string? TextInstruction` Instruction to prepend during text embedding. - `Double? Timeout` The maximum number of seconds to wait for a response from the server. Loading a new model in Inference API can take up to several minutes. Defaults to None, meaning it will loop until the server is available. - `Type Type` Type of the embedding model. - `"HUGGINGFACE_API_EMBEDDING"HuggingfaceApiEmbedding` - `class ManagedOpenAIEmbedding:` - `Component Component` Configuration for the Managed OpenAI embedding model. - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `ModelName ModelName` The name of the OpenAI embedding model. - `"openai-text-embedding-3-small"OpenAITextEmbedding3Small` - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Type Type` Type of the embedding model. - `"MANAGED_OPENAI_EMBEDDING"ManagedOpenAIEmbedding` - `class OpenAIEmbeddingConfig:` - `OpenAIEmbedding Component` Configuration for the OpenAI embedding model. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the OpenAI API. - `string? ApiBase` The base URL for OpenAI API. - `string? ApiKey` The OpenAI API key. - `string? ApiVersion` The version for OpenAI API. - `string ClassName` - `IReadOnlyDictionary? DefaultHeaders` The default headers for API requests. - `Long? Dimensions` The number of dimensions on the output embedding vectors. Works only with v3 embedding models. - `Long EmbedBatchSize` The batch size for embedding calls. - `Long MaxRetries` Maximum number of retries. - `string ModelName` The name of the OpenAI embedding model. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Boolean ReuseClient` Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability. - `Double Timeout` Timeout for each request. - `Type Type` Type of the embedding model. - `"OPENAI_EMBEDDING"OpenAIEmbedding` - `class VertexAIEmbeddingConfig:` - `VertexTextEmbedding Component` Configuration for the VertexAI embedding model. - `required string? ClientEmail` The client email for the VertexAI credentials. - `required string Location` The default location to use when making API calls. - `required string? PrivateKey` The private key for the VertexAI credentials. - `required string? PrivateKeyID` The private key ID for the VertexAI credentials. - `required string Project` The default GCP project to use when making Vertex API calls. - `required string? TokenUri` The token URI for the VertexAI credentials. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the Vertex. - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `EmbedMode EmbedMode` The embedding mode to use. - `"classification"Classification` - `"clustering"Clustering` - `"default"Default` - `"retrieval"Retrieval` - `"similarity"Similarity` - `string ModelName` The modelId of the VertexAI model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Type Type` Type of the embedding model. - `"VERTEXAI_EMBEDDING"VertexaiEmbedding` - `required string Name` - `required string ProjectID` - `ConfigHash? ConfigHash` Hashes for the configuration of a pipeline. - `string? EmbeddingConfigHash` Hash of the embedding config. - `string? ParsingConfigHash` Hash of the llama parse parameters. - `string? TransformConfigHash` Hash of the transform config. - `DateTimeOffset? CreatedAt` Creation datetime - `DataSink? DataSink` Schema for a data sink. - `required string ID` Unique identifier - `required Component Component` Component that implements the data sink - `IReadOnlyDictionary` - `class CloudPineconeVectorStore:` Cloud Pinecone Vector Store. This class is used to store the configuration for a Pinecone vector store, so that it can be created and used in LlamaCloud. Args: api_key (str): API key for authenticating with Pinecone index_name (str): name of the Pinecone index namespace (optional[str]): namespace to use in the Pinecone index insert_kwargs (optional[dict]): additional kwargs to pass during insertion - `required string ApiKey` The API key for authenticating with Pinecone - `required string IndexName` - `string ClassName` - `IReadOnlyDictionary? InsertKwargs` - `string? Namespace` - `SupportsNestedMetadataFilters SupportsNestedMetadataFilters` - `trueTrue` - `class CloudPostgresVectorStore:` - `required string Database` - `required Long EmbedDim` - `required string Host` - `required string Password` - `required Long Port` - `required string SchemaName` - `required string TableName` - `required string User` - `string ClassName` - `PgVectorHnswSettings? HnswSettings` HNSW settings for PGVector. - `DistanceMethod DistanceMethod` The distance method to use. - `"cosine"Cosine` - `"hamming"Hamming` - `"ip"IP` - `"jaccard"Jaccard` - `"l1"L1` - `"l2"L2` - `Long EfConstruction` The number of edges to use during the construction phase. - `Long EfSearch` The number of edges to use during the search phase. - `Long M` The number of bi-directional links created for each new element. - `VectorType VectorType` The type of vector to use. - `"bit"Bit` - `"half_vec"HalfVec` - `"sparse_vec"SparseVec` - `"vector"Vector` - `Boolean? HybridSearch` - `Boolean PerformSetup` - `Boolean SupportsNestedMetadataFilters` - `class CloudQdrantVectorStore:` Cloud Qdrant Vector Store. This class is used to store the configuration for a Qdrant vector store, so that it can be created and used in LlamaCloud. Args: collection_name (str): name of the Qdrant collection url (str): url of the Qdrant instance api_key (str): API key for authenticating with Qdrant max_retries (int): maximum number of retries in case of a failure. Defaults to 3 client_kwargs (dict): additional kwargs to pass to the Qdrant client - `required string ApiKey` - `required string CollectionName` - `required string Url` - `string ClassName` - `IReadOnlyDictionary ClientKwargs` - `Long MaxRetries` - `SupportsNestedMetadataFilters SupportsNestedMetadataFilters` - `trueTrue` - `class CloudAzureAISearchVectorStore:` Cloud Azure AI Search Vector Store. - `required string SearchServiceApiKey` - `required string SearchServiceEndpoint` - `string ClassName` - `string? ClientID` - `string? ClientSecret` - `Long? EmbeddingDimension` - `IReadOnlyDictionary? FilterableMetadataFieldKeys` - `string? IndexName` - `string? SearchServiceApiVersion` - `SupportsNestedMetadataFilters SupportsNestedMetadataFilters` - `trueTrue` - `string? TenantID` - `class CloudMongoDBAtlasVectorSearch:` Cloud MongoDB Atlas Vector Store. This class is used to store the configuration for a MongoDB Atlas vector store, so that it can be created and used in LlamaCloud. Args: mongodb_uri (str): URI for connecting to MongoDB Atlas db_name (str): name of the MongoDB database collection_name (str): name of the MongoDB collection vector_index_name (str): name of the MongoDB Atlas vector index fulltext_index_name (str): name of the MongoDB Atlas full-text index - `required string CollectionName` - `required string DBName` - `required string MongoDBUri` - `string ClassName` - `Long? EmbeddingDimension` - `string? FulltextIndexName` - `Boolean SupportsNestedMetadataFilters` - `string? VectorIndexName` - `class CloudMilvusVectorStore:` Cloud Milvus Vector Store. - `required string Uri` - `string? Token` - `string ClassName` - `string? CollectionName` - `Long? EmbeddingDimension` - `Boolean SupportsNestedMetadataFilters` - `class CloudAstraDBVectorStore:` Cloud AstraDB Vector Store. This class is used to store the configuration for an AstraDB vector store, so that it can be created and used in LlamaCloud. Args: token (str): The Astra DB Application Token to use. api_endpoint (str): The Astra DB JSON API endpoint for your database. collection_name (str): Collection name to use. If not existing, it will be created. embedding_dimension (int): Length of the embedding vectors in use. keyspace (optional[str]): The keyspace to use. If not provided, 'default_keyspace' - `required string Token` The Astra DB Application Token to use - `required string ApiEndpoint` The Astra DB JSON API endpoint for your database - `required string CollectionName` Collection name to use. If not existing, it will be created - `required Long EmbeddingDimension` Length of the embedding vectors in use - `string ClassName` - `string? Keyspace` The keyspace to use. If not provided, 'default_keyspace' - `SupportsNestedMetadataFilters SupportsNestedMetadataFilters` - `trueTrue` - `required string Name` The name of the data sink. - `required string ProjectID` - `required SinkType SinkType` - `"ASTRA_DB"AstraDB` - `"AZUREAI_SEARCH"AzureaiSearch` - `"MILVUS"Milvus` - `"MONGODB_ATLAS"MongoDBAtlas` - `"PINECONE"Pinecone` - `"POSTGRES"Postgres` - `"QDRANT"Qdrant` - `DateTimeOffset? CreatedAt` Creation datetime - `DateTimeOffset? UpdatedAt` Update datetime - `EmbeddingModelConfig? EmbeddingModelConfig` Schema for an embedding model config. - `required string ID` Unique identifier - `required EmbeddingConfig EmbeddingConfig` The embedding configuration for the embedding model config. - `class AzureOpenAIEmbeddingConfig:` - `class BedrockEmbeddingConfig:` - `class CohereEmbeddingConfig:` - `class GeminiEmbeddingConfig:` - `class HuggingFaceInferenceApiEmbeddingConfig:` - `class OpenAIEmbeddingConfig:` - `class VertexAIEmbeddingConfig:` - `required string Name` The name of the embedding model config. - `required string ProjectID` - `DateTimeOffset? CreatedAt` Creation datetime - `DateTimeOffset? UpdatedAt` Update datetime - `string? EmbeddingModelConfigID` The ID of the EmbeddingModelConfig this pipeline is using. - `LlamaParseParameters? LlamaParseParameters` Settings that can be configured for how to use LlamaParse to parse files within a LlamaCloud pipeline. - `Boolean? AdaptiveLongTable` - `Boolean? AggressiveTableExtraction` - `Boolean? AnnotateLinks` - `Boolean? AutoMode` - `string? AutoModeConfigurationJson` - `Boolean? AutoModeTriggerOnImageInPage` - `string? AutoModeTriggerOnRegexpInPage` - `Boolean? AutoModeTriggerOnTableInPage` - `string? AutoModeTriggerOnTextInPage` - `string? AzureOpenAIApiVersion` - `string? AzureOpenAIDeploymentName` - `string? AzureOpenAIEndpoint` - `string? AzureOpenAIKey` - `Double? BboxBottom` - `Double? BboxLeft` - `Double? BboxRight` - `Double? BboxTop` - `string? BoundingBox` - `Boolean? CompactMarkdownTable` - `string? ComplementalFormattingInstruction` - `string? ConfidenceScoreEffort` - `string? ContentGuidelineInstruction` - `Boolean? ContinuousMode` - `Boolean? DisableImageExtraction` - `Boolean? DisableOcr` - `Boolean? DisableReconstruction` - `Boolean? DoNotCache` - `Boolean? DoNotUnrollColumns` - `Boolean? EnableCostOptimizer` - `Boolean? ExtractCharts` - `Boolean? ExtractLayout` - `Boolean? ExtractPrintedPageNumber` - `Boolean? FastMode` - `string? FormattingInstruction` - `string? Gpt4oApiKey` - `Boolean? Gpt4oMode` - `Boolean? GuessXlsxSheetName` - `Boolean? HideFooters` - `Boolean? HideHeaders` - `Boolean? HighResOcr` - `Boolean? HtmlMakeAllElementsVisible` - `Boolean? HtmlRemoveFixedElements` - `Boolean? HtmlRemoveNavigationElements` - `string? HttpProxy` - `Boolean? IgnoreDocumentElementsForLayoutDetection` - `IReadOnlyList? ImagesToSave` - `"embedded"Embedded` - `"layout"Layout` - `"screenshot"Screenshot` - `Boolean? InlineImagesInMarkdown` - `string? InputS3Path` - `string? InputS3Region` - `string? InputUrl` - `Boolean? InternalIsScreenshotJob` - `Boolean? InvalidateCache` - `Boolean? IsFormattingInstruction` - `Double? JobTimeoutExtraTimePerPageInSeconds` - `Double? JobTimeoutInSeconds` - `Boolean? KeepPageSeparatorWhenMergingTables` - `IReadOnlyList Languages` - `"abq"Abq` - `"ady"Ady` - `"af"Af` - `"ang"Ang` - `"ar"Ar` - `"as"As` - `"ava"Ava` - `"az"Az` - `"be"Be` - `"bg"Bg` - `"bgc"Bgc` - `"bh"Bh` - `"bho"Bho` - `"bn"Bn` - `"bs"Bs` - `"ch_sim"ChSim` - `"ch_tra"ChTra` - `"che"Che` - `"cs"Cs` - `"cy"Cy` - `"da"Da` - `"dar"Dar` - `"de"De` - `"en"En` - `"es"Es` - `"et"Et` - `"fa"Fa` - `"fr"Fr` - `"ga"Ga` - `"gom"Gom` - `"hi"Hi` - `"hr"Hr` - `"hu"Hu` - `"id"ID` - `"inh"Inh` - `"is"Is` - `"it"It` - `"ja"Ja` - `"kbd"Kbd` - `"kn"Kn` - `"ko"Ko` - `"ku"Ku` - `"la"La` - `"lbe"Lbe` - `"lez"Lez` - `"lt"Lt` - `"lv"Lv` - `"mah"Mah` - `"mai"Mai` - `"mi"Mi` - `"mn"Mn` - `"mni"Mni` - `"mr"Mr` - `"ms"Ms` - `"mt"Mt` - `"ne"Ne` - `"new"New` - `"nl"Nl` - `"no"No` - `"oc"Oc` - `"pi"Pi` - `"pl"Pl` - `"pt"Pt` - `"ro"Ro` - `"rs_cyrillic"RsCyrillic` - `"rs_latin"RsLatin` - `"ru"Ru` - `"sa"Sa` - `"sck"Sck` - `"sk"Sk` - `"sl"Sl` - `"sq"Sq` - `"sv"Sv` - `"sw"Sw` - `"ta"Ta` - `"tab"Tab` - `"te"Te` - `"th"Th` - `"tjk"Tjk` - `"tl"Tl` - `"tr"Tr` - `"ug"Ug` - `"uk"Uk` - `"ur"Ur` - `"uz"Uz` - `"vi"Vi` - `Boolean? LayoutAware` - `Boolean? LineLevelBoundingBox` - `string? MarkdownTableMultilineHeaderSeparator` - `Long? MaxPages` - `Long? MaxPagesEnforced` - `Boolean? MergeTablesAcrossPagesInMarkdown` - `string? Model` - `Boolean? OutlinedTableExtraction` - `Boolean? OutputPdfOfDocument` - `string? OutputS3PathPrefix` - `string? OutputS3Region` - `Boolean? OutputTablesAsHtml` - `Double? PageErrorTolerance` - `string? PageFooterPrefix` - `string? PageFooterSuffix` - `string? PageHeaderPrefix` - `string? PageHeaderSuffix` - `string? PagePrefix` - `string? PageSeparator` - `string? PageSuffix` - `ParsingMode? ParseMode` Enum for representing the mode of parsing to be used. - `"parse_document_with_agent"ParseDocumentWithAgent` - `"parse_document_with_llm"ParseDocumentWithLlm` - `"parse_document_with_lvm"ParseDocumentWithLvm` - `"parse_page_with_agent"ParsePageWithAgent` - `"parse_page_with_layout_agent"ParsePageWithLayoutAgent` - `"parse_page_with_llm"ParsePageWithLlm` - `"parse_page_with_lvm"ParsePageWithLvm` - `"parse_page_without_llm"ParsePageWithoutLlm` - `string? ParsingInstruction` - `Boolean? PreciseBoundingBox` - `Boolean? PremiumMode` - `Boolean? PresentationOutOfBoundsContent` - `Boolean? PresentationSkipEmbeddedData` - `Boolean? PreserveLayoutAlignmentAcrossPages` - `Boolean? PreserveVerySmallText` - `string? Preset` - `Priority? Priority` The priority for the request. This field may be ignored or overwritten depending on the organization tier. - `"critical"Critical` - `"high"High` - `"low"Low` - `"medium"Medium` - `string? ProjectID` - `Boolean? RemoveHiddenText` - `FailPageMode? ReplaceFailedPageMode` Enum for representing the different available page error handling modes. - `"blank_page"BlankPage` - `"error_message"ErrorMessage` - `"raw_text"RawText` - `string? ReplaceFailedPageWithErrorMessagePrefix` - `string? ReplaceFailedPageWithErrorMessageSuffix` - `Boolean? SaveImages` - `Boolean? SkipDiagonalText` - `Boolean? SpecializedChartParsingAgentic` - `Boolean? SpecializedChartParsingEfficient` - `Boolean? SpecializedChartParsingPlus` - `Boolean? SpecializedImageParsing` - `Boolean? SpreadsheetExtractSubTables` - `Boolean? SpreadsheetForceFormulaComputation` - `Boolean? SpreadsheetIncludeHiddenSheets` - `Boolean? StrictModeBuggyFont` - `Boolean? StrictModeImageExtraction` - `Boolean? StrictModeImageOcr` - `Boolean? StrictModeReconstruction` - `Boolean? StructuredOutput` - `string? StructuredOutputJsonSchema` - `string? StructuredOutputJsonSchemaName` - `string? SystemPrompt` - `string? SystemPromptAppend` - `Boolean? TakeScreenshot` - `string? TargetPages` - `string? Tier` - `Boolean? UseVendorMultimodalModel` - `string? UserPrompt` - `string? VendorMultimodalApiKey` - `string? VendorMultimodalModelName` - `string? Version` - `IReadOnlyList? WebhookConfigurations` Outbound webhook endpoints to notify on job status changes - `IReadOnlyList? WebhookEvents` Events to subscribe to (e.g. 'parse.success', 'extract.error'). If null, all events are delivered. - `"classify.cancelled"ClassifyCancelled` - `"classify.error"ClassifyError` - `"classify.partial_success"ClassifyPartialSuccess` - `"classify.pending"ClassifyPending` - `"classify.running"ClassifyRunning` - `"classify.success"ClassifySuccess` - `"extract.cancelled"ExtractCancelled` - `"extract.error"ExtractError` - `"extract.partial_success"ExtractPartialSuccess` - `"extract.pending"ExtractPending` - `"extract.success"ExtractSuccess` - `"parse.cancelled"ParseCancelled` - `"parse.error"ParseError` - `"parse.partial_success"ParsePartialSuccess` - `"parse.pending"ParsePending` - `"parse.running"ParseRunning` - `"parse.success"ParseSuccess` - `"sheets.cancelled"SheetsCancelled` - `"sheets.error"SheetsError` - `"sheets.partial_success"SheetsPartialSuccess` - `"sheets.pending"SheetsPending` - `"sheets.success"SheetsSuccess` - `"split.cancelled"SplitCancelled` - `"split.error"SplitError` - `"split.pending"SplitPending` - `"split.processing"SplitProcessing` - `"split.success"SplitSuccess` - `"unmapped_event"UnmappedEvent` - `IReadOnlyDictionary? WebhookHeaders` Custom HTTP headers sent with each webhook request (e.g. auth tokens) - `string? WebhookOutputFormat` Response format sent to the webhook: 'string' (default) or 'json' - `string? WebhookSigningSecret` Shared signing secret used to sign webhook deliveries. When set, each request includes an HMAC-SHA256 signature of the request body in the 'LC-Signature' header (value 'sha256='). Recompute the HMAC over the raw request body with this secret to verify the delivery is authentic. - `string? WebhookUrl` URL to receive webhook POST notifications - `string? WebhookUrl` - `string? ManagedPipelineID` The ID of the ManagedPipeline this playground pipeline is linked to. - `PipelineMetadataConfig? MetadataConfig` Metadata configuration for the pipeline. - `IReadOnlyList ExcludedEmbedMetadataKeys` List of metadata keys to exclude from embeddings - `IReadOnlyList ExcludedLlmMetadataKeys` List of metadata keys to exclude from LLM during retrieval - `PipelineType PipelineType` Type of pipeline. Either PLAYGROUND or MANAGED. - `"MANAGED"Managed` - `"PLAYGROUND"Playground` - `PresetRetrievalParams PresetRetrievalParameters` Preset retrieval parameters for the pipeline. - `Double? Alpha` Alpha value for hybrid retrieval to determine the weights between dense and sparse retrieval. 0 is sparse retrieval and 1 is dense retrieval. - `string ClassName` - `Double? DenseSimilarityCutoff` Minimum similarity score wrt query for retrieval - `Long? DenseSimilarityTopK` Number of nodes for dense retrieval. - `Boolean? EnableReranking` Enable reranking for retrieval - `Long? FilesTopK` Number of files to retrieve (only for retrieval mode files_via_metadata and files_via_content). - `Long? RerankTopN` Number of reranked nodes for returning. - `RetrievalMode RetrievalMode` The retrieval mode for the query. - `"auto_routed"AutoRouted` - `"chunks"Chunks` - `"files_via_content"FilesViaContent` - `"files_via_metadata"FilesViaMetadata` - `Boolean RetrieveImageNodes` Whether to retrieve image nodes. - `Boolean RetrievePageFigureNodes` Whether to retrieve page figure nodes. - `Boolean RetrievePageScreenshotNodes` Whether to retrieve page screenshot nodes. - `MetadataFilters? SearchFilters` Metadata filters for vector stores. - `required IReadOnlyList Filters` - `class MetadataFilter:` Comprehensive metadata filter for vector stores to support more operators. Value uses Strict types, as int, float and str are compatible types and were all converted to string before. See: https://docs.pydantic.dev/latest/usage/types/#strict-types - `required string Key` - `required Value? Value` - `Double` - `string` - `IReadOnlyList` - `IReadOnlyList` - `IReadOnlyList` - `Operator Operator` Vector store filter operator. - `"!="` - `"<"` - `"<="` - `"=="` - `">"` - `">="` - `"all"All` - `"any"Any` - `"contains"Contains` - `"in"In` - `"is_empty"IsEmpty` - `"nin"Nin` - `"text_match"TextMatch` - `"text_match_insensitive"TextMatchInsensitive` - `class MetadataFilters:` Metadata filters for vector stores. - `Condition? Condition` Vector store filter conditions to combine different filters. - `"and"And` - `"not"Not` - `"or"Or` - `IReadOnlyDictionary? SearchFiltersInferenceSchema` JSON Schema that will be used to infer search_filters. Omit or leave as null to skip inference. - `IReadOnlyDictionary` - `IReadOnlyList` - `string` - `Double` - `Boolean` - `Long? SparseSimilarityTopK` Number of nodes for sparse retrieval. - `SparseModelConfig? SparseModelConfig` Configuration for sparse embedding models used in hybrid search. This allows users to choose between Splade and BM25 models for sparse retrieval in managed data sinks. - `string ClassName` - `ModelType ModelType` The sparse model type to use. 'bm25' uses Qdrant's FastEmbed BM25 model (default for new pipelines), 'splade' uses HuggingFace Splade model, 'auto' selects based on deployment mode (BYOC uses term frequency, Cloud uses Splade). - `"auto"Auto` - `"bm25"Bm25` - `"splade"Splade` - `Status? Status` Status of the pipeline. - `"CREATED"Created` - `"DELETING"Deleting` - `TransformConfig TransformConfig` Configuration for the transformation. - `class AutoTransformConfig:` - `Long ChunkOverlap` Chunk overlap for the transformation. - `Long ChunkSize` Chunk size for the transformation. - `Mode Mode` - `"auto"Auto` - `class AdvancedModeTransformConfig:` - `ChunkingConfig ChunkingConfig` Configuration for the chunking. - `class NoneChunkingConfig:` - `Mode Mode` - `"none"None` - `class CharacterChunkingConfig:` - `Long ChunkOverlap` - `Long ChunkSize` - `Mode Mode` - `"character"Character` - `class TokenChunkingConfig:` - `Long ChunkOverlap` - `Long ChunkSize` - `Mode Mode` - `"token"Token` - `string Separator` - `class SentenceChunkingConfig:` - `Long ChunkOverlap` - `Long ChunkSize` - `Mode Mode` - `"sentence"Sentence` - `string ParagraphSeparator` - `string Separator` - `class SemanticChunkingConfig:` - `Long BreakpointPercentileThreshold` - `Long BufferSize` - `Mode Mode` - `"semantic"Semantic` - `Mode Mode` - `"advanced"Advanced` - `SegmentationConfig SegmentationConfig` Configuration for the segmentation. - `class NoneSegmentationConfig:` - `Mode Mode` - `"none"None` - `class PageSegmentationConfig:` - `Mode Mode` - `"page"Page` - `string PageSeparator` - `class ElementSegmentationConfig:` - `Mode Mode` - `"element"Element` - `DateTimeOffset? UpdatedAt` Update datetime ### Example ```csharp PipelineUpsertParams parameters = new() { Name = "x" }; var pipeline = await client.Pipelines.Upsert(parameters); Console.WriteLine(pipeline); ``` #### Response ```json { "id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "embedding_config": { "component": { "additional_kwargs": { "foo": "bar" }, "api_base": "api_base", "api_key": "api_key", "api_version": "api_version", "azure_deployment": "azure_deployment", "azure_endpoint": "azure_endpoint", "class_name": "class_name", "default_headers": { "foo": "string" }, "dimensions": 0, "embed_batch_size": 1, "max_retries": 0, "model_name": "model_name", "num_workers": 0, "reuse_client": true, "timeout": 0 }, "type": "AZURE_EMBEDDING" }, "name": "name", "project_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "config_hash": { "embedding_config_hash": "embedding_config_hash", "parsing_config_hash": "parsing_config_hash", "transform_config_hash": "transform_config_hash" }, "created_at": "2019-12-27T18:11:19.117Z", "data_sink": { "id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "component": { "foo": "bar" }, "name": "name", "project_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "sink_type": "ASTRA_DB", "created_at": "2019-12-27T18:11:19.117Z", "updated_at": "2019-12-27T18:11:19.117Z" }, "embedding_model_config": { "id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "embedding_config": { "component": { "additional_kwargs": { "foo": "bar" }, "api_base": "api_base", "api_key": "api_key", "api_version": "api_version", "azure_deployment": "azure_deployment", "azure_endpoint": "azure_endpoint", "class_name": "class_name", "default_headers": { "foo": "string" }, "dimensions": 0, "embed_batch_size": 1, "max_retries": 0, "model_name": "model_name", "num_workers": 0, "reuse_client": true, "timeout": 0 }, "type": "AZURE_EMBEDDING" }, "name": "name", "project_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "created_at": "2019-12-27T18:11:19.117Z", "updated_at": "2019-12-27T18:11:19.117Z" }, "embedding_model_config_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "llama_parse_parameters": { "adaptive_long_table": true, "aggressive_table_extraction": true, "annotate_links": true, "auto_mode": true, "auto_mode_configuration_json": "auto_mode_configuration_json", "auto_mode_trigger_on_image_in_page": true, "auto_mode_trigger_on_regexp_in_page": "auto_mode_trigger_on_regexp_in_page", "auto_mode_trigger_on_table_in_page": true, "auto_mode_trigger_on_text_in_page": "auto_mode_trigger_on_text_in_page", "azure_openai_api_version": "azure_openai_api_version", "azure_openai_deployment_name": "azure_openai_deployment_name", "azure_openai_endpoint": "azure_openai_endpoint", "azure_openai_key": "azure_openai_key", "bbox_bottom": 0, "bbox_left": 0, "bbox_right": 0, "bbox_top": 0, "bounding_box": "bounding_box", "compact_markdown_table": true, "complemental_formatting_instruction": "complemental_formatting_instruction", "confidence_score_effort": "confidence_score_effort", "content_guideline_instruction": "content_guideline_instruction", "continuous_mode": true, "disable_image_extraction": true, "disable_ocr": true, "disable_reconstruction": true, "do_not_cache": true, "do_not_unroll_columns": true, "enable_cost_optimizer": true, "extract_charts": true, "extract_layout": true, "extract_printed_page_number": true, "fast_mode": true, "formatting_instruction": "formatting_instruction", "gpt4o_api_key": "gpt4o_api_key", "gpt4o_mode": true, "guess_xlsx_sheet_name": true, "hide_footers": true, "hide_headers": true, "high_res_ocr": true, "html_make_all_elements_visible": true, "html_remove_fixed_elements": true, "html_remove_navigation_elements": true, "http_proxy": "http_proxy", "ignore_document_elements_for_layout_detection": true, "images_to_save": [ "embedded" ], "inline_images_in_markdown": true, "input_s3_path": "input_s3_path", "input_s3_region": "input_s3_region", "input_url": "input_url", "internal_is_screenshot_job": true, "invalidate_cache": true, "is_formatting_instruction": true, "job_timeout_extra_time_per_page_in_seconds": 0, "job_timeout_in_seconds": 0, "keep_page_separator_when_merging_tables": true, "languages": [ "abq" ], "layout_aware": true, "line_level_bounding_box": true, "markdown_table_multiline_header_separator": "markdown_table_multiline_header_separator", "max_pages": 0, "max_pages_enforced": 0, "merge_tables_across_pages_in_markdown": true, "model": "model", "outlined_table_extraction": true, "output_pdf_of_document": true, "output_s3_path_prefix": "output_s3_path_prefix", "output_s3_region": "output_s3_region", "output_tables_as_HTML": true, "page_error_tolerance": 0, "page_footer_prefix": "page_footer_prefix", "page_footer_suffix": "page_footer_suffix", "page_header_prefix": "page_header_prefix", "page_header_suffix": "page_header_suffix", "page_prefix": "page_prefix", "page_separator": "page_separator", "page_suffix": "page_suffix", "parse_mode": "parse_document_with_agent", "parsing_instruction": "parsing_instruction", "precise_bounding_box": true, "premium_mode": true, "presentation_out_of_bounds_content": true, "presentation_skip_embedded_data": true, "preserve_layout_alignment_across_pages": true, "preserve_very_small_text": true, "preset": "preset", "priority": "critical", "project_id": "project_id", "remove_hidden_text": true, "replace_failed_page_mode": "blank_page", "replace_failed_page_with_error_message_prefix": "replace_failed_page_with_error_message_prefix", "replace_failed_page_with_error_message_suffix": "replace_failed_page_with_error_message_suffix", "save_images": true, "skip_diagonal_text": true, "specialized_chart_parsing_agentic": true, "specialized_chart_parsing_efficient": true, "specialized_chart_parsing_plus": true, "specialized_image_parsing": true, "spreadsheet_extract_sub_tables": true, "spreadsheet_force_formula_computation": true, "spreadsheet_include_hidden_sheets": true, "strict_mode_buggy_font": true, "strict_mode_image_extraction": true, "strict_mode_image_ocr": true, "strict_mode_reconstruction": true, "structured_output": true, "structured_output_json_schema": "structured_output_json_schema", "structured_output_json_schema_name": "structured_output_json_schema_name", "system_prompt": "system_prompt", "system_prompt_append": "system_prompt_append", "take_screenshot": true, "target_pages": "target_pages", "tier": "tier", "use_vendor_multimodal_model": true, "user_prompt": "user_prompt", "vendor_multimodal_api_key": "vendor_multimodal_api_key", "vendor_multimodal_model_name": "vendor_multimodal_model_name", "version": "version", "webhook_configurations": [ { "webhook_events": [ "parse.success", "parse.error" ], "webhook_headers": { "Authorization": "Bearer sk-..." }, "webhook_output_format": "json", "webhook_signing_secret": "whsec_...", "webhook_url": "https://example.com/webhooks/llamacloud" } ], "webhook_url": "webhook_url" }, "managed_pipeline_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "metadata_config": { "excluded_embed_metadata_keys": [ "string" ], "excluded_llm_metadata_keys": [ "string" ] }, "pipeline_type": "MANAGED", "preset_retrieval_parameters": { "alpha": 0, "class_name": "class_name", "dense_similarity_cutoff": 0, "dense_similarity_top_k": 1, "enable_reranking": true, "files_top_k": 1, "rerank_top_n": 1, "retrieval_mode": "auto_routed", "retrieve_image_nodes": true, "retrieve_page_figure_nodes": true, "retrieve_page_screenshot_nodes": true, "search_filters": { "filters": [ { "key": "key", "value": 0, "operator": "!=" } ], "condition": "and" }, "search_filters_inference_schema": { "foo": { "foo": "bar" } }, "sparse_similarity_top_k": 1 }, "sparse_model_config": { "class_name": "class_name", "model_type": "auto" }, "status": "CREATED", "transform_config": { "chunk_overlap": 0, "chunk_size": 1, "mode": "auto" }, "updated_at": "2019-12-27T18:11:19.117Z" } ``` ## Run Search `PipelineRetrieveResponse Pipelines.Retrieve(PipelineRetrieveParamsparameters, CancellationTokencancellationToken = default)` **post** `/api/v1/pipelines/{pipeline_id}/retrieve` Run a retrieval query against a managed pipeline. Searches the pipeline's vector store using the provided query and retrieval parameters. Supports dense, sparse, and hybrid search modes with configurable top-k and reranking. ### Parameters - `PipelineRetrieveParams parameters` - `required string pipelineID` Path param - `required string query` Body param: The query to retrieve against. - `string? organizationID` Query param - `string? projectID` Query param - `Double? alpha` Body param: Alpha value for hybrid retrieval to determine the weights between dense and sparse retrieval. 0 is sparse retrieval and 1 is dense retrieval. - `string className` Body param - `Double? denseSimilarityCutoff` Body param: Minimum similarity score wrt query for retrieval - `Long? denseSimilarityTopK` Body param: Number of nodes for dense retrieval. - `Boolean? enableReranking` Body param: Enable reranking for retrieval - `Long? filesTopK` Body param: Number of files to retrieve (only for retrieval mode files_via_metadata and files_via_content). - `Long? rerankTopN` Body param: Number of reranked nodes for returning. - `RetrievalMode retrievalMode` Body param: The retrieval mode for the query. - `Boolean retrieveImageNodes` Body param: Whether to retrieve image nodes. - `Boolean retrievePageFigureNodes` Body param: Whether to retrieve page figure nodes. - `Boolean retrievePageScreenshotNodes` Body param: Whether to retrieve page screenshot nodes. - `MetadataFilters? searchFilters` Body param: Metadata filters for vector stores. - `IReadOnlyDictionary? searchFiltersInferenceSchema` Body param: JSON Schema that will be used to infer search_filters. Omit or leave as null to skip inference. - `IReadOnlyDictionary` - `IReadOnlyList` - `string` - `Double` - `Boolean` - `Long? sparseSimilarityTopK` Body param: Number of nodes for sparse retrieval. ### Returns - `class PipelineRetrieveResponse:` Schema for the result of an retrieval execution. - `required string PipelineID` The ID of the pipeline that the query was retrieved against. - `required IReadOnlyList RetrievalNodes` The nodes retrieved by the pipeline for the given query. - `required TextNode Node` Provided for backward compatibility. - `string ClassName` - `IReadOnlyList? Embedding` Embedding of the node. - `Long? EndCharIdx` End char index of the node. - `IReadOnlyList ExcludedEmbedMetadataKeys` Metadata keys that are excluded from text for the embed model. - `IReadOnlyList ExcludedLlmMetadataKeys` Metadata keys that are excluded from text for the LLM. - `IReadOnlyDictionary ExtraInfo` A flat dictionary of metadata fields - `string ID` Unique ID of the node. - `string MetadataSeperator` Separator between metadata fields when converting to string. - `string MetadataTemplate` Template for how metadata is formatted, with {key} and {value} placeholders. - `string Mimetype` MIME type of the node content. - `IReadOnlyDictionary Relationships` A mapping of relationships to other node information. - `class RelatedNodeInfo:` - `required string NodeID` - `string ClassName` - `string? Hash` - `IReadOnlyDictionary Metadata` - `NodeType? NodeType` - `"1"1` - `"2"2` - `"3"3` - `"4"4` - `"5"5` - `IReadOnlyList` - `required string NodeID` - `string ClassName` - `string? Hash` - `IReadOnlyDictionary Metadata` - `NodeType? NodeType` - `"1"1` - `"2"2` - `"3"3` - `"4"4` - `"5"5` - `Long? StartCharIdx` Start char index of the node. - `string Text` Text content of the node. - `string TextTemplate` Template for how text is formatted, with {content} and {metadata_str} placeholders. - `string ClassName` - `Double? Score` - `string ClassName` - `IReadOnlyList ImageNodes` The image nodes retrieved by the pipeline for the given query. Deprecated - will soon be replaced with 'page_screenshot_nodes'. - `required Node Node` - `required string FileID` The ID of the file that the page screenshot was taken from - `required Long ImageSize` The size of the image in bytes - `required Long PageIndex` The index of the page for which the screenshot is taken (0-indexed) - `IReadOnlyDictionary? Metadata` Metadata for the screenshot - `required Double Score` The score of the screenshot node - `string ClassName` - `MetadataFilters? InferredSearchFilters` Metadata filters for vector stores. - `required IReadOnlyList Filters` - `class MetadataFilter:` Comprehensive metadata filter for vector stores to support more operators. Value uses Strict types, as int, float and str are compatible types and were all converted to string before. See: https://docs.pydantic.dev/latest/usage/types/#strict-types - `required string Key` - `required Value? Value` - `Double` - `string` - `IReadOnlyList` - `IReadOnlyList` - `IReadOnlyList` - `Operator Operator` Vector store filter operator. - `"!="` - `"<"` - `"<="` - `"=="` - `">"` - `">="` - `"all"All` - `"any"Any` - `"contains"Contains` - `"in"In` - `"is_empty"IsEmpty` - `"nin"Nin` - `"text_match"TextMatch` - `"text_match_insensitive"TextMatchInsensitive` - `class MetadataFilters:` Metadata filters for vector stores. - `Condition? Condition` Vector store filter conditions to combine different filters. - `"and"And` - `"not"Not` - `"or"Or` - `IReadOnlyDictionary Metadata` Metadata associated with the retrieval execution - `IReadOnlyList PageFigureNodes` The page figure nodes retrieved by the pipeline for the given query. - `required Node Node` - `required Double Confidence` The confidence of the figure - `required string FigureName` The name of the figure - `required Long FigureSize` The size of the figure in bytes - `required string FileID` The ID of the file that the figure was taken from - `required Long PageIndex` The index of the page for which the figure is taken (0-indexed) - `Boolean IsLikelyNoise` Whether the figure is likely to be noise - `IReadOnlyDictionary? Metadata` Metadata for the figure - `required Double Score` The score of the figure node - `string ClassName` - `IReadOnlyDictionary RetrievalLatency` The end-to-end latency for retrieval and reranking. ### Example ```csharp PipelineRetrieveParams parameters = new() { PipelineID = "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", Query = "x", }; var pipeline = await client.Pipelines.Retrieve(parameters); Console.WriteLine(pipeline); ``` #### Response ```json { "pipeline_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "retrieval_nodes": [ { "node": { "class_name": "class_name", "embedding": [ 0 ], "end_char_idx": 0, "excluded_embed_metadata_keys": [ "string" ], "excluded_llm_metadata_keys": [ "string" ], "extra_info": { "foo": "bar" }, "id_": "id_", "metadata_seperator": "metadata_seperator", "metadata_template": "metadata_template", "mimetype": "mimetype", "relationships": { "foo": { "node_id": "node_id", "class_name": "class_name", "hash": "hash", "metadata": { "foo": "bar" }, "node_type": "1" } }, "start_char_idx": 0, "text": "text", "text_template": "text_template" }, "class_name": "class_name", "score": 0 } ], "class_name": "class_name", "image_nodes": [ { "node": { "file_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "image_size": 0, "page_index": 0, "metadata": { "foo": "bar" } }, "score": 0, "class_name": "class_name" } ], "inferred_search_filters": { "filters": [ { "key": "key", "value": 0, "operator": "!=" } ], "condition": "and" }, "metadata": { "foo": "string" }, "page_figure_nodes": [ { "node": { "confidence": 0, "figure_name": "figure_name", "figure_size": 0, "file_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "page_index": 0, "is_likely_noise": true, "metadata": { "foo": "bar" } }, "score": 0, "class_name": "class_name" } ], "retrieval_latency": { "foo": 0 } } ``` ## Domain Types ### Advanced Mode Transform Config - `class AdvancedModeTransformConfig:` - `ChunkingConfig ChunkingConfig` Configuration for the chunking. - `class NoneChunkingConfig:` - `Mode Mode` - `"none"None` - `class CharacterChunkingConfig:` - `Long ChunkOverlap` - `Long ChunkSize` - `Mode Mode` - `"character"Character` - `class TokenChunkingConfig:` - `Long ChunkOverlap` - `Long ChunkSize` - `Mode Mode` - `"token"Token` - `string Separator` - `class SentenceChunkingConfig:` - `Long ChunkOverlap` - `Long ChunkSize` - `Mode Mode` - `"sentence"Sentence` - `string ParagraphSeparator` - `string Separator` - `class SemanticChunkingConfig:` - `Long BreakpointPercentileThreshold` - `Long BufferSize` - `Mode Mode` - `"semantic"Semantic` - `Mode Mode` - `"advanced"Advanced` - `SegmentationConfig SegmentationConfig` Configuration for the segmentation. - `class NoneSegmentationConfig:` - `Mode Mode` - `"none"None` - `class PageSegmentationConfig:` - `Mode Mode` - `"page"Page` - `string PageSeparator` - `class ElementSegmentationConfig:` - `Mode Mode` - `"element"Element` ### Auto Transform Config - `class AutoTransformConfig:` - `Long ChunkOverlap` Chunk overlap for the transformation. - `Long ChunkSize` Chunk size for the transformation. - `Mode Mode` - `"auto"Auto` ### Azure OpenAI Embedding - `class AzureOpenAIEmbedding:` - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the OpenAI API. - `string ApiBase` The base URL for Azure deployment. - `string? ApiKey` The OpenAI API key. - `string ApiVersion` The version for Azure OpenAI API. - `string? AzureDeployment` The Azure deployment to use. - `string? AzureEndpoint` The Azure endpoint to use. - `string ClassName` - `IReadOnlyDictionary? DefaultHeaders` The default headers for API requests. - `Long? Dimensions` The number of dimensions on the output embedding vectors. Works only with v3 embedding models. - `Long EmbedBatchSize` The batch size for embedding calls. - `Long MaxRetries` Maximum number of retries. - `string ModelName` The name of the OpenAI embedding model. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Boolean ReuseClient` Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability. - `Double Timeout` Timeout for each request. ### Azure OpenAI Embedding Config - `class AzureOpenAIEmbeddingConfig:` - `AzureOpenAIEmbedding Component` Configuration for the Azure OpenAI embedding model. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the OpenAI API. - `string ApiBase` The base URL for Azure deployment. - `string? ApiKey` The OpenAI API key. - `string ApiVersion` The version for Azure OpenAI API. - `string? AzureDeployment` The Azure deployment to use. - `string? AzureEndpoint` The Azure endpoint to use. - `string ClassName` - `IReadOnlyDictionary? DefaultHeaders` The default headers for API requests. - `Long? Dimensions` The number of dimensions on the output embedding vectors. Works only with v3 embedding models. - `Long EmbedBatchSize` The batch size for embedding calls. - `Long MaxRetries` Maximum number of retries. - `string ModelName` The name of the OpenAI embedding model. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Boolean ReuseClient` Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability. - `Double Timeout` Timeout for each request. - `Type Type` Type of the embedding model. - `"AZURE_EMBEDDING"AzureEmbedding` ### Bedrock Embedding - `class BedrockEmbedding:` - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the bedrock client. - `string? AwsAccessKeyID` AWS Access Key ID to use - `string? AwsSecretAccessKey` AWS Secret Access Key to use - `string? AwsSessionToken` AWS Session Token to use - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `Long MaxRetries` The maximum number of API retries. - `string ModelName` The modelId of the Bedrock model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `string? ProfileName` The name of aws profile to use. If not given, then the default profile is used. - `string? RegionName` AWS region name to use. Uses region configured in AWS CLI if not passed - `Double Timeout` The timeout for the Bedrock API request in seconds. It will be used for both connect and read timeouts. ### Bedrock Embedding Config - `class BedrockEmbeddingConfig:` - `BedrockEmbedding Component` Configuration for the Bedrock embedding model. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the bedrock client. - `string? AwsAccessKeyID` AWS Access Key ID to use - `string? AwsSecretAccessKey` AWS Secret Access Key to use - `string? AwsSessionToken` AWS Session Token to use - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `Long MaxRetries` The maximum number of API retries. - `string ModelName` The modelId of the Bedrock model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `string? ProfileName` The name of aws profile to use. If not given, then the default profile is used. - `string? RegionName` AWS region name to use. Uses region configured in AWS CLI if not passed - `Double Timeout` The timeout for the Bedrock API request in seconds. It will be used for both connect and read timeouts. - `Type Type` Type of the embedding model. - `"BEDROCK_EMBEDDING"BedrockEmbedding` ### Cohere Embedding - `class CohereEmbedding:` - `required string? ApiKey` The Cohere API key. - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `string EmbeddingType` Embedding type. If not provided float embedding_type is used when needed. - `string? InputType` Model Input type. If not provided, search_document and search_query are used when needed. - `string ModelName` The modelId of the Cohere model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `string Truncate` Truncation type - START/ END/ NONE ### Cohere Embedding Config - `class CohereEmbeddingConfig:` - `CohereEmbedding Component` Configuration for the Cohere embedding model. - `required string? ApiKey` The Cohere API key. - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `string EmbeddingType` Embedding type. If not provided float embedding_type is used when needed. - `string? InputType` Model Input type. If not provided, search_document and search_query are used when needed. - `string ModelName` The modelId of the Cohere model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `string Truncate` Truncation type - START/ END/ NONE - `Type Type` Type of the embedding model. - `"COHERE_EMBEDDING"CohereEmbedding` ### Data Sink Create - `class DataSinkCreate:` Schema for creating a data sink. - `required Component Component` Component that implements the data sink - `IReadOnlyDictionary` - `class CloudPineconeVectorStore:` Cloud Pinecone Vector Store. This class is used to store the configuration for a Pinecone vector store, so that it can be created and used in LlamaCloud. Args: api_key (str): API key for authenticating with Pinecone index_name (str): name of the Pinecone index namespace (optional[str]): namespace to use in the Pinecone index insert_kwargs (optional[dict]): additional kwargs to pass during insertion - `required string ApiKey` The API key for authenticating with Pinecone - `required string IndexName` - `string ClassName` - `IReadOnlyDictionary? InsertKwargs` - `string? Namespace` - `SupportsNestedMetadataFilters SupportsNestedMetadataFilters` - `trueTrue` - `class CloudPostgresVectorStore:` - `required string Database` - `required Long EmbedDim` - `required string Host` - `required string Password` - `required Long Port` - `required string SchemaName` - `required string TableName` - `required string User` - `string ClassName` - `PgVectorHnswSettings? HnswSettings` HNSW settings for PGVector. - `DistanceMethod DistanceMethod` The distance method to use. - `"cosine"Cosine` - `"hamming"Hamming` - `"ip"IP` - `"jaccard"Jaccard` - `"l1"L1` - `"l2"L2` - `Long EfConstruction` The number of edges to use during the construction phase. - `Long EfSearch` The number of edges to use during the search phase. - `Long M` The number of bi-directional links created for each new element. - `VectorType VectorType` The type of vector to use. - `"bit"Bit` - `"half_vec"HalfVec` - `"sparse_vec"SparseVec` - `"vector"Vector` - `Boolean? HybridSearch` - `Boolean PerformSetup` - `Boolean SupportsNestedMetadataFilters` - `class CloudQdrantVectorStore:` Cloud Qdrant Vector Store. This class is used to store the configuration for a Qdrant vector store, so that it can be created and used in LlamaCloud. Args: collection_name (str): name of the Qdrant collection url (str): url of the Qdrant instance api_key (str): API key for authenticating with Qdrant max_retries (int): maximum number of retries in case of a failure. Defaults to 3 client_kwargs (dict): additional kwargs to pass to the Qdrant client - `required string ApiKey` - `required string CollectionName` - `required string Url` - `string ClassName` - `IReadOnlyDictionary ClientKwargs` - `Long MaxRetries` - `SupportsNestedMetadataFilters SupportsNestedMetadataFilters` - `trueTrue` - `class CloudAzureAISearchVectorStore:` Cloud Azure AI Search Vector Store. - `required string SearchServiceApiKey` - `required string SearchServiceEndpoint` - `string ClassName` - `string? ClientID` - `string? ClientSecret` - `Long? EmbeddingDimension` - `IReadOnlyDictionary? FilterableMetadataFieldKeys` - `string? IndexName` - `string? SearchServiceApiVersion` - `SupportsNestedMetadataFilters SupportsNestedMetadataFilters` - `trueTrue` - `string? TenantID` - `class CloudMongoDBAtlasVectorSearch:` Cloud MongoDB Atlas Vector Store. This class is used to store the configuration for a MongoDB Atlas vector store, so that it can be created and used in LlamaCloud. Args: mongodb_uri (str): URI for connecting to MongoDB Atlas db_name (str): name of the MongoDB database collection_name (str): name of the MongoDB collection vector_index_name (str): name of the MongoDB Atlas vector index fulltext_index_name (str): name of the MongoDB Atlas full-text index - `required string CollectionName` - `required string DBName` - `required string MongoDBUri` - `string ClassName` - `Long? EmbeddingDimension` - `string? FulltextIndexName` - `Boolean SupportsNestedMetadataFilters` - `string? VectorIndexName` - `class CloudMilvusVectorStore:` Cloud Milvus Vector Store. - `required string Uri` - `string? Token` - `string ClassName` - `string? CollectionName` - `Long? EmbeddingDimension` - `Boolean SupportsNestedMetadataFilters` - `class CloudAstraDBVectorStore:` Cloud AstraDB Vector Store. This class is used to store the configuration for an AstraDB vector store, so that it can be created and used in LlamaCloud. Args: token (str): The Astra DB Application Token to use. api_endpoint (str): The Astra DB JSON API endpoint for your database. collection_name (str): Collection name to use. If not existing, it will be created. embedding_dimension (int): Length of the embedding vectors in use. keyspace (optional[str]): The keyspace to use. If not provided, 'default_keyspace' - `required string Token` The Astra DB Application Token to use - `required string ApiEndpoint` The Astra DB JSON API endpoint for your database - `required string CollectionName` Collection name to use. If not existing, it will be created - `required Long EmbeddingDimension` Length of the embedding vectors in use - `string ClassName` - `string? Keyspace` The keyspace to use. If not provided, 'default_keyspace' - `SupportsNestedMetadataFilters SupportsNestedMetadataFilters` - `trueTrue` - `required string Name` The name of the data sink. - `required SinkType SinkType` - `"ASTRA_DB"AstraDB` - `"AZUREAI_SEARCH"AzureaiSearch` - `"MILVUS"Milvus` - `"MONGODB_ATLAS"MongoDBAtlas` - `"PINECONE"Pinecone` - `"POSTGRES"Postgres` - `"QDRANT"Qdrant` ### Gemini Embedding - `class GeminiEmbedding:` - `string? ApiBase` API base to access the model. Defaults to None. - `string? ApiKey` API key to access the model. Defaults to None. - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `string ModelName` The modelId of the Gemini model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Long? OutputDimensionality` Optional reduced dimension for output embeddings. Supported by models/text-embedding-004 and newer (e.g. gemini-embedding-001). Not supported by models/embedding-001. - `string? TaskType` The task for embedding model. - `string? Title` Title is only applicable for retrieval_document tasks, and is used to represent a document title. For other tasks, title is invalid. - `string? Transport` Transport to access the model. Defaults to None. ### Gemini Embedding Config - `class GeminiEmbeddingConfig:` - `GeminiEmbedding Component` Configuration for the Gemini embedding model. - `string? ApiBase` API base to access the model. Defaults to None. - `string? ApiKey` API key to access the model. Defaults to None. - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `string ModelName` The modelId of the Gemini model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Long? OutputDimensionality` Optional reduced dimension for output embeddings. Supported by models/text-embedding-004 and newer (e.g. gemini-embedding-001). Not supported by models/embedding-001. - `string? TaskType` The task for embedding model. - `string? Title` Title is only applicable for retrieval_document tasks, and is used to represent a document title. For other tasks, title is invalid. - `string? Transport` Transport to access the model. Defaults to None. - `Type Type` Type of the embedding model. - `"GEMINI_EMBEDDING"GeminiEmbedding` ### Hugging Face Inference API Embedding - `class HuggingFaceInferenceApiEmbedding:` - `Token? Token` Hugging Face token. Will default to the locally saved token. Pass token=False if you don’t want to send your token to the server. - `string` - `Boolean` - `string ClassName` - `IReadOnlyDictionary? Cookies` Additional cookies to send to the server. - `Long EmbedBatchSize` The batch size for embedding calls. - `IReadOnlyDictionary? Headers` Additional headers to send to the server. By default only the authorization and user-agent headers are sent. Values in this dictionary will override the default values. - `string? ModelName` Hugging Face model name. If None, the task will be used. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Pooling? Pooling` Enum of possible pooling choices with pooling behaviors. - `"cls"Cls` - `"last"Last` - `"mean"Mean` - `string? QueryInstruction` Instruction to prepend during query embedding. - `string? Task` Optional task to pick Hugging Face's recommended model, used when model_name is left as default of None. - `string? TextInstruction` Instruction to prepend during text embedding. - `Double? Timeout` The maximum number of seconds to wait for a response from the server. Loading a new model in Inference API can take up to several minutes. Defaults to None, meaning it will loop until the server is available. ### Hugging Face Inference API Embedding Config - `class HuggingFaceInferenceApiEmbeddingConfig:` - `HuggingFaceInferenceApiEmbedding Component` Configuration for the HuggingFace Inference API embedding model. - `Token? Token` Hugging Face token. Will default to the locally saved token. Pass token=False if you don’t want to send your token to the server. - `string` - `Boolean` - `string ClassName` - `IReadOnlyDictionary? Cookies` Additional cookies to send to the server. - `Long EmbedBatchSize` The batch size for embedding calls. - `IReadOnlyDictionary? Headers` Additional headers to send to the server. By default only the authorization and user-agent headers are sent. Values in this dictionary will override the default values. - `string? ModelName` Hugging Face model name. If None, the task will be used. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Pooling? Pooling` Enum of possible pooling choices with pooling behaviors. - `"cls"Cls` - `"last"Last` - `"mean"Mean` - `string? QueryInstruction` Instruction to prepend during query embedding. - `string? Task` Optional task to pick Hugging Face's recommended model, used when model_name is left as default of None. - `string? TextInstruction` Instruction to prepend during text embedding. - `Double? Timeout` The maximum number of seconds to wait for a response from the server. Loading a new model in Inference API can take up to several minutes. Defaults to None, meaning it will loop until the server is available. - `Type Type` Type of the embedding model. - `"HUGGINGFACE_API_EMBEDDING"HuggingfaceApiEmbedding` ### Llama Parse Parameters - `class LlamaParseParameters:` - `Boolean? AdaptiveLongTable` - `Boolean? AggressiveTableExtraction` - `Boolean? AnnotateLinks` - `Boolean? AutoMode` - `string? AutoModeConfigurationJson` - `Boolean? AutoModeTriggerOnImageInPage` - `string? AutoModeTriggerOnRegexpInPage` - `Boolean? AutoModeTriggerOnTableInPage` - `string? AutoModeTriggerOnTextInPage` - `string? AzureOpenAIApiVersion` - `string? AzureOpenAIDeploymentName` - `string? AzureOpenAIEndpoint` - `string? AzureOpenAIKey` - `Double? BboxBottom` - `Double? BboxLeft` - `Double? BboxRight` - `Double? BboxTop` - `string? BoundingBox` - `Boolean? CompactMarkdownTable` - `string? ComplementalFormattingInstruction` - `string? ConfidenceScoreEffort` - `string? ContentGuidelineInstruction` - `Boolean? ContinuousMode` - `Boolean? DisableImageExtraction` - `Boolean? DisableOcr` - `Boolean? DisableReconstruction` - `Boolean? DoNotCache` - `Boolean? DoNotUnrollColumns` - `Boolean? EnableCostOptimizer` - `Boolean? ExtractCharts` - `Boolean? ExtractLayout` - `Boolean? ExtractPrintedPageNumber` - `Boolean? FastMode` - `string? FormattingInstruction` - `string? Gpt4oApiKey` - `Boolean? Gpt4oMode` - `Boolean? GuessXlsxSheetName` - `Boolean? HideFooters` - `Boolean? HideHeaders` - `Boolean? HighResOcr` - `Boolean? HtmlMakeAllElementsVisible` - `Boolean? HtmlRemoveFixedElements` - `Boolean? HtmlRemoveNavigationElements` - `string? HttpProxy` - `Boolean? IgnoreDocumentElementsForLayoutDetection` - `IReadOnlyList? ImagesToSave` - `"embedded"Embedded` - `"layout"Layout` - `"screenshot"Screenshot` - `Boolean? InlineImagesInMarkdown` - `string? InputS3Path` - `string? InputS3Region` - `string? InputUrl` - `Boolean? InternalIsScreenshotJob` - `Boolean? InvalidateCache` - `Boolean? IsFormattingInstruction` - `Double? JobTimeoutExtraTimePerPageInSeconds` - `Double? JobTimeoutInSeconds` - `Boolean? KeepPageSeparatorWhenMergingTables` - `IReadOnlyList Languages` - `"abq"Abq` - `"ady"Ady` - `"af"Af` - `"ang"Ang` - `"ar"Ar` - `"as"As` - `"ava"Ava` - `"az"Az` - `"be"Be` - `"bg"Bg` - `"bgc"Bgc` - `"bh"Bh` - `"bho"Bho` - `"bn"Bn` - `"bs"Bs` - `"ch_sim"ChSim` - `"ch_tra"ChTra` - `"che"Che` - `"cs"Cs` - `"cy"Cy` - `"da"Da` - `"dar"Dar` - `"de"De` - `"en"En` - `"es"Es` - `"et"Et` - `"fa"Fa` - `"fr"Fr` - `"ga"Ga` - `"gom"Gom` - `"hi"Hi` - `"hr"Hr` - `"hu"Hu` - `"id"ID` - `"inh"Inh` - `"is"Is` - `"it"It` - `"ja"Ja` - `"kbd"Kbd` - `"kn"Kn` - `"ko"Ko` - `"ku"Ku` - `"la"La` - `"lbe"Lbe` - `"lez"Lez` - `"lt"Lt` - `"lv"Lv` - `"mah"Mah` - `"mai"Mai` - `"mi"Mi` - `"mn"Mn` - `"mni"Mni` - `"mr"Mr` - `"ms"Ms` - `"mt"Mt` - `"ne"Ne` - `"new"New` - `"nl"Nl` - `"no"No` - `"oc"Oc` - `"pi"Pi` - `"pl"Pl` - `"pt"Pt` - `"ro"Ro` - `"rs_cyrillic"RsCyrillic` - `"rs_latin"RsLatin` - `"ru"Ru` - `"sa"Sa` - `"sck"Sck` - `"sk"Sk` - `"sl"Sl` - `"sq"Sq` - `"sv"Sv` - `"sw"Sw` - `"ta"Ta` - `"tab"Tab` - `"te"Te` - `"th"Th` - `"tjk"Tjk` - `"tl"Tl` - `"tr"Tr` - `"ug"Ug` - `"uk"Uk` - `"ur"Ur` - `"uz"Uz` - `"vi"Vi` - `Boolean? LayoutAware` - `Boolean? LineLevelBoundingBox` - `string? MarkdownTableMultilineHeaderSeparator` - `Long? MaxPages` - `Long? MaxPagesEnforced` - `Boolean? MergeTablesAcrossPagesInMarkdown` - `string? Model` - `Boolean? OutlinedTableExtraction` - `Boolean? OutputPdfOfDocument` - `string? OutputS3PathPrefix` - `string? OutputS3Region` - `Boolean? OutputTablesAsHtml` - `Double? PageErrorTolerance` - `string? PageFooterPrefix` - `string? PageFooterSuffix` - `string? PageHeaderPrefix` - `string? PageHeaderSuffix` - `string? PagePrefix` - `string? PageSeparator` - `string? PageSuffix` - `ParsingMode? ParseMode` Enum for representing the mode of parsing to be used. - `"parse_document_with_agent"ParseDocumentWithAgent` - `"parse_document_with_llm"ParseDocumentWithLlm` - `"parse_document_with_lvm"ParseDocumentWithLvm` - `"parse_page_with_agent"ParsePageWithAgent` - `"parse_page_with_layout_agent"ParsePageWithLayoutAgent` - `"parse_page_with_llm"ParsePageWithLlm` - `"parse_page_with_lvm"ParsePageWithLvm` - `"parse_page_without_llm"ParsePageWithoutLlm` - `string? ParsingInstruction` - `Boolean? PreciseBoundingBox` - `Boolean? PremiumMode` - `Boolean? PresentationOutOfBoundsContent` - `Boolean? PresentationSkipEmbeddedData` - `Boolean? PreserveLayoutAlignmentAcrossPages` - `Boolean? PreserveVerySmallText` - `string? Preset` - `Priority? Priority` The priority for the request. This field may be ignored or overwritten depending on the organization tier. - `"critical"Critical` - `"high"High` - `"low"Low` - `"medium"Medium` - `string? ProjectID` - `Boolean? RemoveHiddenText` - `FailPageMode? ReplaceFailedPageMode` Enum for representing the different available page error handling modes. - `"blank_page"BlankPage` - `"error_message"ErrorMessage` - `"raw_text"RawText` - `string? ReplaceFailedPageWithErrorMessagePrefix` - `string? ReplaceFailedPageWithErrorMessageSuffix` - `Boolean? SaveImages` - `Boolean? SkipDiagonalText` - `Boolean? SpecializedChartParsingAgentic` - `Boolean? SpecializedChartParsingEfficient` - `Boolean? SpecializedChartParsingPlus` - `Boolean? SpecializedImageParsing` - `Boolean? SpreadsheetExtractSubTables` - `Boolean? SpreadsheetForceFormulaComputation` - `Boolean? SpreadsheetIncludeHiddenSheets` - `Boolean? StrictModeBuggyFont` - `Boolean? StrictModeImageExtraction` - `Boolean? StrictModeImageOcr` - `Boolean? StrictModeReconstruction` - `Boolean? StructuredOutput` - `string? StructuredOutputJsonSchema` - `string? StructuredOutputJsonSchemaName` - `string? SystemPrompt` - `string? SystemPromptAppend` - `Boolean? TakeScreenshot` - `string? TargetPages` - `string? Tier` - `Boolean? UseVendorMultimodalModel` - `string? UserPrompt` - `string? VendorMultimodalApiKey` - `string? VendorMultimodalModelName` - `string? Version` - `IReadOnlyList? WebhookConfigurations` Outbound webhook endpoints to notify on job status changes - `IReadOnlyList? WebhookEvents` Events to subscribe to (e.g. 'parse.success', 'extract.error'). If null, all events are delivered. - `"classify.cancelled"ClassifyCancelled` - `"classify.error"ClassifyError` - `"classify.partial_success"ClassifyPartialSuccess` - `"classify.pending"ClassifyPending` - `"classify.running"ClassifyRunning` - `"classify.success"ClassifySuccess` - `"extract.cancelled"ExtractCancelled` - `"extract.error"ExtractError` - `"extract.partial_success"ExtractPartialSuccess` - `"extract.pending"ExtractPending` - `"extract.success"ExtractSuccess` - `"parse.cancelled"ParseCancelled` - `"parse.error"ParseError` - `"parse.partial_success"ParsePartialSuccess` - `"parse.pending"ParsePending` - `"parse.running"ParseRunning` - `"parse.success"ParseSuccess` - `"sheets.cancelled"SheetsCancelled` - `"sheets.error"SheetsError` - `"sheets.partial_success"SheetsPartialSuccess` - `"sheets.pending"SheetsPending` - `"sheets.success"SheetsSuccess` - `"split.cancelled"SplitCancelled` - `"split.error"SplitError` - `"split.pending"SplitPending` - `"split.processing"SplitProcessing` - `"split.success"SplitSuccess` - `"unmapped_event"UnmappedEvent` - `IReadOnlyDictionary? WebhookHeaders` Custom HTTP headers sent with each webhook request (e.g. auth tokens) - `string? WebhookOutputFormat` Response format sent to the webhook: 'string' (default) or 'json' - `string? WebhookSigningSecret` Shared signing secret used to sign webhook deliveries. When set, each request includes an HMAC-SHA256 signature of the request body in the 'LC-Signature' header (value 'sha256='). Recompute the HMAC over the raw request body with this secret to verify the delivery is authentic. - `string? WebhookUrl` URL to receive webhook POST notifications - `string? WebhookUrl` ### Llm Parameters - `class LlmParameters:` - `string ClassName` - `ModelName ModelName` The name of the model to use for LLM completions. - `"AZURE_OPENAI_GPT_4O"AzureOpenAIGpt4O` - `"AZURE_OPENAI_GPT_4O_MINI"AzureOpenAIGpt4OMini` - `"AZURE_OPENAI_GPT_4_1"AzureOpenAIGpt4_1` - `"AZURE_OPENAI_GPT_4_1_MINI"AzureOpenAIGpt4_1Mini` - `"AZURE_OPENAI_GPT_4_1_NANO"AzureOpenAIGpt4_1Nano` - `"BEDROCK_CLAUDE_3_5_SONNET_V1"BedrockClaude3_5SonnetV1` - `"BEDROCK_CLAUDE_3_5_SONNET_V2"BedrockClaude3_5SonnetV2` - `"CLAUDE_4_5_SONNET"Claude4_5Sonnet` - `"GPT_4O"Gpt4O` - `"GPT_4O_MINI"Gpt4OMini` - `"GPT_4_1"Gpt4_1` - `"GPT_4_1_MINI"Gpt4_1Mini` - `"GPT_4_1_NANO"Gpt4_1Nano` - `string? SystemPrompt` The system prompt to use for the completion. - `Double? Temperature` The temperature value for the model. - `Boolean? UseChainOfThoughtReasoning` Whether to use chain of thought reasoning. - `Boolean? UseCitation` Whether to show citations in the response. ### Managed Ingestion Status Response - `class ManagedIngestionStatusResponse:` - `required Status Status` Status of the ingestion. - `"CANCELLED"Cancelled` - `"ERROR"Error` - `"IN_PROGRESS"InProgress` - `"NOT_STARTED"NotStarted` - `"PARTIAL_SUCCESS"PartialSuccess` - `"SUCCESS"Success` - `DateTimeOffset? DeploymentDate` Date of the deployment. - `DateTimeOffset? EffectiveAt` When the status is effective - `IReadOnlyList? Error` List of errors that occurred during ingestion. - `required string JobID` ID of the job that failed. - `required string Message` List of errors that occurred during ingestion. - `required Step Step` Name of the job that failed. - `"DATA_SOURCE"DataSource` - `"FILE_UPDATER"FileUpdater` - `"INGESTION"Ingestion` - `"MANAGED_INGESTION"ManagedIngestion` - `"METADATA_UPDATE"MetadataUpdate` - `"PARSE"Parse` - `"TRANSFORM"Transform` - `string? JobID` ID of the latest job. ### Message Role - `enum MessageRole:` Message role. - `"assistant"Assistant` - `"chatbot"Chatbot` - `"developer"Developer` - `"function"Function` - `"model"Model` - `"system"System` - `"tool"Tool` - `"user"User` ### Metadata Filters - `class MetadataFilters:` Metadata filters for vector stores. - `required IReadOnlyList Filters` - `class MetadataFilter:` Comprehensive metadata filter for vector stores to support more operators. Value uses Strict types, as int, float and str are compatible types and were all converted to string before. See: https://docs.pydantic.dev/latest/usage/types/#strict-types - `required string Key` - `required Value? Value` - `Double` - `string` - `IReadOnlyList` - `IReadOnlyList` - `IReadOnlyList` - `Operator Operator` Vector store filter operator. - `"!="` - `"<"` - `"<="` - `"=="` - `">"` - `">="` - `"all"All` - `"any"Any` - `"contains"Contains` - `"in"In` - `"is_empty"IsEmpty` - `"nin"Nin` - `"text_match"TextMatch` - `"text_match_insensitive"TextMatchInsensitive` - `class MetadataFilters:` Metadata filters for vector stores. - `Condition? Condition` Vector store filter conditions to combine different filters. - `"and"And` - `"not"Not` - `"or"Or` ### OpenAI Embedding - `class OpenAIEmbedding:` - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the OpenAI API. - `string? ApiBase` The base URL for OpenAI API. - `string? ApiKey` The OpenAI API key. - `string? ApiVersion` The version for OpenAI API. - `string ClassName` - `IReadOnlyDictionary? DefaultHeaders` The default headers for API requests. - `Long? Dimensions` The number of dimensions on the output embedding vectors. Works only with v3 embedding models. - `Long EmbedBatchSize` The batch size for embedding calls. - `Long MaxRetries` Maximum number of retries. - `string ModelName` The name of the OpenAI embedding model. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Boolean ReuseClient` Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability. - `Double Timeout` Timeout for each request. ### OpenAI Embedding Config - `class OpenAIEmbeddingConfig:` - `OpenAIEmbedding Component` Configuration for the OpenAI embedding model. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the OpenAI API. - `string? ApiBase` The base URL for OpenAI API. - `string? ApiKey` The OpenAI API key. - `string? ApiVersion` The version for OpenAI API. - `string ClassName` - `IReadOnlyDictionary? DefaultHeaders` The default headers for API requests. - `Long? Dimensions` The number of dimensions on the output embedding vectors. Works only with v3 embedding models. - `Long EmbedBatchSize` The batch size for embedding calls. - `Long MaxRetries` Maximum number of retries. - `string ModelName` The name of the OpenAI embedding model. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Boolean ReuseClient` Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability. - `Double Timeout` Timeout for each request. - `Type Type` Type of the embedding model. - `"OPENAI_EMBEDDING"OpenAIEmbedding` ### Page Figure Node With Score - `class PageFigureNodeWithScore:` Page figure metadata with score - `required Node Node` - `required Double Confidence` The confidence of the figure - `required string FigureName` The name of the figure - `required Long FigureSize` The size of the figure in bytes - `required string FileID` The ID of the file that the figure was taken from - `required Long PageIndex` The index of the page for which the figure is taken (0-indexed) - `Boolean IsLikelyNoise` Whether the figure is likely to be noise - `IReadOnlyDictionary? Metadata` Metadata for the figure - `required Double Score` The score of the figure node - `string ClassName` ### Page Screenshot Node With Score - `class PageScreenshotNodeWithScore:` Page screenshot metadata with score - `required Node Node` - `required string FileID` The ID of the file that the page screenshot was taken from - `required Long ImageSize` The size of the image in bytes - `required Long PageIndex` The index of the page for which the screenshot is taken (0-indexed) - `IReadOnlyDictionary? Metadata` Metadata for the screenshot - `required Double Score` The score of the screenshot node - `string ClassName` ### Pipeline - `class Pipeline:` Schema for a pipeline. - `required string ID` Unique identifier - `required EmbeddingConfig EmbeddingConfig` - `class AzureOpenAIEmbeddingConfig:` - `AzureOpenAIEmbedding Component` Configuration for the Azure OpenAI embedding model. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the OpenAI API. - `string ApiBase` The base URL for Azure deployment. - `string? ApiKey` The OpenAI API key. - `string ApiVersion` The version for Azure OpenAI API. - `string? AzureDeployment` The Azure deployment to use. - `string? AzureEndpoint` The Azure endpoint to use. - `string ClassName` - `IReadOnlyDictionary? DefaultHeaders` The default headers for API requests. - `Long? Dimensions` The number of dimensions on the output embedding vectors. Works only with v3 embedding models. - `Long EmbedBatchSize` The batch size for embedding calls. - `Long MaxRetries` Maximum number of retries. - `string ModelName` The name of the OpenAI embedding model. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Boolean ReuseClient` Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability. - `Double Timeout` Timeout for each request. - `Type Type` Type of the embedding model. - `"AZURE_EMBEDDING"AzureEmbedding` - `class BedrockEmbeddingConfig:` - `BedrockEmbedding Component` Configuration for the Bedrock embedding model. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the bedrock client. - `string? AwsAccessKeyID` AWS Access Key ID to use - `string? AwsSecretAccessKey` AWS Secret Access Key to use - `string? AwsSessionToken` AWS Session Token to use - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `Long MaxRetries` The maximum number of API retries. - `string ModelName` The modelId of the Bedrock model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `string? ProfileName` The name of aws profile to use. If not given, then the default profile is used. - `string? RegionName` AWS region name to use. Uses region configured in AWS CLI if not passed - `Double Timeout` The timeout for the Bedrock API request in seconds. It will be used for both connect and read timeouts. - `Type Type` Type of the embedding model. - `"BEDROCK_EMBEDDING"BedrockEmbedding` - `class CohereEmbeddingConfig:` - `CohereEmbedding Component` Configuration for the Cohere embedding model. - `required string? ApiKey` The Cohere API key. - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `string EmbeddingType` Embedding type. If not provided float embedding_type is used when needed. - `string? InputType` Model Input type. If not provided, search_document and search_query are used when needed. - `string ModelName` The modelId of the Cohere model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `string Truncate` Truncation type - START/ END/ NONE - `Type Type` Type of the embedding model. - `"COHERE_EMBEDDING"CohereEmbedding` - `class GeminiEmbeddingConfig:` - `GeminiEmbedding Component` Configuration for the Gemini embedding model. - `string? ApiBase` API base to access the model. Defaults to None. - `string? ApiKey` API key to access the model. Defaults to None. - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `string ModelName` The modelId of the Gemini model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Long? OutputDimensionality` Optional reduced dimension for output embeddings. Supported by models/text-embedding-004 and newer (e.g. gemini-embedding-001). Not supported by models/embedding-001. - `string? TaskType` The task for embedding model. - `string? Title` Title is only applicable for retrieval_document tasks, and is used to represent a document title. For other tasks, title is invalid. - `string? Transport` Transport to access the model. Defaults to None. - `Type Type` Type of the embedding model. - `"GEMINI_EMBEDDING"GeminiEmbedding` - `class HuggingFaceInferenceApiEmbeddingConfig:` - `HuggingFaceInferenceApiEmbedding Component` Configuration for the HuggingFace Inference API embedding model. - `Token? Token` Hugging Face token. Will default to the locally saved token. Pass token=False if you don’t want to send your token to the server. - `string` - `Boolean` - `string ClassName` - `IReadOnlyDictionary? Cookies` Additional cookies to send to the server. - `Long EmbedBatchSize` The batch size for embedding calls. - `IReadOnlyDictionary? Headers` Additional headers to send to the server. By default only the authorization and user-agent headers are sent. Values in this dictionary will override the default values. - `string? ModelName` Hugging Face model name. If None, the task will be used. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Pooling? Pooling` Enum of possible pooling choices with pooling behaviors. - `"cls"Cls` - `"last"Last` - `"mean"Mean` - `string? QueryInstruction` Instruction to prepend during query embedding. - `string? Task` Optional task to pick Hugging Face's recommended model, used when model_name is left as default of None. - `string? TextInstruction` Instruction to prepend during text embedding. - `Double? Timeout` The maximum number of seconds to wait for a response from the server. Loading a new model in Inference API can take up to several minutes. Defaults to None, meaning it will loop until the server is available. - `Type Type` Type of the embedding model. - `"HUGGINGFACE_API_EMBEDDING"HuggingfaceApiEmbedding` - `class ManagedOpenAIEmbedding:` - `Component Component` Configuration for the Managed OpenAI embedding model. - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `ModelName ModelName` The name of the OpenAI embedding model. - `"openai-text-embedding-3-small"OpenAITextEmbedding3Small` - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Type Type` Type of the embedding model. - `"MANAGED_OPENAI_EMBEDDING"ManagedOpenAIEmbedding` - `class OpenAIEmbeddingConfig:` - `OpenAIEmbedding Component` Configuration for the OpenAI embedding model. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the OpenAI API. - `string? ApiBase` The base URL for OpenAI API. - `string? ApiKey` The OpenAI API key. - `string? ApiVersion` The version for OpenAI API. - `string ClassName` - `IReadOnlyDictionary? DefaultHeaders` The default headers for API requests. - `Long? Dimensions` The number of dimensions on the output embedding vectors. Works only with v3 embedding models. - `Long EmbedBatchSize` The batch size for embedding calls. - `Long MaxRetries` Maximum number of retries. - `string ModelName` The name of the OpenAI embedding model. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Boolean ReuseClient` Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability. - `Double Timeout` Timeout for each request. - `Type Type` Type of the embedding model. - `"OPENAI_EMBEDDING"OpenAIEmbedding` - `class VertexAIEmbeddingConfig:` - `VertexTextEmbedding Component` Configuration for the VertexAI embedding model. - `required string? ClientEmail` The client email for the VertexAI credentials. - `required string Location` The default location to use when making API calls. - `required string? PrivateKey` The private key for the VertexAI credentials. - `required string? PrivateKeyID` The private key ID for the VertexAI credentials. - `required string Project` The default GCP project to use when making Vertex API calls. - `required string? TokenUri` The token URI for the VertexAI credentials. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the Vertex. - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `EmbedMode EmbedMode` The embedding mode to use. - `"classification"Classification` - `"clustering"Clustering` - `"default"Default` - `"retrieval"Retrieval` - `"similarity"Similarity` - `string ModelName` The modelId of the VertexAI model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Type Type` Type of the embedding model. - `"VERTEXAI_EMBEDDING"VertexaiEmbedding` - `required string Name` - `required string ProjectID` - `ConfigHash? ConfigHash` Hashes for the configuration of a pipeline. - `string? EmbeddingConfigHash` Hash of the embedding config. - `string? ParsingConfigHash` Hash of the llama parse parameters. - `string? TransformConfigHash` Hash of the transform config. - `DateTimeOffset? CreatedAt` Creation datetime - `DataSink? DataSink` Schema for a data sink. - `required string ID` Unique identifier - `required Component Component` Component that implements the data sink - `IReadOnlyDictionary` - `class CloudPineconeVectorStore:` Cloud Pinecone Vector Store. This class is used to store the configuration for a Pinecone vector store, so that it can be created and used in LlamaCloud. Args: api_key (str): API key for authenticating with Pinecone index_name (str): name of the Pinecone index namespace (optional[str]): namespace to use in the Pinecone index insert_kwargs (optional[dict]): additional kwargs to pass during insertion - `required string ApiKey` The API key for authenticating with Pinecone - `required string IndexName` - `string ClassName` - `IReadOnlyDictionary? InsertKwargs` - `string? Namespace` - `SupportsNestedMetadataFilters SupportsNestedMetadataFilters` - `trueTrue` - `class CloudPostgresVectorStore:` - `required string Database` - `required Long EmbedDim` - `required string Host` - `required string Password` - `required Long Port` - `required string SchemaName` - `required string TableName` - `required string User` - `string ClassName` - `PgVectorHnswSettings? HnswSettings` HNSW settings for PGVector. - `DistanceMethod DistanceMethod` The distance method to use. - `"cosine"Cosine` - `"hamming"Hamming` - `"ip"IP` - `"jaccard"Jaccard` - `"l1"L1` - `"l2"L2` - `Long EfConstruction` The number of edges to use during the construction phase. - `Long EfSearch` The number of edges to use during the search phase. - `Long M` The number of bi-directional links created for each new element. - `VectorType VectorType` The type of vector to use. - `"bit"Bit` - `"half_vec"HalfVec` - `"sparse_vec"SparseVec` - `"vector"Vector` - `Boolean? HybridSearch` - `Boolean PerformSetup` - `Boolean SupportsNestedMetadataFilters` - `class CloudQdrantVectorStore:` Cloud Qdrant Vector Store. This class is used to store the configuration for a Qdrant vector store, so that it can be created and used in LlamaCloud. Args: collection_name (str): name of the Qdrant collection url (str): url of the Qdrant instance api_key (str): API key for authenticating with Qdrant max_retries (int): maximum number of retries in case of a failure. Defaults to 3 client_kwargs (dict): additional kwargs to pass to the Qdrant client - `required string ApiKey` - `required string CollectionName` - `required string Url` - `string ClassName` - `IReadOnlyDictionary ClientKwargs` - `Long MaxRetries` - `SupportsNestedMetadataFilters SupportsNestedMetadataFilters` - `trueTrue` - `class CloudAzureAISearchVectorStore:` Cloud Azure AI Search Vector Store. - `required string SearchServiceApiKey` - `required string SearchServiceEndpoint` - `string ClassName` - `string? ClientID` - `string? ClientSecret` - `Long? EmbeddingDimension` - `IReadOnlyDictionary? FilterableMetadataFieldKeys` - `string? IndexName` - `string? SearchServiceApiVersion` - `SupportsNestedMetadataFilters SupportsNestedMetadataFilters` - `trueTrue` - `string? TenantID` - `class CloudMongoDBAtlasVectorSearch:` Cloud MongoDB Atlas Vector Store. This class is used to store the configuration for a MongoDB Atlas vector store, so that it can be created and used in LlamaCloud. Args: mongodb_uri (str): URI for connecting to MongoDB Atlas db_name (str): name of the MongoDB database collection_name (str): name of the MongoDB collection vector_index_name (str): name of the MongoDB Atlas vector index fulltext_index_name (str): name of the MongoDB Atlas full-text index - `required string CollectionName` - `required string DBName` - `required string MongoDBUri` - `string ClassName` - `Long? EmbeddingDimension` - `string? FulltextIndexName` - `Boolean SupportsNestedMetadataFilters` - `string? VectorIndexName` - `class CloudMilvusVectorStore:` Cloud Milvus Vector Store. - `required string Uri` - `string? Token` - `string ClassName` - `string? CollectionName` - `Long? EmbeddingDimension` - `Boolean SupportsNestedMetadataFilters` - `class CloudAstraDBVectorStore:` Cloud AstraDB Vector Store. This class is used to store the configuration for an AstraDB vector store, so that it can be created and used in LlamaCloud. Args: token (str): The Astra DB Application Token to use. api_endpoint (str): The Astra DB JSON API endpoint for your database. collection_name (str): Collection name to use. If not existing, it will be created. embedding_dimension (int): Length of the embedding vectors in use. keyspace (optional[str]): The keyspace to use. If not provided, 'default_keyspace' - `required string Token` The Astra DB Application Token to use - `required string ApiEndpoint` The Astra DB JSON API endpoint for your database - `required string CollectionName` Collection name to use. If not existing, it will be created - `required Long EmbeddingDimension` Length of the embedding vectors in use - `string ClassName` - `string? Keyspace` The keyspace to use. If not provided, 'default_keyspace' - `SupportsNestedMetadataFilters SupportsNestedMetadataFilters` - `trueTrue` - `required string Name` The name of the data sink. - `required string ProjectID` - `required SinkType SinkType` - `"ASTRA_DB"AstraDB` - `"AZUREAI_SEARCH"AzureaiSearch` - `"MILVUS"Milvus` - `"MONGODB_ATLAS"MongoDBAtlas` - `"PINECONE"Pinecone` - `"POSTGRES"Postgres` - `"QDRANT"Qdrant` - `DateTimeOffset? CreatedAt` Creation datetime - `DateTimeOffset? UpdatedAt` Update datetime - `EmbeddingModelConfig? EmbeddingModelConfig` Schema for an embedding model config. - `required string ID` Unique identifier - `required EmbeddingConfig EmbeddingConfig` The embedding configuration for the embedding model config. - `class AzureOpenAIEmbeddingConfig:` - `class BedrockEmbeddingConfig:` - `class CohereEmbeddingConfig:` - `class GeminiEmbeddingConfig:` - `class HuggingFaceInferenceApiEmbeddingConfig:` - `class OpenAIEmbeddingConfig:` - `class VertexAIEmbeddingConfig:` - `required string Name` The name of the embedding model config. - `required string ProjectID` - `DateTimeOffset? CreatedAt` Creation datetime - `DateTimeOffset? UpdatedAt` Update datetime - `string? EmbeddingModelConfigID` The ID of the EmbeddingModelConfig this pipeline is using. - `LlamaParseParameters? LlamaParseParameters` Settings that can be configured for how to use LlamaParse to parse files within a LlamaCloud pipeline. - `Boolean? AdaptiveLongTable` - `Boolean? AggressiveTableExtraction` - `Boolean? AnnotateLinks` - `Boolean? AutoMode` - `string? AutoModeConfigurationJson` - `Boolean? AutoModeTriggerOnImageInPage` - `string? AutoModeTriggerOnRegexpInPage` - `Boolean? AutoModeTriggerOnTableInPage` - `string? AutoModeTriggerOnTextInPage` - `string? AzureOpenAIApiVersion` - `string? AzureOpenAIDeploymentName` - `string? AzureOpenAIEndpoint` - `string? AzureOpenAIKey` - `Double? BboxBottom` - `Double? BboxLeft` - `Double? BboxRight` - `Double? BboxTop` - `string? BoundingBox` - `Boolean? CompactMarkdownTable` - `string? ComplementalFormattingInstruction` - `string? ConfidenceScoreEffort` - `string? ContentGuidelineInstruction` - `Boolean? ContinuousMode` - `Boolean? DisableImageExtraction` - `Boolean? DisableOcr` - `Boolean? DisableReconstruction` - `Boolean? DoNotCache` - `Boolean? DoNotUnrollColumns` - `Boolean? EnableCostOptimizer` - `Boolean? ExtractCharts` - `Boolean? ExtractLayout` - `Boolean? ExtractPrintedPageNumber` - `Boolean? FastMode` - `string? FormattingInstruction` - `string? Gpt4oApiKey` - `Boolean? Gpt4oMode` - `Boolean? GuessXlsxSheetName` - `Boolean? HideFooters` - `Boolean? HideHeaders` - `Boolean? HighResOcr` - `Boolean? HtmlMakeAllElementsVisible` - `Boolean? HtmlRemoveFixedElements` - `Boolean? HtmlRemoveNavigationElements` - `string? HttpProxy` - `Boolean? IgnoreDocumentElementsForLayoutDetection` - `IReadOnlyList? ImagesToSave` - `"embedded"Embedded` - `"layout"Layout` - `"screenshot"Screenshot` - `Boolean? InlineImagesInMarkdown` - `string? InputS3Path` - `string? InputS3Region` - `string? InputUrl` - `Boolean? InternalIsScreenshotJob` - `Boolean? InvalidateCache` - `Boolean? IsFormattingInstruction` - `Double? JobTimeoutExtraTimePerPageInSeconds` - `Double? JobTimeoutInSeconds` - `Boolean? KeepPageSeparatorWhenMergingTables` - `IReadOnlyList Languages` - `"abq"Abq` - `"ady"Ady` - `"af"Af` - `"ang"Ang` - `"ar"Ar` - `"as"As` - `"ava"Ava` - `"az"Az` - `"be"Be` - `"bg"Bg` - `"bgc"Bgc` - `"bh"Bh` - `"bho"Bho` - `"bn"Bn` - `"bs"Bs` - `"ch_sim"ChSim` - `"ch_tra"ChTra` - `"che"Che` - `"cs"Cs` - `"cy"Cy` - `"da"Da` - `"dar"Dar` - `"de"De` - `"en"En` - `"es"Es` - `"et"Et` - `"fa"Fa` - `"fr"Fr` - `"ga"Ga` - `"gom"Gom` - `"hi"Hi` - `"hr"Hr` - `"hu"Hu` - `"id"ID` - `"inh"Inh` - `"is"Is` - `"it"It` - `"ja"Ja` - `"kbd"Kbd` - `"kn"Kn` - `"ko"Ko` - `"ku"Ku` - `"la"La` - `"lbe"Lbe` - `"lez"Lez` - `"lt"Lt` - `"lv"Lv` - `"mah"Mah` - `"mai"Mai` - `"mi"Mi` - `"mn"Mn` - `"mni"Mni` - `"mr"Mr` - `"ms"Ms` - `"mt"Mt` - `"ne"Ne` - `"new"New` - `"nl"Nl` - `"no"No` - `"oc"Oc` - `"pi"Pi` - `"pl"Pl` - `"pt"Pt` - `"ro"Ro` - `"rs_cyrillic"RsCyrillic` - `"rs_latin"RsLatin` - `"ru"Ru` - `"sa"Sa` - `"sck"Sck` - `"sk"Sk` - `"sl"Sl` - `"sq"Sq` - `"sv"Sv` - `"sw"Sw` - `"ta"Ta` - `"tab"Tab` - `"te"Te` - `"th"Th` - `"tjk"Tjk` - `"tl"Tl` - `"tr"Tr` - `"ug"Ug` - `"uk"Uk` - `"ur"Ur` - `"uz"Uz` - `"vi"Vi` - `Boolean? LayoutAware` - `Boolean? LineLevelBoundingBox` - `string? MarkdownTableMultilineHeaderSeparator` - `Long? MaxPages` - `Long? MaxPagesEnforced` - `Boolean? MergeTablesAcrossPagesInMarkdown` - `string? Model` - `Boolean? OutlinedTableExtraction` - `Boolean? OutputPdfOfDocument` - `string? OutputS3PathPrefix` - `string? OutputS3Region` - `Boolean? OutputTablesAsHtml` - `Double? PageErrorTolerance` - `string? PageFooterPrefix` - `string? PageFooterSuffix` - `string? PageHeaderPrefix` - `string? PageHeaderSuffix` - `string? PagePrefix` - `string? PageSeparator` - `string? PageSuffix` - `ParsingMode? ParseMode` Enum for representing the mode of parsing to be used. - `"parse_document_with_agent"ParseDocumentWithAgent` - `"parse_document_with_llm"ParseDocumentWithLlm` - `"parse_document_with_lvm"ParseDocumentWithLvm` - `"parse_page_with_agent"ParsePageWithAgent` - `"parse_page_with_layout_agent"ParsePageWithLayoutAgent` - `"parse_page_with_llm"ParsePageWithLlm` - `"parse_page_with_lvm"ParsePageWithLvm` - `"parse_page_without_llm"ParsePageWithoutLlm` - `string? ParsingInstruction` - `Boolean? PreciseBoundingBox` - `Boolean? PremiumMode` - `Boolean? PresentationOutOfBoundsContent` - `Boolean? PresentationSkipEmbeddedData` - `Boolean? PreserveLayoutAlignmentAcrossPages` - `Boolean? PreserveVerySmallText` - `string? Preset` - `Priority? Priority` The priority for the request. This field may be ignored or overwritten depending on the organization tier. - `"critical"Critical` - `"high"High` - `"low"Low` - `"medium"Medium` - `string? ProjectID` - `Boolean? RemoveHiddenText` - `FailPageMode? ReplaceFailedPageMode` Enum for representing the different available page error handling modes. - `"blank_page"BlankPage` - `"error_message"ErrorMessage` - `"raw_text"RawText` - `string? ReplaceFailedPageWithErrorMessagePrefix` - `string? ReplaceFailedPageWithErrorMessageSuffix` - `Boolean? SaveImages` - `Boolean? SkipDiagonalText` - `Boolean? SpecializedChartParsingAgentic` - `Boolean? SpecializedChartParsingEfficient` - `Boolean? SpecializedChartParsingPlus` - `Boolean? SpecializedImageParsing` - `Boolean? SpreadsheetExtractSubTables` - `Boolean? SpreadsheetForceFormulaComputation` - `Boolean? SpreadsheetIncludeHiddenSheets` - `Boolean? StrictModeBuggyFont` - `Boolean? StrictModeImageExtraction` - `Boolean? StrictModeImageOcr` - `Boolean? StrictModeReconstruction` - `Boolean? StructuredOutput` - `string? StructuredOutputJsonSchema` - `string? StructuredOutputJsonSchemaName` - `string? SystemPrompt` - `string? SystemPromptAppend` - `Boolean? TakeScreenshot` - `string? TargetPages` - `string? Tier` - `Boolean? UseVendorMultimodalModel` - `string? UserPrompt` - `string? VendorMultimodalApiKey` - `string? VendorMultimodalModelName` - `string? Version` - `IReadOnlyList? WebhookConfigurations` Outbound webhook endpoints to notify on job status changes - `IReadOnlyList? WebhookEvents` Events to subscribe to (e.g. 'parse.success', 'extract.error'). If null, all events are delivered. - `"classify.cancelled"ClassifyCancelled` - `"classify.error"ClassifyError` - `"classify.partial_success"ClassifyPartialSuccess` - `"classify.pending"ClassifyPending` - `"classify.running"ClassifyRunning` - `"classify.success"ClassifySuccess` - `"extract.cancelled"ExtractCancelled` - `"extract.error"ExtractError` - `"extract.partial_success"ExtractPartialSuccess` - `"extract.pending"ExtractPending` - `"extract.success"ExtractSuccess` - `"parse.cancelled"ParseCancelled` - `"parse.error"ParseError` - `"parse.partial_success"ParsePartialSuccess` - `"parse.pending"ParsePending` - `"parse.running"ParseRunning` - `"parse.success"ParseSuccess` - `"sheets.cancelled"SheetsCancelled` - `"sheets.error"SheetsError` - `"sheets.partial_success"SheetsPartialSuccess` - `"sheets.pending"SheetsPending` - `"sheets.success"SheetsSuccess` - `"split.cancelled"SplitCancelled` - `"split.error"SplitError` - `"split.pending"SplitPending` - `"split.processing"SplitProcessing` - `"split.success"SplitSuccess` - `"unmapped_event"UnmappedEvent` - `IReadOnlyDictionary? WebhookHeaders` Custom HTTP headers sent with each webhook request (e.g. auth tokens) - `string? WebhookOutputFormat` Response format sent to the webhook: 'string' (default) or 'json' - `string? WebhookSigningSecret` Shared signing secret used to sign webhook deliveries. When set, each request includes an HMAC-SHA256 signature of the request body in the 'LC-Signature' header (value 'sha256='). Recompute the HMAC over the raw request body with this secret to verify the delivery is authentic. - `string? WebhookUrl` URL to receive webhook POST notifications - `string? WebhookUrl` - `string? ManagedPipelineID` The ID of the ManagedPipeline this playground pipeline is linked to. - `PipelineMetadataConfig? MetadataConfig` Metadata configuration for the pipeline. - `IReadOnlyList ExcludedEmbedMetadataKeys` List of metadata keys to exclude from embeddings - `IReadOnlyList ExcludedLlmMetadataKeys` List of metadata keys to exclude from LLM during retrieval - `PipelineType PipelineType` Type of pipeline. Either PLAYGROUND or MANAGED. - `"MANAGED"Managed` - `"PLAYGROUND"Playground` - `PresetRetrievalParams PresetRetrievalParameters` Preset retrieval parameters for the pipeline. - `Double? Alpha` Alpha value for hybrid retrieval to determine the weights between dense and sparse retrieval. 0 is sparse retrieval and 1 is dense retrieval. - `string ClassName` - `Double? DenseSimilarityCutoff` Minimum similarity score wrt query for retrieval - `Long? DenseSimilarityTopK` Number of nodes for dense retrieval. - `Boolean? EnableReranking` Enable reranking for retrieval - `Long? FilesTopK` Number of files to retrieve (only for retrieval mode files_via_metadata and files_via_content). - `Long? RerankTopN` Number of reranked nodes for returning. - `RetrievalMode RetrievalMode` The retrieval mode for the query. - `"auto_routed"AutoRouted` - `"chunks"Chunks` - `"files_via_content"FilesViaContent` - `"files_via_metadata"FilesViaMetadata` - `Boolean RetrieveImageNodes` Whether to retrieve image nodes. - `Boolean RetrievePageFigureNodes` Whether to retrieve page figure nodes. - `Boolean RetrievePageScreenshotNodes` Whether to retrieve page screenshot nodes. - `MetadataFilters? SearchFilters` Metadata filters for vector stores. - `required IReadOnlyList Filters` - `class MetadataFilter:` Comprehensive metadata filter for vector stores to support more operators. Value uses Strict types, as int, float and str are compatible types and were all converted to string before. See: https://docs.pydantic.dev/latest/usage/types/#strict-types - `required string Key` - `required Value? Value` - `Double` - `string` - `IReadOnlyList` - `IReadOnlyList` - `IReadOnlyList` - `Operator Operator` Vector store filter operator. - `"!="` - `"<"` - `"<="` - `"=="` - `">"` - `">="` - `"all"All` - `"any"Any` - `"contains"Contains` - `"in"In` - `"is_empty"IsEmpty` - `"nin"Nin` - `"text_match"TextMatch` - `"text_match_insensitive"TextMatchInsensitive` - `class MetadataFilters:` Metadata filters for vector stores. - `Condition? Condition` Vector store filter conditions to combine different filters. - `"and"And` - `"not"Not` - `"or"Or` - `IReadOnlyDictionary? SearchFiltersInferenceSchema` JSON Schema that will be used to infer search_filters. Omit or leave as null to skip inference. - `IReadOnlyDictionary` - `IReadOnlyList` - `string` - `Double` - `Boolean` - `Long? SparseSimilarityTopK` Number of nodes for sparse retrieval. - `SparseModelConfig? SparseModelConfig` Configuration for sparse embedding models used in hybrid search. This allows users to choose between Splade and BM25 models for sparse retrieval in managed data sinks. - `string ClassName` - `ModelType ModelType` The sparse model type to use. 'bm25' uses Qdrant's FastEmbed BM25 model (default for new pipelines), 'splade' uses HuggingFace Splade model, 'auto' selects based on deployment mode (BYOC uses term frequency, Cloud uses Splade). - `"auto"Auto` - `"bm25"Bm25` - `"splade"Splade` - `Status? Status` Status of the pipeline. - `"CREATED"Created` - `"DELETING"Deleting` - `TransformConfig TransformConfig` Configuration for the transformation. - `class AutoTransformConfig:` - `Long ChunkOverlap` Chunk overlap for the transformation. - `Long ChunkSize` Chunk size for the transformation. - `Mode Mode` - `"auto"Auto` - `class AdvancedModeTransformConfig:` - `ChunkingConfig ChunkingConfig` Configuration for the chunking. - `class NoneChunkingConfig:` - `Mode Mode` - `"none"None` - `class CharacterChunkingConfig:` - `Long ChunkOverlap` - `Long ChunkSize` - `Mode Mode` - `"character"Character` - `class TokenChunkingConfig:` - `Long ChunkOverlap` - `Long ChunkSize` - `Mode Mode` - `"token"Token` - `string Separator` - `class SentenceChunkingConfig:` - `Long ChunkOverlap` - `Long ChunkSize` - `Mode Mode` - `"sentence"Sentence` - `string ParagraphSeparator` - `string Separator` - `class SemanticChunkingConfig:` - `Long BreakpointPercentileThreshold` - `Long BufferSize` - `Mode Mode` - `"semantic"Semantic` - `Mode Mode` - `"advanced"Advanced` - `SegmentationConfig SegmentationConfig` Configuration for the segmentation. - `class NoneSegmentationConfig:` - `Mode Mode` - `"none"None` - `class PageSegmentationConfig:` - `Mode Mode` - `"page"Page` - `string PageSeparator` - `class ElementSegmentationConfig:` - `Mode Mode` - `"element"Element` - `DateTimeOffset? UpdatedAt` Update datetime ### Pipeline Create - `class PipelineCreate:` Schema for creating a pipeline. - `required string Name` - `DataSinkCreate? DataSink` Schema for creating a data sink. - `required Component Component` Component that implements the data sink - `IReadOnlyDictionary` - `class CloudPineconeVectorStore:` Cloud Pinecone Vector Store. This class is used to store the configuration for a Pinecone vector store, so that it can be created and used in LlamaCloud. Args: api_key (str): API key for authenticating with Pinecone index_name (str): name of the Pinecone index namespace (optional[str]): namespace to use in the Pinecone index insert_kwargs (optional[dict]): additional kwargs to pass during insertion - `required string ApiKey` The API key for authenticating with Pinecone - `required string IndexName` - `string ClassName` - `IReadOnlyDictionary? InsertKwargs` - `string? Namespace` - `SupportsNestedMetadataFilters SupportsNestedMetadataFilters` - `trueTrue` - `class CloudPostgresVectorStore:` - `required string Database` - `required Long EmbedDim` - `required string Host` - `required string Password` - `required Long Port` - `required string SchemaName` - `required string TableName` - `required string User` - `string ClassName` - `PgVectorHnswSettings? HnswSettings` HNSW settings for PGVector. - `DistanceMethod DistanceMethod` The distance method to use. - `"cosine"Cosine` - `"hamming"Hamming` - `"ip"IP` - `"jaccard"Jaccard` - `"l1"L1` - `"l2"L2` - `Long EfConstruction` The number of edges to use during the construction phase. - `Long EfSearch` The number of edges to use during the search phase. - `Long M` The number of bi-directional links created for each new element. - `VectorType VectorType` The type of vector to use. - `"bit"Bit` - `"half_vec"HalfVec` - `"sparse_vec"SparseVec` - `"vector"Vector` - `Boolean? HybridSearch` - `Boolean PerformSetup` - `Boolean SupportsNestedMetadataFilters` - `class CloudQdrantVectorStore:` Cloud Qdrant Vector Store. This class is used to store the configuration for a Qdrant vector store, so that it can be created and used in LlamaCloud. Args: collection_name (str): name of the Qdrant collection url (str): url of the Qdrant instance api_key (str): API key for authenticating with Qdrant max_retries (int): maximum number of retries in case of a failure. Defaults to 3 client_kwargs (dict): additional kwargs to pass to the Qdrant client - `required string ApiKey` - `required string CollectionName` - `required string Url` - `string ClassName` - `IReadOnlyDictionary ClientKwargs` - `Long MaxRetries` - `SupportsNestedMetadataFilters SupportsNestedMetadataFilters` - `trueTrue` - `class CloudAzureAISearchVectorStore:` Cloud Azure AI Search Vector Store. - `required string SearchServiceApiKey` - `required string SearchServiceEndpoint` - `string ClassName` - `string? ClientID` - `string? ClientSecret` - `Long? EmbeddingDimension` - `IReadOnlyDictionary? FilterableMetadataFieldKeys` - `string? IndexName` - `string? SearchServiceApiVersion` - `SupportsNestedMetadataFilters SupportsNestedMetadataFilters` - `trueTrue` - `string? TenantID` - `class CloudMongoDBAtlasVectorSearch:` Cloud MongoDB Atlas Vector Store. This class is used to store the configuration for a MongoDB Atlas vector store, so that it can be created and used in LlamaCloud. Args: mongodb_uri (str): URI for connecting to MongoDB Atlas db_name (str): name of the MongoDB database collection_name (str): name of the MongoDB collection vector_index_name (str): name of the MongoDB Atlas vector index fulltext_index_name (str): name of the MongoDB Atlas full-text index - `required string CollectionName` - `required string DBName` - `required string MongoDBUri` - `string ClassName` - `Long? EmbeddingDimension` - `string? FulltextIndexName` - `Boolean SupportsNestedMetadataFilters` - `string? VectorIndexName` - `class CloudMilvusVectorStore:` Cloud Milvus Vector Store. - `required string Uri` - `string? Token` - `string ClassName` - `string? CollectionName` - `Long? EmbeddingDimension` - `Boolean SupportsNestedMetadataFilters` - `class CloudAstraDBVectorStore:` Cloud AstraDB Vector Store. This class is used to store the configuration for an AstraDB vector store, so that it can be created and used in LlamaCloud. Args: token (str): The Astra DB Application Token to use. api_endpoint (str): The Astra DB JSON API endpoint for your database. collection_name (str): Collection name to use. If not existing, it will be created. embedding_dimension (int): Length of the embedding vectors in use. keyspace (optional[str]): The keyspace to use. If not provided, 'default_keyspace' - `required string Token` The Astra DB Application Token to use - `required string ApiEndpoint` The Astra DB JSON API endpoint for your database - `required string CollectionName` Collection name to use. If not existing, it will be created - `required Long EmbeddingDimension` Length of the embedding vectors in use - `string ClassName` - `string? Keyspace` The keyspace to use. If not provided, 'default_keyspace' - `SupportsNestedMetadataFilters SupportsNestedMetadataFilters` - `trueTrue` - `required string Name` The name of the data sink. - `required SinkType SinkType` - `"ASTRA_DB"AstraDB` - `"AZUREAI_SEARCH"AzureaiSearch` - `"MILVUS"Milvus` - `"MONGODB_ATLAS"MongoDBAtlas` - `"PINECONE"Pinecone` - `"POSTGRES"Postgres` - `"QDRANT"Qdrant` - `string? DataSinkID` Data sink ID. When provided instead of data_sink, the data sink will be looked up by ID. - `EmbeddingConfig? EmbeddingConfig` - `class AzureOpenAIEmbeddingConfig:` - `AzureOpenAIEmbedding Component` Configuration for the Azure OpenAI embedding model. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the OpenAI API. - `string ApiBase` The base URL for Azure deployment. - `string? ApiKey` The OpenAI API key. - `string ApiVersion` The version for Azure OpenAI API. - `string? AzureDeployment` The Azure deployment to use. - `string? AzureEndpoint` The Azure endpoint to use. - `string ClassName` - `IReadOnlyDictionary? DefaultHeaders` The default headers for API requests. - `Long? Dimensions` The number of dimensions on the output embedding vectors. Works only with v3 embedding models. - `Long EmbedBatchSize` The batch size for embedding calls. - `Long MaxRetries` Maximum number of retries. - `string ModelName` The name of the OpenAI embedding model. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Boolean ReuseClient` Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability. - `Double Timeout` Timeout for each request. - `Type Type` Type of the embedding model. - `"AZURE_EMBEDDING"AzureEmbedding` - `class BedrockEmbeddingConfig:` - `BedrockEmbedding Component` Configuration for the Bedrock embedding model. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the bedrock client. - `string? AwsAccessKeyID` AWS Access Key ID to use - `string? AwsSecretAccessKey` AWS Secret Access Key to use - `string? AwsSessionToken` AWS Session Token to use - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `Long MaxRetries` The maximum number of API retries. - `string ModelName` The modelId of the Bedrock model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `string? ProfileName` The name of aws profile to use. If not given, then the default profile is used. - `string? RegionName` AWS region name to use. Uses region configured in AWS CLI if not passed - `Double Timeout` The timeout for the Bedrock API request in seconds. It will be used for both connect and read timeouts. - `Type Type` Type of the embedding model. - `"BEDROCK_EMBEDDING"BedrockEmbedding` - `class CohereEmbeddingConfig:` - `CohereEmbedding Component` Configuration for the Cohere embedding model. - `required string? ApiKey` The Cohere API key. - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `string EmbeddingType` Embedding type. If not provided float embedding_type is used when needed. - `string? InputType` Model Input type. If not provided, search_document and search_query are used when needed. - `string ModelName` The modelId of the Cohere model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `string Truncate` Truncation type - START/ END/ NONE - `Type Type` Type of the embedding model. - `"COHERE_EMBEDDING"CohereEmbedding` - `class GeminiEmbeddingConfig:` - `GeminiEmbedding Component` Configuration for the Gemini embedding model. - `string? ApiBase` API base to access the model. Defaults to None. - `string? ApiKey` API key to access the model. Defaults to None. - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `string ModelName` The modelId of the Gemini model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Long? OutputDimensionality` Optional reduced dimension for output embeddings. Supported by models/text-embedding-004 and newer (e.g. gemini-embedding-001). Not supported by models/embedding-001. - `string? TaskType` The task for embedding model. - `string? Title` Title is only applicable for retrieval_document tasks, and is used to represent a document title. For other tasks, title is invalid. - `string? Transport` Transport to access the model. Defaults to None. - `Type Type` Type of the embedding model. - `"GEMINI_EMBEDDING"GeminiEmbedding` - `class HuggingFaceInferenceApiEmbeddingConfig:` - `HuggingFaceInferenceApiEmbedding Component` Configuration for the HuggingFace Inference API embedding model. - `Token? Token` Hugging Face token. Will default to the locally saved token. Pass token=False if you don’t want to send your token to the server. - `string` - `Boolean` - `string ClassName` - `IReadOnlyDictionary? Cookies` Additional cookies to send to the server. - `Long EmbedBatchSize` The batch size for embedding calls. - `IReadOnlyDictionary? Headers` Additional headers to send to the server. By default only the authorization and user-agent headers are sent. Values in this dictionary will override the default values. - `string? ModelName` Hugging Face model name. If None, the task will be used. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Pooling? Pooling` Enum of possible pooling choices with pooling behaviors. - `"cls"Cls` - `"last"Last` - `"mean"Mean` - `string? QueryInstruction` Instruction to prepend during query embedding. - `string? Task` Optional task to pick Hugging Face's recommended model, used when model_name is left as default of None. - `string? TextInstruction` Instruction to prepend during text embedding. - `Double? Timeout` The maximum number of seconds to wait for a response from the server. Loading a new model in Inference API can take up to several minutes. Defaults to None, meaning it will loop until the server is available. - `Type Type` Type of the embedding model. - `"HUGGINGFACE_API_EMBEDDING"HuggingfaceApiEmbedding` - `class OpenAIEmbeddingConfig:` - `OpenAIEmbedding Component` Configuration for the OpenAI embedding model. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the OpenAI API. - `string? ApiBase` The base URL for OpenAI API. - `string? ApiKey` The OpenAI API key. - `string? ApiVersion` The version for OpenAI API. - `string ClassName` - `IReadOnlyDictionary? DefaultHeaders` The default headers for API requests. - `Long? Dimensions` The number of dimensions on the output embedding vectors. Works only with v3 embedding models. - `Long EmbedBatchSize` The batch size for embedding calls. - `Long MaxRetries` Maximum number of retries. - `string ModelName` The name of the OpenAI embedding model. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Boolean ReuseClient` Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability. - `Double Timeout` Timeout for each request. - `Type Type` Type of the embedding model. - `"OPENAI_EMBEDDING"OpenAIEmbedding` - `class VertexAIEmbeddingConfig:` - `VertexTextEmbedding Component` Configuration for the VertexAI embedding model. - `required string? ClientEmail` The client email for the VertexAI credentials. - `required string Location` The default location to use when making API calls. - `required string? PrivateKey` The private key for the VertexAI credentials. - `required string? PrivateKeyID` The private key ID for the VertexAI credentials. - `required string Project` The default GCP project to use when making Vertex API calls. - `required string? TokenUri` The token URI for the VertexAI credentials. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the Vertex. - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `EmbedMode EmbedMode` The embedding mode to use. - `"classification"Classification` - `"clustering"Clustering` - `"default"Default` - `"retrieval"Retrieval` - `"similarity"Similarity` - `string ModelName` The modelId of the VertexAI model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Type Type` Type of the embedding model. - `"VERTEXAI_EMBEDDING"VertexaiEmbedding` - `string? EmbeddingModelConfigID` Embedding model config ID. When provided instead of embedding_config, the embedding model config will be looked up by ID. - `LlamaParseParameters LlamaParseParameters` Settings that can be configured for how to use LlamaParse to parse files within a LlamaCloud pipeline. - `Boolean? AdaptiveLongTable` - `Boolean? AggressiveTableExtraction` - `Boolean? AnnotateLinks` - `Boolean? AutoMode` - `string? AutoModeConfigurationJson` - `Boolean? AutoModeTriggerOnImageInPage` - `string? AutoModeTriggerOnRegexpInPage` - `Boolean? AutoModeTriggerOnTableInPage` - `string? AutoModeTriggerOnTextInPage` - `string? AzureOpenAIApiVersion` - `string? AzureOpenAIDeploymentName` - `string? AzureOpenAIEndpoint` - `string? AzureOpenAIKey` - `Double? BboxBottom` - `Double? BboxLeft` - `Double? BboxRight` - `Double? BboxTop` - `string? BoundingBox` - `Boolean? CompactMarkdownTable` - `string? ComplementalFormattingInstruction` - `string? ConfidenceScoreEffort` - `string? ContentGuidelineInstruction` - `Boolean? ContinuousMode` - `Boolean? DisableImageExtraction` - `Boolean? DisableOcr` - `Boolean? DisableReconstruction` - `Boolean? DoNotCache` - `Boolean? DoNotUnrollColumns` - `Boolean? EnableCostOptimizer` - `Boolean? ExtractCharts` - `Boolean? ExtractLayout` - `Boolean? ExtractPrintedPageNumber` - `Boolean? FastMode` - `string? FormattingInstruction` - `string? Gpt4oApiKey` - `Boolean? Gpt4oMode` - `Boolean? GuessXlsxSheetName` - `Boolean? HideFooters` - `Boolean? HideHeaders` - `Boolean? HighResOcr` - `Boolean? HtmlMakeAllElementsVisible` - `Boolean? HtmlRemoveFixedElements` - `Boolean? HtmlRemoveNavigationElements` - `string? HttpProxy` - `Boolean? IgnoreDocumentElementsForLayoutDetection` - `IReadOnlyList? ImagesToSave` - `"embedded"Embedded` - `"layout"Layout` - `"screenshot"Screenshot` - `Boolean? InlineImagesInMarkdown` - `string? InputS3Path` - `string? InputS3Region` - `string? InputUrl` - `Boolean? InternalIsScreenshotJob` - `Boolean? InvalidateCache` - `Boolean? IsFormattingInstruction` - `Double? JobTimeoutExtraTimePerPageInSeconds` - `Double? JobTimeoutInSeconds` - `Boolean? KeepPageSeparatorWhenMergingTables` - `IReadOnlyList Languages` - `"abq"Abq` - `"ady"Ady` - `"af"Af` - `"ang"Ang` - `"ar"Ar` - `"as"As` - `"ava"Ava` - `"az"Az` - `"be"Be` - `"bg"Bg` - `"bgc"Bgc` - `"bh"Bh` - `"bho"Bho` - `"bn"Bn` - `"bs"Bs` - `"ch_sim"ChSim` - `"ch_tra"ChTra` - `"che"Che` - `"cs"Cs` - `"cy"Cy` - `"da"Da` - `"dar"Dar` - `"de"De` - `"en"En` - `"es"Es` - `"et"Et` - `"fa"Fa` - `"fr"Fr` - `"ga"Ga` - `"gom"Gom` - `"hi"Hi` - `"hr"Hr` - `"hu"Hu` - `"id"ID` - `"inh"Inh` - `"is"Is` - `"it"It` - `"ja"Ja` - `"kbd"Kbd` - `"kn"Kn` - `"ko"Ko` - `"ku"Ku` - `"la"La` - `"lbe"Lbe` - `"lez"Lez` - `"lt"Lt` - `"lv"Lv` - `"mah"Mah` - `"mai"Mai` - `"mi"Mi` - `"mn"Mn` - `"mni"Mni` - `"mr"Mr` - `"ms"Ms` - `"mt"Mt` - `"ne"Ne` - `"new"New` - `"nl"Nl` - `"no"No` - `"oc"Oc` - `"pi"Pi` - `"pl"Pl` - `"pt"Pt` - `"ro"Ro` - `"rs_cyrillic"RsCyrillic` - `"rs_latin"RsLatin` - `"ru"Ru` - `"sa"Sa` - `"sck"Sck` - `"sk"Sk` - `"sl"Sl` - `"sq"Sq` - `"sv"Sv` - `"sw"Sw` - `"ta"Ta` - `"tab"Tab` - `"te"Te` - `"th"Th` - `"tjk"Tjk` - `"tl"Tl` - `"tr"Tr` - `"ug"Ug` - `"uk"Uk` - `"ur"Ur` - `"uz"Uz` - `"vi"Vi` - `Boolean? LayoutAware` - `Boolean? LineLevelBoundingBox` - `string? MarkdownTableMultilineHeaderSeparator` - `Long? MaxPages` - `Long? MaxPagesEnforced` - `Boolean? MergeTablesAcrossPagesInMarkdown` - `string? Model` - `Boolean? OutlinedTableExtraction` - `Boolean? OutputPdfOfDocument` - `string? OutputS3PathPrefix` - `string? OutputS3Region` - `Boolean? OutputTablesAsHtml` - `Double? PageErrorTolerance` - `string? PageFooterPrefix` - `string? PageFooterSuffix` - `string? PageHeaderPrefix` - `string? PageHeaderSuffix` - `string? PagePrefix` - `string? PageSeparator` - `string? PageSuffix` - `ParsingMode? ParseMode` Enum for representing the mode of parsing to be used. - `"parse_document_with_agent"ParseDocumentWithAgent` - `"parse_document_with_llm"ParseDocumentWithLlm` - `"parse_document_with_lvm"ParseDocumentWithLvm` - `"parse_page_with_agent"ParsePageWithAgent` - `"parse_page_with_layout_agent"ParsePageWithLayoutAgent` - `"parse_page_with_llm"ParsePageWithLlm` - `"parse_page_with_lvm"ParsePageWithLvm` - `"parse_page_without_llm"ParsePageWithoutLlm` - `string? ParsingInstruction` - `Boolean? PreciseBoundingBox` - `Boolean? PremiumMode` - `Boolean? PresentationOutOfBoundsContent` - `Boolean? PresentationSkipEmbeddedData` - `Boolean? PreserveLayoutAlignmentAcrossPages` - `Boolean? PreserveVerySmallText` - `string? Preset` - `Priority? Priority` The priority for the request. This field may be ignored or overwritten depending on the organization tier. - `"critical"Critical` - `"high"High` - `"low"Low` - `"medium"Medium` - `string? ProjectID` - `Boolean? RemoveHiddenText` - `FailPageMode? ReplaceFailedPageMode` Enum for representing the different available page error handling modes. - `"blank_page"BlankPage` - `"error_message"ErrorMessage` - `"raw_text"RawText` - `string? ReplaceFailedPageWithErrorMessagePrefix` - `string? ReplaceFailedPageWithErrorMessageSuffix` - `Boolean? SaveImages` - `Boolean? SkipDiagonalText` - `Boolean? SpecializedChartParsingAgentic` - `Boolean? SpecializedChartParsingEfficient` - `Boolean? SpecializedChartParsingPlus` - `Boolean? SpecializedImageParsing` - `Boolean? SpreadsheetExtractSubTables` - `Boolean? SpreadsheetForceFormulaComputation` - `Boolean? SpreadsheetIncludeHiddenSheets` - `Boolean? StrictModeBuggyFont` - `Boolean? StrictModeImageExtraction` - `Boolean? StrictModeImageOcr` - `Boolean? StrictModeReconstruction` - `Boolean? StructuredOutput` - `string? StructuredOutputJsonSchema` - `string? StructuredOutputJsonSchemaName` - `string? SystemPrompt` - `string? SystemPromptAppend` - `Boolean? TakeScreenshot` - `string? TargetPages` - `string? Tier` - `Boolean? UseVendorMultimodalModel` - `string? UserPrompt` - `string? VendorMultimodalApiKey` - `string? VendorMultimodalModelName` - `string? Version` - `IReadOnlyList? WebhookConfigurations` Outbound webhook endpoints to notify on job status changes - `IReadOnlyList? WebhookEvents` Events to subscribe to (e.g. 'parse.success', 'extract.error'). If null, all events are delivered. - `"classify.cancelled"ClassifyCancelled` - `"classify.error"ClassifyError` - `"classify.partial_success"ClassifyPartialSuccess` - `"classify.pending"ClassifyPending` - `"classify.running"ClassifyRunning` - `"classify.success"ClassifySuccess` - `"extract.cancelled"ExtractCancelled` - `"extract.error"ExtractError` - `"extract.partial_success"ExtractPartialSuccess` - `"extract.pending"ExtractPending` - `"extract.success"ExtractSuccess` - `"parse.cancelled"ParseCancelled` - `"parse.error"ParseError` - `"parse.partial_success"ParsePartialSuccess` - `"parse.pending"ParsePending` - `"parse.running"ParseRunning` - `"parse.success"ParseSuccess` - `"sheets.cancelled"SheetsCancelled` - `"sheets.error"SheetsError` - `"sheets.partial_success"SheetsPartialSuccess` - `"sheets.pending"SheetsPending` - `"sheets.success"SheetsSuccess` - `"split.cancelled"SplitCancelled` - `"split.error"SplitError` - `"split.pending"SplitPending` - `"split.processing"SplitProcessing` - `"split.success"SplitSuccess` - `"unmapped_event"UnmappedEvent` - `IReadOnlyDictionary? WebhookHeaders` Custom HTTP headers sent with each webhook request (e.g. auth tokens) - `string? WebhookOutputFormat` Response format sent to the webhook: 'string' (default) or 'json' - `string? WebhookSigningSecret` Shared signing secret used to sign webhook deliveries. When set, each request includes an HMAC-SHA256 signature of the request body in the 'LC-Signature' header (value 'sha256='). Recompute the HMAC over the raw request body with this secret to verify the delivery is authentic. - `string? WebhookUrl` URL to receive webhook POST notifications - `string? WebhookUrl` - `string? ManagedPipelineID` The ID of the ManagedPipeline this playground pipeline is linked to. - `PipelineMetadataConfig? MetadataConfig` Metadata configuration for the pipeline. - `IReadOnlyList ExcludedEmbedMetadataKeys` List of metadata keys to exclude from embeddings - `IReadOnlyList ExcludedLlmMetadataKeys` List of metadata keys to exclude from LLM during retrieval - `PipelineType PipelineType` Type of pipeline. Either PLAYGROUND or MANAGED. - `"MANAGED"Managed` - `"PLAYGROUND"Playground` - `PresetRetrievalParams PresetRetrievalParameters` Preset retrieval parameters for the pipeline. - `Double? Alpha` Alpha value for hybrid retrieval to determine the weights between dense and sparse retrieval. 0 is sparse retrieval and 1 is dense retrieval. - `string ClassName` - `Double? DenseSimilarityCutoff` Minimum similarity score wrt query for retrieval - `Long? DenseSimilarityTopK` Number of nodes for dense retrieval. - `Boolean? EnableReranking` Enable reranking for retrieval - `Long? FilesTopK` Number of files to retrieve (only for retrieval mode files_via_metadata and files_via_content). - `Long? RerankTopN` Number of reranked nodes for returning. - `RetrievalMode RetrievalMode` The retrieval mode for the query. - `"auto_routed"AutoRouted` - `"chunks"Chunks` - `"files_via_content"FilesViaContent` - `"files_via_metadata"FilesViaMetadata` - `Boolean RetrieveImageNodes` Whether to retrieve image nodes. - `Boolean RetrievePageFigureNodes` Whether to retrieve page figure nodes. - `Boolean RetrievePageScreenshotNodes` Whether to retrieve page screenshot nodes. - `MetadataFilters? SearchFilters` Metadata filters for vector stores. - `required IReadOnlyList Filters` - `class MetadataFilter:` Comprehensive metadata filter for vector stores to support more operators. Value uses Strict types, as int, float and str are compatible types and were all converted to string before. See: https://docs.pydantic.dev/latest/usage/types/#strict-types - `required string Key` - `required Value? Value` - `Double` - `string` - `IReadOnlyList` - `IReadOnlyList` - `IReadOnlyList` - `Operator Operator` Vector store filter operator. - `"!="` - `"<"` - `"<="` - `"=="` - `">"` - `">="` - `"all"All` - `"any"Any` - `"contains"Contains` - `"in"In` - `"is_empty"IsEmpty` - `"nin"Nin` - `"text_match"TextMatch` - `"text_match_insensitive"TextMatchInsensitive` - `class MetadataFilters:` Metadata filters for vector stores. - `Condition? Condition` Vector store filter conditions to combine different filters. - `"and"And` - `"not"Not` - `"or"Or` - `IReadOnlyDictionary? SearchFiltersInferenceSchema` JSON Schema that will be used to infer search_filters. Omit or leave as null to skip inference. - `IReadOnlyDictionary` - `IReadOnlyList` - `string` - `Double` - `Boolean` - `Long? SparseSimilarityTopK` Number of nodes for sparse retrieval. - `SparseModelConfig? SparseModelConfig` Configuration for sparse embedding models used in hybrid search. This allows users to choose between Splade and BM25 models for sparse retrieval in managed data sinks. - `string ClassName` - `ModelType ModelType` The sparse model type to use. 'bm25' uses Qdrant's FastEmbed BM25 model (default for new pipelines), 'splade' uses HuggingFace Splade model, 'auto' selects based on deployment mode (BYOC uses term frequency, Cloud uses Splade). - `"auto"Auto` - `"bm25"Bm25` - `"splade"Splade` - `string? Status` Status of the pipeline deployment. - `TransformConfig? TransformConfig` Configuration for the transformation. - `class AutoTransformConfig:` - `Long ChunkOverlap` Chunk overlap for the transformation. - `Long ChunkSize` Chunk size for the transformation. - `Mode Mode` - `"auto"Auto` - `class AdvancedModeTransformConfig:` - `ChunkingConfig ChunkingConfig` Configuration for the chunking. - `class NoneChunkingConfig:` - `Mode Mode` - `"none"None` - `class CharacterChunkingConfig:` - `Long ChunkOverlap` - `Long ChunkSize` - `Mode Mode` - `"character"Character` - `class TokenChunkingConfig:` - `Long ChunkOverlap` - `Long ChunkSize` - `Mode Mode` - `"token"Token` - `string Separator` - `class SentenceChunkingConfig:` - `Long ChunkOverlap` - `Long ChunkSize` - `Mode Mode` - `"sentence"Sentence` - `string ParagraphSeparator` - `string Separator` - `class SemanticChunkingConfig:` - `Long BreakpointPercentileThreshold` - `Long BufferSize` - `Mode Mode` - `"semantic"Semantic` - `Mode Mode` - `"advanced"Advanced` - `SegmentationConfig SegmentationConfig` Configuration for the segmentation. - `class NoneSegmentationConfig:` - `Mode Mode` - `"none"None` - `class PageSegmentationConfig:` - `Mode Mode` - `"page"Page` - `string PageSeparator` - `class ElementSegmentationConfig:` - `Mode Mode` - `"element"Element` ### Pipeline Metadata Config - `class PipelineMetadataConfig:` - `IReadOnlyList ExcludedEmbedMetadataKeys` List of metadata keys to exclude from embeddings - `IReadOnlyList ExcludedLlmMetadataKeys` List of metadata keys to exclude from LLM during retrieval ### Pipeline Type - `enum PipelineType:` Enum for representing the type of a pipeline - `"MANAGED"Managed` - `"PLAYGROUND"Playground` ### Preset Retrieval Params - `class PresetRetrievalParams:` Schema for the search params for an retrieval execution that can be preset for a pipeline. - `Double? Alpha` Alpha value for hybrid retrieval to determine the weights between dense and sparse retrieval. 0 is sparse retrieval and 1 is dense retrieval. - `string ClassName` - `Double? DenseSimilarityCutoff` Minimum similarity score wrt query for retrieval - `Long? DenseSimilarityTopK` Number of nodes for dense retrieval. - `Boolean? EnableReranking` Enable reranking for retrieval - `Long? FilesTopK` Number of files to retrieve (only for retrieval mode files_via_metadata and files_via_content). - `Long? RerankTopN` Number of reranked nodes for returning. - `RetrievalMode RetrievalMode` The retrieval mode for the query. - `"auto_routed"AutoRouted` - `"chunks"Chunks` - `"files_via_content"FilesViaContent` - `"files_via_metadata"FilesViaMetadata` - `Boolean RetrieveImageNodes` Whether to retrieve image nodes. - `Boolean RetrievePageFigureNodes` Whether to retrieve page figure nodes. - `Boolean RetrievePageScreenshotNodes` Whether to retrieve page screenshot nodes. - `MetadataFilters? SearchFilters` Metadata filters for vector stores. - `required IReadOnlyList Filters` - `class MetadataFilter:` Comprehensive metadata filter for vector stores to support more operators. Value uses Strict types, as int, float and str are compatible types and were all converted to string before. See: https://docs.pydantic.dev/latest/usage/types/#strict-types - `required string Key` - `required Value? Value` - `Double` - `string` - `IReadOnlyList` - `IReadOnlyList` - `IReadOnlyList` - `Operator Operator` Vector store filter operator. - `"!="` - `"<"` - `"<="` - `"=="` - `">"` - `">="` - `"all"All` - `"any"Any` - `"contains"Contains` - `"in"In` - `"is_empty"IsEmpty` - `"nin"Nin` - `"text_match"TextMatch` - `"text_match_insensitive"TextMatchInsensitive` - `class MetadataFilters:` Metadata filters for vector stores. - `Condition? Condition` Vector store filter conditions to combine different filters. - `"and"And` - `"not"Not` - `"or"Or` - `IReadOnlyDictionary? SearchFiltersInferenceSchema` JSON Schema that will be used to infer search_filters. Omit or leave as null to skip inference. - `IReadOnlyDictionary` - `IReadOnlyList` - `string` - `Double` - `Boolean` - `Long? SparseSimilarityTopK` Number of nodes for sparse retrieval. ### Retrieval Mode - `enum RetrievalMode:` - `"auto_routed"AutoRouted` - `"chunks"Chunks` - `"files_via_content"FilesViaContent` - `"files_via_metadata"FilesViaMetadata` ### Sparse Model Config - `class SparseModelConfig:` Configuration for sparse embedding models used in hybrid search. This allows users to choose between Splade and BM25 models for sparse retrieval in managed data sinks. - `string ClassName` - `ModelType ModelType` The sparse model type to use. 'bm25' uses Qdrant's FastEmbed BM25 model (default for new pipelines), 'splade' uses HuggingFace Splade model, 'auto' selects based on deployment mode (BYOC uses term frequency, Cloud uses Splade). - `"auto"Auto` - `"bm25"Bm25` - `"splade"Splade` ### Vertex AI Embedding Config - `class VertexAIEmbeddingConfig:` - `VertexTextEmbedding Component` Configuration for the VertexAI embedding model. - `required string? ClientEmail` The client email for the VertexAI credentials. - `required string Location` The default location to use when making API calls. - `required string? PrivateKey` The private key for the VertexAI credentials. - `required string? PrivateKeyID` The private key ID for the VertexAI credentials. - `required string Project` The default GCP project to use when making Vertex API calls. - `required string? TokenUri` The token URI for the VertexAI credentials. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the Vertex. - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `EmbedMode EmbedMode` The embedding mode to use. - `"classification"Classification` - `"clustering"Clustering` - `"default"Default` - `"retrieval"Retrieval` - `"similarity"Similarity` - `string ModelName` The modelId of the VertexAI model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Type Type` Type of the embedding model. - `"VERTEXAI_EMBEDDING"VertexaiEmbedding` ### Vertex Text Embedding - `class VertexTextEmbedding:` - `required string? ClientEmail` The client email for the VertexAI credentials. - `required string Location` The default location to use when making API calls. - `required string? PrivateKey` The private key for the VertexAI credentials. - `required string? PrivateKeyID` The private key ID for the VertexAI credentials. - `required string Project` The default GCP project to use when making Vertex API calls. - `required string? TokenUri` The token URI for the VertexAI credentials. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the Vertex. - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `EmbedMode EmbedMode` The embedding mode to use. - `"classification"Classification` - `"clustering"Clustering` - `"default"Default` - `"retrieval"Retrieval` - `"similarity"Similarity` - `string ModelName` The modelId of the VertexAI model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. # Sync ## Sync Pipeline `Pipeline Pipelines.Sync.Create(SyncCreateParamsparameters, CancellationTokencancellationToken = default)` **post** `/api/v1/pipelines/{pipeline_id}/sync` Trigger an incremental sync for a managed pipeline. Processes new and updated documents from data sources and files, then updates the index for retrieval. ### Parameters - `SyncCreateParams parameters` - `required string pipelineID` ### Returns - `class Pipeline:` Schema for a pipeline. - `required string ID` Unique identifier - `required EmbeddingConfig EmbeddingConfig` - `class AzureOpenAIEmbeddingConfig:` - `AzureOpenAIEmbedding Component` Configuration for the Azure OpenAI embedding model. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the OpenAI API. - `string ApiBase` The base URL for Azure deployment. - `string? ApiKey` The OpenAI API key. - `string ApiVersion` The version for Azure OpenAI API. - `string? AzureDeployment` The Azure deployment to use. - `string? AzureEndpoint` The Azure endpoint to use. - `string ClassName` - `IReadOnlyDictionary? DefaultHeaders` The default headers for API requests. - `Long? Dimensions` The number of dimensions on the output embedding vectors. Works only with v3 embedding models. - `Long EmbedBatchSize` The batch size for embedding calls. - `Long MaxRetries` Maximum number of retries. - `string ModelName` The name of the OpenAI embedding model. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Boolean ReuseClient` Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability. - `Double Timeout` Timeout for each request. - `Type Type` Type of the embedding model. - `"AZURE_EMBEDDING"AzureEmbedding` - `class BedrockEmbeddingConfig:` - `BedrockEmbedding Component` Configuration for the Bedrock embedding model. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the bedrock client. - `string? AwsAccessKeyID` AWS Access Key ID to use - `string? AwsSecretAccessKey` AWS Secret Access Key to use - `string? AwsSessionToken` AWS Session Token to use - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `Long MaxRetries` The maximum number of API retries. - `string ModelName` The modelId of the Bedrock model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `string? ProfileName` The name of aws profile to use. If not given, then the default profile is used. - `string? RegionName` AWS region name to use. Uses region configured in AWS CLI if not passed - `Double Timeout` The timeout for the Bedrock API request in seconds. It will be used for both connect and read timeouts. - `Type Type` Type of the embedding model. - `"BEDROCK_EMBEDDING"BedrockEmbedding` - `class CohereEmbeddingConfig:` - `CohereEmbedding Component` Configuration for the Cohere embedding model. - `required string? ApiKey` The Cohere API key. - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `string EmbeddingType` Embedding type. If not provided float embedding_type is used when needed. - `string? InputType` Model Input type. If not provided, search_document and search_query are used when needed. - `string ModelName` The modelId of the Cohere model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `string Truncate` Truncation type - START/ END/ NONE - `Type Type` Type of the embedding model. - `"COHERE_EMBEDDING"CohereEmbedding` - `class GeminiEmbeddingConfig:` - `GeminiEmbedding Component` Configuration for the Gemini embedding model. - `string? ApiBase` API base to access the model. Defaults to None. - `string? ApiKey` API key to access the model. Defaults to None. - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `string ModelName` The modelId of the Gemini model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Long? OutputDimensionality` Optional reduced dimension for output embeddings. Supported by models/text-embedding-004 and newer (e.g. gemini-embedding-001). Not supported by models/embedding-001. - `string? TaskType` The task for embedding model. - `string? Title` Title is only applicable for retrieval_document tasks, and is used to represent a document title. For other tasks, title is invalid. - `string? Transport` Transport to access the model. Defaults to None. - `Type Type` Type of the embedding model. - `"GEMINI_EMBEDDING"GeminiEmbedding` - `class HuggingFaceInferenceApiEmbeddingConfig:` - `HuggingFaceInferenceApiEmbedding Component` Configuration for the HuggingFace Inference API embedding model. - `Token? Token` Hugging Face token. Will default to the locally saved token. Pass token=False if you don’t want to send your token to the server. - `string` - `Boolean` - `string ClassName` - `IReadOnlyDictionary? Cookies` Additional cookies to send to the server. - `Long EmbedBatchSize` The batch size for embedding calls. - `IReadOnlyDictionary? Headers` Additional headers to send to the server. By default only the authorization and user-agent headers are sent. Values in this dictionary will override the default values. - `string? ModelName` Hugging Face model name. If None, the task will be used. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Pooling? Pooling` Enum of possible pooling choices with pooling behaviors. - `"cls"Cls` - `"last"Last` - `"mean"Mean` - `string? QueryInstruction` Instruction to prepend during query embedding. - `string? Task` Optional task to pick Hugging Face's recommended model, used when model_name is left as default of None. - `string? TextInstruction` Instruction to prepend during text embedding. - `Double? Timeout` The maximum number of seconds to wait for a response from the server. Loading a new model in Inference API can take up to several minutes. Defaults to None, meaning it will loop until the server is available. - `Type Type` Type of the embedding model. - `"HUGGINGFACE_API_EMBEDDING"HuggingfaceApiEmbedding` - `class ManagedOpenAIEmbedding:` - `Component Component` Configuration for the Managed OpenAI embedding model. - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `ModelName ModelName` The name of the OpenAI embedding model. - `"openai-text-embedding-3-small"OpenAITextEmbedding3Small` - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Type Type` Type of the embedding model. - `"MANAGED_OPENAI_EMBEDDING"ManagedOpenAIEmbedding` - `class OpenAIEmbeddingConfig:` - `OpenAIEmbedding Component` Configuration for the OpenAI embedding model. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the OpenAI API. - `string? ApiBase` The base URL for OpenAI API. - `string? ApiKey` The OpenAI API key. - `string? ApiVersion` The version for OpenAI API. - `string ClassName` - `IReadOnlyDictionary? DefaultHeaders` The default headers for API requests. - `Long? Dimensions` The number of dimensions on the output embedding vectors. Works only with v3 embedding models. - `Long EmbedBatchSize` The batch size for embedding calls. - `Long MaxRetries` Maximum number of retries. - `string ModelName` The name of the OpenAI embedding model. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Boolean ReuseClient` Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability. - `Double Timeout` Timeout for each request. - `Type Type` Type of the embedding model. - `"OPENAI_EMBEDDING"OpenAIEmbedding` - `class VertexAIEmbeddingConfig:` - `VertexTextEmbedding Component` Configuration for the VertexAI embedding model. - `required string? ClientEmail` The client email for the VertexAI credentials. - `required string Location` The default location to use when making API calls. - `required string? PrivateKey` The private key for the VertexAI credentials. - `required string? PrivateKeyID` The private key ID for the VertexAI credentials. - `required string Project` The default GCP project to use when making Vertex API calls. - `required string? TokenUri` The token URI for the VertexAI credentials. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the Vertex. - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `EmbedMode EmbedMode` The embedding mode to use. - `"classification"Classification` - `"clustering"Clustering` - `"default"Default` - `"retrieval"Retrieval` - `"similarity"Similarity` - `string ModelName` The modelId of the VertexAI model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Type Type` Type of the embedding model. - `"VERTEXAI_EMBEDDING"VertexaiEmbedding` - `required string Name` - `required string ProjectID` - `ConfigHash? ConfigHash` Hashes for the configuration of a pipeline. - `string? EmbeddingConfigHash` Hash of the embedding config. - `string? ParsingConfigHash` Hash of the llama parse parameters. - `string? TransformConfigHash` Hash of the transform config. - `DateTimeOffset? CreatedAt` Creation datetime - `DataSink? DataSink` Schema for a data sink. - `required string ID` Unique identifier - `required Component Component` Component that implements the data sink - `IReadOnlyDictionary` - `class CloudPineconeVectorStore:` Cloud Pinecone Vector Store. This class is used to store the configuration for a Pinecone vector store, so that it can be created and used in LlamaCloud. Args: api_key (str): API key for authenticating with Pinecone index_name (str): name of the Pinecone index namespace (optional[str]): namespace to use in the Pinecone index insert_kwargs (optional[dict]): additional kwargs to pass during insertion - `required string ApiKey` The API key for authenticating with Pinecone - `required string IndexName` - `string ClassName` - `IReadOnlyDictionary? InsertKwargs` - `string? Namespace` - `SupportsNestedMetadataFilters SupportsNestedMetadataFilters` - `trueTrue` - `class CloudPostgresVectorStore:` - `required string Database` - `required Long EmbedDim` - `required string Host` - `required string Password` - `required Long Port` - `required string SchemaName` - `required string TableName` - `required string User` - `string ClassName` - `PgVectorHnswSettings? HnswSettings` HNSW settings for PGVector. - `DistanceMethod DistanceMethod` The distance method to use. - `"cosine"Cosine` - `"hamming"Hamming` - `"ip"IP` - `"jaccard"Jaccard` - `"l1"L1` - `"l2"L2` - `Long EfConstruction` The number of edges to use during the construction phase. - `Long EfSearch` The number of edges to use during the search phase. - `Long M` The number of bi-directional links created for each new element. - `VectorType VectorType` The type of vector to use. - `"bit"Bit` - `"half_vec"HalfVec` - `"sparse_vec"SparseVec` - `"vector"Vector` - `Boolean? HybridSearch` - `Boolean PerformSetup` - `Boolean SupportsNestedMetadataFilters` - `class CloudQdrantVectorStore:` Cloud Qdrant Vector Store. This class is used to store the configuration for a Qdrant vector store, so that it can be created and used in LlamaCloud. Args: collection_name (str): name of the Qdrant collection url (str): url of the Qdrant instance api_key (str): API key for authenticating with Qdrant max_retries (int): maximum number of retries in case of a failure. Defaults to 3 client_kwargs (dict): additional kwargs to pass to the Qdrant client - `required string ApiKey` - `required string CollectionName` - `required string Url` - `string ClassName` - `IReadOnlyDictionary ClientKwargs` - `Long MaxRetries` - `SupportsNestedMetadataFilters SupportsNestedMetadataFilters` - `trueTrue` - `class CloudAzureAISearchVectorStore:` Cloud Azure AI Search Vector Store. - `required string SearchServiceApiKey` - `required string SearchServiceEndpoint` - `string ClassName` - `string? ClientID` - `string? ClientSecret` - `Long? EmbeddingDimension` - `IReadOnlyDictionary? FilterableMetadataFieldKeys` - `string? IndexName` - `string? SearchServiceApiVersion` - `SupportsNestedMetadataFilters SupportsNestedMetadataFilters` - `trueTrue` - `string? TenantID` - `class CloudMongoDBAtlasVectorSearch:` Cloud MongoDB Atlas Vector Store. This class is used to store the configuration for a MongoDB Atlas vector store, so that it can be created and used in LlamaCloud. Args: mongodb_uri (str): URI for connecting to MongoDB Atlas db_name (str): name of the MongoDB database collection_name (str): name of the MongoDB collection vector_index_name (str): name of the MongoDB Atlas vector index fulltext_index_name (str): name of the MongoDB Atlas full-text index - `required string CollectionName` - `required string DBName` - `required string MongoDBUri` - `string ClassName` - `Long? EmbeddingDimension` - `string? FulltextIndexName` - `Boolean SupportsNestedMetadataFilters` - `string? VectorIndexName` - `class CloudMilvusVectorStore:` Cloud Milvus Vector Store. - `required string Uri` - `string? Token` - `string ClassName` - `string? CollectionName` - `Long? EmbeddingDimension` - `Boolean SupportsNestedMetadataFilters` - `class CloudAstraDBVectorStore:` Cloud AstraDB Vector Store. This class is used to store the configuration for an AstraDB vector store, so that it can be created and used in LlamaCloud. Args: token (str): The Astra DB Application Token to use. api_endpoint (str): The Astra DB JSON API endpoint for your database. collection_name (str): Collection name to use. If not existing, it will be created. embedding_dimension (int): Length of the embedding vectors in use. keyspace (optional[str]): The keyspace to use. If not provided, 'default_keyspace' - `required string Token` The Astra DB Application Token to use - `required string ApiEndpoint` The Astra DB JSON API endpoint for your database - `required string CollectionName` Collection name to use. If not existing, it will be created - `required Long EmbeddingDimension` Length of the embedding vectors in use - `string ClassName` - `string? Keyspace` The keyspace to use. If not provided, 'default_keyspace' - `SupportsNestedMetadataFilters SupportsNestedMetadataFilters` - `trueTrue` - `required string Name` The name of the data sink. - `required string ProjectID` - `required SinkType SinkType` - `"ASTRA_DB"AstraDB` - `"AZUREAI_SEARCH"AzureaiSearch` - `"MILVUS"Milvus` - `"MONGODB_ATLAS"MongoDBAtlas` - `"PINECONE"Pinecone` - `"POSTGRES"Postgres` - `"QDRANT"Qdrant` - `DateTimeOffset? CreatedAt` Creation datetime - `DateTimeOffset? UpdatedAt` Update datetime - `EmbeddingModelConfig? EmbeddingModelConfig` Schema for an embedding model config. - `required string ID` Unique identifier - `required EmbeddingConfig EmbeddingConfig` The embedding configuration for the embedding model config. - `class AzureOpenAIEmbeddingConfig:` - `class BedrockEmbeddingConfig:` - `class CohereEmbeddingConfig:` - `class GeminiEmbeddingConfig:` - `class HuggingFaceInferenceApiEmbeddingConfig:` - `class OpenAIEmbeddingConfig:` - `class VertexAIEmbeddingConfig:` - `required string Name` The name of the embedding model config. - `required string ProjectID` - `DateTimeOffset? CreatedAt` Creation datetime - `DateTimeOffset? UpdatedAt` Update datetime - `string? EmbeddingModelConfigID` The ID of the EmbeddingModelConfig this pipeline is using. - `LlamaParseParameters? LlamaParseParameters` Settings that can be configured for how to use LlamaParse to parse files within a LlamaCloud pipeline. - `Boolean? AdaptiveLongTable` - `Boolean? AggressiveTableExtraction` - `Boolean? AnnotateLinks` - `Boolean? AutoMode` - `string? AutoModeConfigurationJson` - `Boolean? AutoModeTriggerOnImageInPage` - `string? AutoModeTriggerOnRegexpInPage` - `Boolean? AutoModeTriggerOnTableInPage` - `string? AutoModeTriggerOnTextInPage` - `string? AzureOpenAIApiVersion` - `string? AzureOpenAIDeploymentName` - `string? AzureOpenAIEndpoint` - `string? AzureOpenAIKey` - `Double? BboxBottom` - `Double? BboxLeft` - `Double? BboxRight` - `Double? BboxTop` - `string? BoundingBox` - `Boolean? CompactMarkdownTable` - `string? ComplementalFormattingInstruction` - `string? ConfidenceScoreEffort` - `string? ContentGuidelineInstruction` - `Boolean? ContinuousMode` - `Boolean? DisableImageExtraction` - `Boolean? DisableOcr` - `Boolean? DisableReconstruction` - `Boolean? DoNotCache` - `Boolean? DoNotUnrollColumns` - `Boolean? EnableCostOptimizer` - `Boolean? ExtractCharts` - `Boolean? ExtractLayout` - `Boolean? ExtractPrintedPageNumber` - `Boolean? FastMode` - `string? FormattingInstruction` - `string? Gpt4oApiKey` - `Boolean? Gpt4oMode` - `Boolean? GuessXlsxSheetName` - `Boolean? HideFooters` - `Boolean? HideHeaders` - `Boolean? HighResOcr` - `Boolean? HtmlMakeAllElementsVisible` - `Boolean? HtmlRemoveFixedElements` - `Boolean? HtmlRemoveNavigationElements` - `string? HttpProxy` - `Boolean? IgnoreDocumentElementsForLayoutDetection` - `IReadOnlyList? ImagesToSave` - `"embedded"Embedded` - `"layout"Layout` - `"screenshot"Screenshot` - `Boolean? InlineImagesInMarkdown` - `string? InputS3Path` - `string? InputS3Region` - `string? InputUrl` - `Boolean? InternalIsScreenshotJob` - `Boolean? InvalidateCache` - `Boolean? IsFormattingInstruction` - `Double? JobTimeoutExtraTimePerPageInSeconds` - `Double? JobTimeoutInSeconds` - `Boolean? KeepPageSeparatorWhenMergingTables` - `IReadOnlyList Languages` - `"abq"Abq` - `"ady"Ady` - `"af"Af` - `"ang"Ang` - `"ar"Ar` - `"as"As` - `"ava"Ava` - `"az"Az` - `"be"Be` - `"bg"Bg` - `"bgc"Bgc` - `"bh"Bh` - `"bho"Bho` - `"bn"Bn` - `"bs"Bs` - `"ch_sim"ChSim` - `"ch_tra"ChTra` - `"che"Che` - `"cs"Cs` - `"cy"Cy` - `"da"Da` - `"dar"Dar` - `"de"De` - `"en"En` - `"es"Es` - `"et"Et` - `"fa"Fa` - `"fr"Fr` - `"ga"Ga` - `"gom"Gom` - `"hi"Hi` - `"hr"Hr` - `"hu"Hu` - `"id"ID` - `"inh"Inh` - `"is"Is` - `"it"It` - `"ja"Ja` - `"kbd"Kbd` - `"kn"Kn` - `"ko"Ko` - `"ku"Ku` - `"la"La` - `"lbe"Lbe` - `"lez"Lez` - `"lt"Lt` - `"lv"Lv` - `"mah"Mah` - `"mai"Mai` - `"mi"Mi` - `"mn"Mn` - `"mni"Mni` - `"mr"Mr` - `"ms"Ms` - `"mt"Mt` - `"ne"Ne` - `"new"New` - `"nl"Nl` - `"no"No` - `"oc"Oc` - `"pi"Pi` - `"pl"Pl` - `"pt"Pt` - `"ro"Ro` - `"rs_cyrillic"RsCyrillic` - `"rs_latin"RsLatin` - `"ru"Ru` - `"sa"Sa` - `"sck"Sck` - `"sk"Sk` - `"sl"Sl` - `"sq"Sq` - `"sv"Sv` - `"sw"Sw` - `"ta"Ta` - `"tab"Tab` - `"te"Te` - `"th"Th` - `"tjk"Tjk` - `"tl"Tl` - `"tr"Tr` - `"ug"Ug` - `"uk"Uk` - `"ur"Ur` - `"uz"Uz` - `"vi"Vi` - `Boolean? LayoutAware` - `Boolean? LineLevelBoundingBox` - `string? MarkdownTableMultilineHeaderSeparator` - `Long? MaxPages` - `Long? MaxPagesEnforced` - `Boolean? MergeTablesAcrossPagesInMarkdown` - `string? Model` - `Boolean? OutlinedTableExtraction` - `Boolean? OutputPdfOfDocument` - `string? OutputS3PathPrefix` - `string? OutputS3Region` - `Boolean? OutputTablesAsHtml` - `Double? PageErrorTolerance` - `string? PageFooterPrefix` - `string? PageFooterSuffix` - `string? PageHeaderPrefix` - `string? PageHeaderSuffix` - `string? PagePrefix` - `string? PageSeparator` - `string? PageSuffix` - `ParsingMode? ParseMode` Enum for representing the mode of parsing to be used. - `"parse_document_with_agent"ParseDocumentWithAgent` - `"parse_document_with_llm"ParseDocumentWithLlm` - `"parse_document_with_lvm"ParseDocumentWithLvm` - `"parse_page_with_agent"ParsePageWithAgent` - `"parse_page_with_layout_agent"ParsePageWithLayoutAgent` - `"parse_page_with_llm"ParsePageWithLlm` - `"parse_page_with_lvm"ParsePageWithLvm` - `"parse_page_without_llm"ParsePageWithoutLlm` - `string? ParsingInstruction` - `Boolean? PreciseBoundingBox` - `Boolean? PremiumMode` - `Boolean? PresentationOutOfBoundsContent` - `Boolean? PresentationSkipEmbeddedData` - `Boolean? PreserveLayoutAlignmentAcrossPages` - `Boolean? PreserveVerySmallText` - `string? Preset` - `Priority? Priority` The priority for the request. This field may be ignored or overwritten depending on the organization tier. - `"critical"Critical` - `"high"High` - `"low"Low` - `"medium"Medium` - `string? ProjectID` - `Boolean? RemoveHiddenText` - `FailPageMode? ReplaceFailedPageMode` Enum for representing the different available page error handling modes. - `"blank_page"BlankPage` - `"error_message"ErrorMessage` - `"raw_text"RawText` - `string? ReplaceFailedPageWithErrorMessagePrefix` - `string? ReplaceFailedPageWithErrorMessageSuffix` - `Boolean? SaveImages` - `Boolean? SkipDiagonalText` - `Boolean? SpecializedChartParsingAgentic` - `Boolean? SpecializedChartParsingEfficient` - `Boolean? SpecializedChartParsingPlus` - `Boolean? SpecializedImageParsing` - `Boolean? SpreadsheetExtractSubTables` - `Boolean? SpreadsheetForceFormulaComputation` - `Boolean? SpreadsheetIncludeHiddenSheets` - `Boolean? StrictModeBuggyFont` - `Boolean? StrictModeImageExtraction` - `Boolean? StrictModeImageOcr` - `Boolean? StrictModeReconstruction` - `Boolean? StructuredOutput` - `string? StructuredOutputJsonSchema` - `string? StructuredOutputJsonSchemaName` - `string? SystemPrompt` - `string? SystemPromptAppend` - `Boolean? TakeScreenshot` - `string? TargetPages` - `string? Tier` - `Boolean? UseVendorMultimodalModel` - `string? UserPrompt` - `string? VendorMultimodalApiKey` - `string? VendorMultimodalModelName` - `string? Version` - `IReadOnlyList? WebhookConfigurations` Outbound webhook endpoints to notify on job status changes - `IReadOnlyList? WebhookEvents` Events to subscribe to (e.g. 'parse.success', 'extract.error'). If null, all events are delivered. - `"classify.cancelled"ClassifyCancelled` - `"classify.error"ClassifyError` - `"classify.partial_success"ClassifyPartialSuccess` - `"classify.pending"ClassifyPending` - `"classify.running"ClassifyRunning` - `"classify.success"ClassifySuccess` - `"extract.cancelled"ExtractCancelled` - `"extract.error"ExtractError` - `"extract.partial_success"ExtractPartialSuccess` - `"extract.pending"ExtractPending` - `"extract.success"ExtractSuccess` - `"parse.cancelled"ParseCancelled` - `"parse.error"ParseError` - `"parse.partial_success"ParsePartialSuccess` - `"parse.pending"ParsePending` - `"parse.running"ParseRunning` - `"parse.success"ParseSuccess` - `"sheets.cancelled"SheetsCancelled` - `"sheets.error"SheetsError` - `"sheets.partial_success"SheetsPartialSuccess` - `"sheets.pending"SheetsPending` - `"sheets.success"SheetsSuccess` - `"split.cancelled"SplitCancelled` - `"split.error"SplitError` - `"split.pending"SplitPending` - `"split.processing"SplitProcessing` - `"split.success"SplitSuccess` - `"unmapped_event"UnmappedEvent` - `IReadOnlyDictionary? WebhookHeaders` Custom HTTP headers sent with each webhook request (e.g. auth tokens) - `string? WebhookOutputFormat` Response format sent to the webhook: 'string' (default) or 'json' - `string? WebhookSigningSecret` Shared signing secret used to sign webhook deliveries. When set, each request includes an HMAC-SHA256 signature of the request body in the 'LC-Signature' header (value 'sha256='). Recompute the HMAC over the raw request body with this secret to verify the delivery is authentic. - `string? WebhookUrl` URL to receive webhook POST notifications - `string? WebhookUrl` - `string? ManagedPipelineID` The ID of the ManagedPipeline this playground pipeline is linked to. - `PipelineMetadataConfig? MetadataConfig` Metadata configuration for the pipeline. - `IReadOnlyList ExcludedEmbedMetadataKeys` List of metadata keys to exclude from embeddings - `IReadOnlyList ExcludedLlmMetadataKeys` List of metadata keys to exclude from LLM during retrieval - `PipelineType PipelineType` Type of pipeline. Either PLAYGROUND or MANAGED. - `"MANAGED"Managed` - `"PLAYGROUND"Playground` - `PresetRetrievalParams PresetRetrievalParameters` Preset retrieval parameters for the pipeline. - `Double? Alpha` Alpha value for hybrid retrieval to determine the weights between dense and sparse retrieval. 0 is sparse retrieval and 1 is dense retrieval. - `string ClassName` - `Double? DenseSimilarityCutoff` Minimum similarity score wrt query for retrieval - `Long? DenseSimilarityTopK` Number of nodes for dense retrieval. - `Boolean? EnableReranking` Enable reranking for retrieval - `Long? FilesTopK` Number of files to retrieve (only for retrieval mode files_via_metadata and files_via_content). - `Long? RerankTopN` Number of reranked nodes for returning. - `RetrievalMode RetrievalMode` The retrieval mode for the query. - `"auto_routed"AutoRouted` - `"chunks"Chunks` - `"files_via_content"FilesViaContent` - `"files_via_metadata"FilesViaMetadata` - `Boolean RetrieveImageNodes` Whether to retrieve image nodes. - `Boolean RetrievePageFigureNodes` Whether to retrieve page figure nodes. - `Boolean RetrievePageScreenshotNodes` Whether to retrieve page screenshot nodes. - `MetadataFilters? SearchFilters` Metadata filters for vector stores. - `required IReadOnlyList Filters` - `class MetadataFilter:` Comprehensive metadata filter for vector stores to support more operators. Value uses Strict types, as int, float and str are compatible types and were all converted to string before. See: https://docs.pydantic.dev/latest/usage/types/#strict-types - `required string Key` - `required Value? Value` - `Double` - `string` - `IReadOnlyList` - `IReadOnlyList` - `IReadOnlyList` - `Operator Operator` Vector store filter operator. - `"!="` - `"<"` - `"<="` - `"=="` - `">"` - `">="` - `"all"All` - `"any"Any` - `"contains"Contains` - `"in"In` - `"is_empty"IsEmpty` - `"nin"Nin` - `"text_match"TextMatch` - `"text_match_insensitive"TextMatchInsensitive` - `class MetadataFilters:` Metadata filters for vector stores. - `Condition? Condition` Vector store filter conditions to combine different filters. - `"and"And` - `"not"Not` - `"or"Or` - `IReadOnlyDictionary? SearchFiltersInferenceSchema` JSON Schema that will be used to infer search_filters. Omit or leave as null to skip inference. - `IReadOnlyDictionary` - `IReadOnlyList` - `string` - `Double` - `Boolean` - `Long? SparseSimilarityTopK` Number of nodes for sparse retrieval. - `SparseModelConfig? SparseModelConfig` Configuration for sparse embedding models used in hybrid search. This allows users to choose between Splade and BM25 models for sparse retrieval in managed data sinks. - `string ClassName` - `ModelType ModelType` The sparse model type to use. 'bm25' uses Qdrant's FastEmbed BM25 model (default for new pipelines), 'splade' uses HuggingFace Splade model, 'auto' selects based on deployment mode (BYOC uses term frequency, Cloud uses Splade). - `"auto"Auto` - `"bm25"Bm25` - `"splade"Splade` - `Status? Status` Status of the pipeline. - `"CREATED"Created` - `"DELETING"Deleting` - `TransformConfig TransformConfig` Configuration for the transformation. - `class AutoTransformConfig:` - `Long ChunkOverlap` Chunk overlap for the transformation. - `Long ChunkSize` Chunk size for the transformation. - `Mode Mode` - `"auto"Auto` - `class AdvancedModeTransformConfig:` - `ChunkingConfig ChunkingConfig` Configuration for the chunking. - `class NoneChunkingConfig:` - `Mode Mode` - `"none"None` - `class CharacterChunkingConfig:` - `Long ChunkOverlap` - `Long ChunkSize` - `Mode Mode` - `"character"Character` - `class TokenChunkingConfig:` - `Long ChunkOverlap` - `Long ChunkSize` - `Mode Mode` - `"token"Token` - `string Separator` - `class SentenceChunkingConfig:` - `Long ChunkOverlap` - `Long ChunkSize` - `Mode Mode` - `"sentence"Sentence` - `string ParagraphSeparator` - `string Separator` - `class SemanticChunkingConfig:` - `Long BreakpointPercentileThreshold` - `Long BufferSize` - `Mode Mode` - `"semantic"Semantic` - `Mode Mode` - `"advanced"Advanced` - `SegmentationConfig SegmentationConfig` Configuration for the segmentation. - `class NoneSegmentationConfig:` - `Mode Mode` - `"none"None` - `class PageSegmentationConfig:` - `Mode Mode` - `"page"Page` - `string PageSeparator` - `class ElementSegmentationConfig:` - `Mode Mode` - `"element"Element` - `DateTimeOffset? UpdatedAt` Update datetime ### Example ```csharp SyncCreateParams parameters = new() { PipelineID = "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e" }; var pipeline = await client.Pipelines.Sync.Create(parameters); Console.WriteLine(pipeline); ``` #### Response ```json { "id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "embedding_config": { "component": { "additional_kwargs": { "foo": "bar" }, "api_base": "api_base", "api_key": "api_key", "api_version": "api_version", "azure_deployment": "azure_deployment", "azure_endpoint": "azure_endpoint", "class_name": "class_name", "default_headers": { "foo": "string" }, "dimensions": 0, "embed_batch_size": 1, "max_retries": 0, "model_name": "model_name", "num_workers": 0, "reuse_client": true, "timeout": 0 }, "type": "AZURE_EMBEDDING" }, "name": "name", "project_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "config_hash": { "embedding_config_hash": "embedding_config_hash", "parsing_config_hash": "parsing_config_hash", "transform_config_hash": "transform_config_hash" }, "created_at": "2019-12-27T18:11:19.117Z", "data_sink": { "id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "component": { "foo": "bar" }, "name": "name", "project_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "sink_type": "ASTRA_DB", "created_at": "2019-12-27T18:11:19.117Z", "updated_at": "2019-12-27T18:11:19.117Z" }, "embedding_model_config": { "id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "embedding_config": { "component": { "additional_kwargs": { "foo": "bar" }, "api_base": "api_base", "api_key": "api_key", "api_version": "api_version", "azure_deployment": "azure_deployment", "azure_endpoint": "azure_endpoint", "class_name": "class_name", "default_headers": { "foo": "string" }, "dimensions": 0, "embed_batch_size": 1, "max_retries": 0, "model_name": "model_name", "num_workers": 0, "reuse_client": true, "timeout": 0 }, "type": "AZURE_EMBEDDING" }, "name": "name", "project_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "created_at": "2019-12-27T18:11:19.117Z", "updated_at": "2019-12-27T18:11:19.117Z" }, "embedding_model_config_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "llama_parse_parameters": { "adaptive_long_table": true, "aggressive_table_extraction": true, "annotate_links": true, "auto_mode": true, "auto_mode_configuration_json": "auto_mode_configuration_json", "auto_mode_trigger_on_image_in_page": true, "auto_mode_trigger_on_regexp_in_page": "auto_mode_trigger_on_regexp_in_page", "auto_mode_trigger_on_table_in_page": true, "auto_mode_trigger_on_text_in_page": "auto_mode_trigger_on_text_in_page", "azure_openai_api_version": "azure_openai_api_version", "azure_openai_deployment_name": "azure_openai_deployment_name", "azure_openai_endpoint": "azure_openai_endpoint", "azure_openai_key": "azure_openai_key", "bbox_bottom": 0, "bbox_left": 0, "bbox_right": 0, "bbox_top": 0, "bounding_box": "bounding_box", "compact_markdown_table": true, "complemental_formatting_instruction": "complemental_formatting_instruction", "confidence_score_effort": "confidence_score_effort", "content_guideline_instruction": "content_guideline_instruction", "continuous_mode": true, "disable_image_extraction": true, "disable_ocr": true, "disable_reconstruction": true, "do_not_cache": true, "do_not_unroll_columns": true, "enable_cost_optimizer": true, "extract_charts": true, "extract_layout": true, "extract_printed_page_number": true, "fast_mode": true, "formatting_instruction": "formatting_instruction", "gpt4o_api_key": "gpt4o_api_key", "gpt4o_mode": true, "guess_xlsx_sheet_name": true, "hide_footers": true, "hide_headers": true, "high_res_ocr": true, "html_make_all_elements_visible": true, "html_remove_fixed_elements": true, "html_remove_navigation_elements": true, "http_proxy": "http_proxy", "ignore_document_elements_for_layout_detection": true, "images_to_save": [ "embedded" ], "inline_images_in_markdown": true, "input_s3_path": "input_s3_path", "input_s3_region": "input_s3_region", "input_url": "input_url", "internal_is_screenshot_job": true, "invalidate_cache": true, "is_formatting_instruction": true, "job_timeout_extra_time_per_page_in_seconds": 0, "job_timeout_in_seconds": 0, "keep_page_separator_when_merging_tables": true, "languages": [ "abq" ], "layout_aware": true, "line_level_bounding_box": true, "markdown_table_multiline_header_separator": "markdown_table_multiline_header_separator", "max_pages": 0, "max_pages_enforced": 0, "merge_tables_across_pages_in_markdown": true, "model": "model", "outlined_table_extraction": true, "output_pdf_of_document": true, "output_s3_path_prefix": "output_s3_path_prefix", "output_s3_region": "output_s3_region", "output_tables_as_HTML": true, "page_error_tolerance": 0, "page_footer_prefix": "page_footer_prefix", "page_footer_suffix": "page_footer_suffix", "page_header_prefix": "page_header_prefix", "page_header_suffix": "page_header_suffix", "page_prefix": "page_prefix", "page_separator": "page_separator", "page_suffix": "page_suffix", "parse_mode": "parse_document_with_agent", "parsing_instruction": "parsing_instruction", "precise_bounding_box": true, "premium_mode": true, "presentation_out_of_bounds_content": true, "presentation_skip_embedded_data": true, "preserve_layout_alignment_across_pages": true, "preserve_very_small_text": true, "preset": "preset", "priority": "critical", "project_id": "project_id", "remove_hidden_text": true, "replace_failed_page_mode": "blank_page", "replace_failed_page_with_error_message_prefix": "replace_failed_page_with_error_message_prefix", "replace_failed_page_with_error_message_suffix": "replace_failed_page_with_error_message_suffix", "save_images": true, "skip_diagonal_text": true, "specialized_chart_parsing_agentic": true, "specialized_chart_parsing_efficient": true, "specialized_chart_parsing_plus": true, "specialized_image_parsing": true, "spreadsheet_extract_sub_tables": true, "spreadsheet_force_formula_computation": true, "spreadsheet_include_hidden_sheets": true, "strict_mode_buggy_font": true, "strict_mode_image_extraction": true, "strict_mode_image_ocr": true, "strict_mode_reconstruction": true, "structured_output": true, "structured_output_json_schema": "structured_output_json_schema", "structured_output_json_schema_name": "structured_output_json_schema_name", "system_prompt": "system_prompt", "system_prompt_append": "system_prompt_append", "take_screenshot": true, "target_pages": "target_pages", "tier": "tier", "use_vendor_multimodal_model": true, "user_prompt": "user_prompt", "vendor_multimodal_api_key": "vendor_multimodal_api_key", "vendor_multimodal_model_name": "vendor_multimodal_model_name", "version": "version", "webhook_configurations": [ { "webhook_events": [ "parse.success", "parse.error" ], "webhook_headers": { "Authorization": "Bearer sk-..." }, "webhook_output_format": "json", "webhook_signing_secret": "whsec_...", "webhook_url": "https://example.com/webhooks/llamacloud" } ], "webhook_url": "webhook_url" }, "managed_pipeline_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "metadata_config": { "excluded_embed_metadata_keys": [ "string" ], "excluded_llm_metadata_keys": [ "string" ] }, "pipeline_type": "MANAGED", "preset_retrieval_parameters": { "alpha": 0, "class_name": "class_name", "dense_similarity_cutoff": 0, "dense_similarity_top_k": 1, "enable_reranking": true, "files_top_k": 1, "rerank_top_n": 1, "retrieval_mode": "auto_routed", "retrieve_image_nodes": true, "retrieve_page_figure_nodes": true, "retrieve_page_screenshot_nodes": true, "search_filters": { "filters": [ { "key": "key", "value": 0, "operator": "!=" } ], "condition": "and" }, "search_filters_inference_schema": { "foo": { "foo": "bar" } }, "sparse_similarity_top_k": 1 }, "sparse_model_config": { "class_name": "class_name", "model_type": "auto" }, "status": "CREATED", "transform_config": { "chunk_overlap": 0, "chunk_size": 1, "mode": "auto" }, "updated_at": "2019-12-27T18:11:19.117Z" } ``` ## Cancel Pipeline Sync `Pipeline Pipelines.Sync.Cancel(SyncCancelParamsparameters, CancellationTokencancellationToken = default)` **post** `/api/v1/pipelines/{pipeline_id}/sync/cancel` Cancel all running sync jobs for a pipeline. ### Parameters - `SyncCancelParams parameters` - `required string pipelineID` ### Returns - `class Pipeline:` Schema for a pipeline. - `required string ID` Unique identifier - `required EmbeddingConfig EmbeddingConfig` - `class AzureOpenAIEmbeddingConfig:` - `AzureOpenAIEmbedding Component` Configuration for the Azure OpenAI embedding model. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the OpenAI API. - `string ApiBase` The base URL for Azure deployment. - `string? ApiKey` The OpenAI API key. - `string ApiVersion` The version for Azure OpenAI API. - `string? AzureDeployment` The Azure deployment to use. - `string? AzureEndpoint` The Azure endpoint to use. - `string ClassName` - `IReadOnlyDictionary? DefaultHeaders` The default headers for API requests. - `Long? Dimensions` The number of dimensions on the output embedding vectors. Works only with v3 embedding models. - `Long EmbedBatchSize` The batch size for embedding calls. - `Long MaxRetries` Maximum number of retries. - `string ModelName` The name of the OpenAI embedding model. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Boolean ReuseClient` Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability. - `Double Timeout` Timeout for each request. - `Type Type` Type of the embedding model. - `"AZURE_EMBEDDING"AzureEmbedding` - `class BedrockEmbeddingConfig:` - `BedrockEmbedding Component` Configuration for the Bedrock embedding model. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the bedrock client. - `string? AwsAccessKeyID` AWS Access Key ID to use - `string? AwsSecretAccessKey` AWS Secret Access Key to use - `string? AwsSessionToken` AWS Session Token to use - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `Long MaxRetries` The maximum number of API retries. - `string ModelName` The modelId of the Bedrock model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `string? ProfileName` The name of aws profile to use. If not given, then the default profile is used. - `string? RegionName` AWS region name to use. Uses region configured in AWS CLI if not passed - `Double Timeout` The timeout for the Bedrock API request in seconds. It will be used for both connect and read timeouts. - `Type Type` Type of the embedding model. - `"BEDROCK_EMBEDDING"BedrockEmbedding` - `class CohereEmbeddingConfig:` - `CohereEmbedding Component` Configuration for the Cohere embedding model. - `required string? ApiKey` The Cohere API key. - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `string EmbeddingType` Embedding type. If not provided float embedding_type is used when needed. - `string? InputType` Model Input type. If not provided, search_document and search_query are used when needed. - `string ModelName` The modelId of the Cohere model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `string Truncate` Truncation type - START/ END/ NONE - `Type Type` Type of the embedding model. - `"COHERE_EMBEDDING"CohereEmbedding` - `class GeminiEmbeddingConfig:` - `GeminiEmbedding Component` Configuration for the Gemini embedding model. - `string? ApiBase` API base to access the model. Defaults to None. - `string? ApiKey` API key to access the model. Defaults to None. - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `string ModelName` The modelId of the Gemini model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Long? OutputDimensionality` Optional reduced dimension for output embeddings. Supported by models/text-embedding-004 and newer (e.g. gemini-embedding-001). Not supported by models/embedding-001. - `string? TaskType` The task for embedding model. - `string? Title` Title is only applicable for retrieval_document tasks, and is used to represent a document title. For other tasks, title is invalid. - `string? Transport` Transport to access the model. Defaults to None. - `Type Type` Type of the embedding model. - `"GEMINI_EMBEDDING"GeminiEmbedding` - `class HuggingFaceInferenceApiEmbeddingConfig:` - `HuggingFaceInferenceApiEmbedding Component` Configuration for the HuggingFace Inference API embedding model. - `Token? Token` Hugging Face token. Will default to the locally saved token. Pass token=False if you don’t want to send your token to the server. - `string` - `Boolean` - `string ClassName` - `IReadOnlyDictionary? Cookies` Additional cookies to send to the server. - `Long EmbedBatchSize` The batch size for embedding calls. - `IReadOnlyDictionary? Headers` Additional headers to send to the server. By default only the authorization and user-agent headers are sent. Values in this dictionary will override the default values. - `string? ModelName` Hugging Face model name. If None, the task will be used. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Pooling? Pooling` Enum of possible pooling choices with pooling behaviors. - `"cls"Cls` - `"last"Last` - `"mean"Mean` - `string? QueryInstruction` Instruction to prepend during query embedding. - `string? Task` Optional task to pick Hugging Face's recommended model, used when model_name is left as default of None. - `string? TextInstruction` Instruction to prepend during text embedding. - `Double? Timeout` The maximum number of seconds to wait for a response from the server. Loading a new model in Inference API can take up to several minutes. Defaults to None, meaning it will loop until the server is available. - `Type Type` Type of the embedding model. - `"HUGGINGFACE_API_EMBEDDING"HuggingfaceApiEmbedding` - `class ManagedOpenAIEmbedding:` - `Component Component` Configuration for the Managed OpenAI embedding model. - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `ModelName ModelName` The name of the OpenAI embedding model. - `"openai-text-embedding-3-small"OpenAITextEmbedding3Small` - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Type Type` Type of the embedding model. - `"MANAGED_OPENAI_EMBEDDING"ManagedOpenAIEmbedding` - `class OpenAIEmbeddingConfig:` - `OpenAIEmbedding Component` Configuration for the OpenAI embedding model. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the OpenAI API. - `string? ApiBase` The base URL for OpenAI API. - `string? ApiKey` The OpenAI API key. - `string? ApiVersion` The version for OpenAI API. - `string ClassName` - `IReadOnlyDictionary? DefaultHeaders` The default headers for API requests. - `Long? Dimensions` The number of dimensions on the output embedding vectors. Works only with v3 embedding models. - `Long EmbedBatchSize` The batch size for embedding calls. - `Long MaxRetries` Maximum number of retries. - `string ModelName` The name of the OpenAI embedding model. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Boolean ReuseClient` Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability. - `Double Timeout` Timeout for each request. - `Type Type` Type of the embedding model. - `"OPENAI_EMBEDDING"OpenAIEmbedding` - `class VertexAIEmbeddingConfig:` - `VertexTextEmbedding Component` Configuration for the VertexAI embedding model. - `required string? ClientEmail` The client email for the VertexAI credentials. - `required string Location` The default location to use when making API calls. - `required string? PrivateKey` The private key for the VertexAI credentials. - `required string? PrivateKeyID` The private key ID for the VertexAI credentials. - `required string Project` The default GCP project to use when making Vertex API calls. - `required string? TokenUri` The token URI for the VertexAI credentials. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the Vertex. - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `EmbedMode EmbedMode` The embedding mode to use. - `"classification"Classification` - `"clustering"Clustering` - `"default"Default` - `"retrieval"Retrieval` - `"similarity"Similarity` - `string ModelName` The modelId of the VertexAI model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Type Type` Type of the embedding model. - `"VERTEXAI_EMBEDDING"VertexaiEmbedding` - `required string Name` - `required string ProjectID` - `ConfigHash? ConfigHash` Hashes for the configuration of a pipeline. - `string? EmbeddingConfigHash` Hash of the embedding config. - `string? ParsingConfigHash` Hash of the llama parse parameters. - `string? TransformConfigHash` Hash of the transform config. - `DateTimeOffset? CreatedAt` Creation datetime - `DataSink? DataSink` Schema for a data sink. - `required string ID` Unique identifier - `required Component Component` Component that implements the data sink - `IReadOnlyDictionary` - `class CloudPineconeVectorStore:` Cloud Pinecone Vector Store. This class is used to store the configuration for a Pinecone vector store, so that it can be created and used in LlamaCloud. Args: api_key (str): API key for authenticating with Pinecone index_name (str): name of the Pinecone index namespace (optional[str]): namespace to use in the Pinecone index insert_kwargs (optional[dict]): additional kwargs to pass during insertion - `required string ApiKey` The API key for authenticating with Pinecone - `required string IndexName` - `string ClassName` - `IReadOnlyDictionary? InsertKwargs` - `string? Namespace` - `SupportsNestedMetadataFilters SupportsNestedMetadataFilters` - `trueTrue` - `class CloudPostgresVectorStore:` - `required string Database` - `required Long EmbedDim` - `required string Host` - `required string Password` - `required Long Port` - `required string SchemaName` - `required string TableName` - `required string User` - `string ClassName` - `PgVectorHnswSettings? HnswSettings` HNSW settings for PGVector. - `DistanceMethod DistanceMethod` The distance method to use. - `"cosine"Cosine` - `"hamming"Hamming` - `"ip"IP` - `"jaccard"Jaccard` - `"l1"L1` - `"l2"L2` - `Long EfConstruction` The number of edges to use during the construction phase. - `Long EfSearch` The number of edges to use during the search phase. - `Long M` The number of bi-directional links created for each new element. - `VectorType VectorType` The type of vector to use. - `"bit"Bit` - `"half_vec"HalfVec` - `"sparse_vec"SparseVec` - `"vector"Vector` - `Boolean? HybridSearch` - `Boolean PerformSetup` - `Boolean SupportsNestedMetadataFilters` - `class CloudQdrantVectorStore:` Cloud Qdrant Vector Store. This class is used to store the configuration for a Qdrant vector store, so that it can be created and used in LlamaCloud. Args: collection_name (str): name of the Qdrant collection url (str): url of the Qdrant instance api_key (str): API key for authenticating with Qdrant max_retries (int): maximum number of retries in case of a failure. Defaults to 3 client_kwargs (dict): additional kwargs to pass to the Qdrant client - `required string ApiKey` - `required string CollectionName` - `required string Url` - `string ClassName` - `IReadOnlyDictionary ClientKwargs` - `Long MaxRetries` - `SupportsNestedMetadataFilters SupportsNestedMetadataFilters` - `trueTrue` - `class CloudAzureAISearchVectorStore:` Cloud Azure AI Search Vector Store. - `required string SearchServiceApiKey` - `required string SearchServiceEndpoint` - `string ClassName` - `string? ClientID` - `string? ClientSecret` - `Long? EmbeddingDimension` - `IReadOnlyDictionary? FilterableMetadataFieldKeys` - `string? IndexName` - `string? SearchServiceApiVersion` - `SupportsNestedMetadataFilters SupportsNestedMetadataFilters` - `trueTrue` - `string? TenantID` - `class CloudMongoDBAtlasVectorSearch:` Cloud MongoDB Atlas Vector Store. This class is used to store the configuration for a MongoDB Atlas vector store, so that it can be created and used in LlamaCloud. Args: mongodb_uri (str): URI for connecting to MongoDB Atlas db_name (str): name of the MongoDB database collection_name (str): name of the MongoDB collection vector_index_name (str): name of the MongoDB Atlas vector index fulltext_index_name (str): name of the MongoDB Atlas full-text index - `required string CollectionName` - `required string DBName` - `required string MongoDBUri` - `string ClassName` - `Long? EmbeddingDimension` - `string? FulltextIndexName` - `Boolean SupportsNestedMetadataFilters` - `string? VectorIndexName` - `class CloudMilvusVectorStore:` Cloud Milvus Vector Store. - `required string Uri` - `string? Token` - `string ClassName` - `string? CollectionName` - `Long? EmbeddingDimension` - `Boolean SupportsNestedMetadataFilters` - `class CloudAstraDBVectorStore:` Cloud AstraDB Vector Store. This class is used to store the configuration for an AstraDB vector store, so that it can be created and used in LlamaCloud. Args: token (str): The Astra DB Application Token to use. api_endpoint (str): The Astra DB JSON API endpoint for your database. collection_name (str): Collection name to use. If not existing, it will be created. embedding_dimension (int): Length of the embedding vectors in use. keyspace (optional[str]): The keyspace to use. If not provided, 'default_keyspace' - `required string Token` The Astra DB Application Token to use - `required string ApiEndpoint` The Astra DB JSON API endpoint for your database - `required string CollectionName` Collection name to use. If not existing, it will be created - `required Long EmbeddingDimension` Length of the embedding vectors in use - `string ClassName` - `string? Keyspace` The keyspace to use. If not provided, 'default_keyspace' - `SupportsNestedMetadataFilters SupportsNestedMetadataFilters` - `trueTrue` - `required string Name` The name of the data sink. - `required string ProjectID` - `required SinkType SinkType` - `"ASTRA_DB"AstraDB` - `"AZUREAI_SEARCH"AzureaiSearch` - `"MILVUS"Milvus` - `"MONGODB_ATLAS"MongoDBAtlas` - `"PINECONE"Pinecone` - `"POSTGRES"Postgres` - `"QDRANT"Qdrant` - `DateTimeOffset? CreatedAt` Creation datetime - `DateTimeOffset? UpdatedAt` Update datetime - `EmbeddingModelConfig? EmbeddingModelConfig` Schema for an embedding model config. - `required string ID` Unique identifier - `required EmbeddingConfig EmbeddingConfig` The embedding configuration for the embedding model config. - `class AzureOpenAIEmbeddingConfig:` - `class BedrockEmbeddingConfig:` - `class CohereEmbeddingConfig:` - `class GeminiEmbeddingConfig:` - `class HuggingFaceInferenceApiEmbeddingConfig:` - `class OpenAIEmbeddingConfig:` - `class VertexAIEmbeddingConfig:` - `required string Name` The name of the embedding model config. - `required string ProjectID` - `DateTimeOffset? CreatedAt` Creation datetime - `DateTimeOffset? UpdatedAt` Update datetime - `string? EmbeddingModelConfigID` The ID of the EmbeddingModelConfig this pipeline is using. - `LlamaParseParameters? LlamaParseParameters` Settings that can be configured for how to use LlamaParse to parse files within a LlamaCloud pipeline. - `Boolean? AdaptiveLongTable` - `Boolean? AggressiveTableExtraction` - `Boolean? AnnotateLinks` - `Boolean? AutoMode` - `string? AutoModeConfigurationJson` - `Boolean? AutoModeTriggerOnImageInPage` - `string? AutoModeTriggerOnRegexpInPage` - `Boolean? AutoModeTriggerOnTableInPage` - `string? AutoModeTriggerOnTextInPage` - `string? AzureOpenAIApiVersion` - `string? AzureOpenAIDeploymentName` - `string? AzureOpenAIEndpoint` - `string? AzureOpenAIKey` - `Double? BboxBottom` - `Double? BboxLeft` - `Double? BboxRight` - `Double? BboxTop` - `string? BoundingBox` - `Boolean? CompactMarkdownTable` - `string? ComplementalFormattingInstruction` - `string? ConfidenceScoreEffort` - `string? ContentGuidelineInstruction` - `Boolean? ContinuousMode` - `Boolean? DisableImageExtraction` - `Boolean? DisableOcr` - `Boolean? DisableReconstruction` - `Boolean? DoNotCache` - `Boolean? DoNotUnrollColumns` - `Boolean? EnableCostOptimizer` - `Boolean? ExtractCharts` - `Boolean? ExtractLayout` - `Boolean? ExtractPrintedPageNumber` - `Boolean? FastMode` - `string? FormattingInstruction` - `string? Gpt4oApiKey` - `Boolean? Gpt4oMode` - `Boolean? GuessXlsxSheetName` - `Boolean? HideFooters` - `Boolean? HideHeaders` - `Boolean? HighResOcr` - `Boolean? HtmlMakeAllElementsVisible` - `Boolean? HtmlRemoveFixedElements` - `Boolean? HtmlRemoveNavigationElements` - `string? HttpProxy` - `Boolean? IgnoreDocumentElementsForLayoutDetection` - `IReadOnlyList? ImagesToSave` - `"embedded"Embedded` - `"layout"Layout` - `"screenshot"Screenshot` - `Boolean? InlineImagesInMarkdown` - `string? InputS3Path` - `string? InputS3Region` - `string? InputUrl` - `Boolean? InternalIsScreenshotJob` - `Boolean? InvalidateCache` - `Boolean? IsFormattingInstruction` - `Double? JobTimeoutExtraTimePerPageInSeconds` - `Double? JobTimeoutInSeconds` - `Boolean? KeepPageSeparatorWhenMergingTables` - `IReadOnlyList Languages` - `"abq"Abq` - `"ady"Ady` - `"af"Af` - `"ang"Ang` - `"ar"Ar` - `"as"As` - `"ava"Ava` - `"az"Az` - `"be"Be` - `"bg"Bg` - `"bgc"Bgc` - `"bh"Bh` - `"bho"Bho` - `"bn"Bn` - `"bs"Bs` - `"ch_sim"ChSim` - `"ch_tra"ChTra` - `"che"Che` - `"cs"Cs` - `"cy"Cy` - `"da"Da` - `"dar"Dar` - `"de"De` - `"en"En` - `"es"Es` - `"et"Et` - `"fa"Fa` - `"fr"Fr` - `"ga"Ga` - `"gom"Gom` - `"hi"Hi` - `"hr"Hr` - `"hu"Hu` - `"id"ID` - `"inh"Inh` - `"is"Is` - `"it"It` - `"ja"Ja` - `"kbd"Kbd` - `"kn"Kn` - `"ko"Ko` - `"ku"Ku` - `"la"La` - `"lbe"Lbe` - `"lez"Lez` - `"lt"Lt` - `"lv"Lv` - `"mah"Mah` - `"mai"Mai` - `"mi"Mi` - `"mn"Mn` - `"mni"Mni` - `"mr"Mr` - `"ms"Ms` - `"mt"Mt` - `"ne"Ne` - `"new"New` - `"nl"Nl` - `"no"No` - `"oc"Oc` - `"pi"Pi` - `"pl"Pl` - `"pt"Pt` - `"ro"Ro` - `"rs_cyrillic"RsCyrillic` - `"rs_latin"RsLatin` - `"ru"Ru` - `"sa"Sa` - `"sck"Sck` - `"sk"Sk` - `"sl"Sl` - `"sq"Sq` - `"sv"Sv` - `"sw"Sw` - `"ta"Ta` - `"tab"Tab` - `"te"Te` - `"th"Th` - `"tjk"Tjk` - `"tl"Tl` - `"tr"Tr` - `"ug"Ug` - `"uk"Uk` - `"ur"Ur` - `"uz"Uz` - `"vi"Vi` - `Boolean? LayoutAware` - `Boolean? LineLevelBoundingBox` - `string? MarkdownTableMultilineHeaderSeparator` - `Long? MaxPages` - `Long? MaxPagesEnforced` - `Boolean? MergeTablesAcrossPagesInMarkdown` - `string? Model` - `Boolean? OutlinedTableExtraction` - `Boolean? OutputPdfOfDocument` - `string? OutputS3PathPrefix` - `string? OutputS3Region` - `Boolean? OutputTablesAsHtml` - `Double? PageErrorTolerance` - `string? PageFooterPrefix` - `string? PageFooterSuffix` - `string? PageHeaderPrefix` - `string? PageHeaderSuffix` - `string? PagePrefix` - `string? PageSeparator` - `string? PageSuffix` - `ParsingMode? ParseMode` Enum for representing the mode of parsing to be used. - `"parse_document_with_agent"ParseDocumentWithAgent` - `"parse_document_with_llm"ParseDocumentWithLlm` - `"parse_document_with_lvm"ParseDocumentWithLvm` - `"parse_page_with_agent"ParsePageWithAgent` - `"parse_page_with_layout_agent"ParsePageWithLayoutAgent` - `"parse_page_with_llm"ParsePageWithLlm` - `"parse_page_with_lvm"ParsePageWithLvm` - `"parse_page_without_llm"ParsePageWithoutLlm` - `string? ParsingInstruction` - `Boolean? PreciseBoundingBox` - `Boolean? PremiumMode` - `Boolean? PresentationOutOfBoundsContent` - `Boolean? PresentationSkipEmbeddedData` - `Boolean? PreserveLayoutAlignmentAcrossPages` - `Boolean? PreserveVerySmallText` - `string? Preset` - `Priority? Priority` The priority for the request. This field may be ignored or overwritten depending on the organization tier. - `"critical"Critical` - `"high"High` - `"low"Low` - `"medium"Medium` - `string? ProjectID` - `Boolean? RemoveHiddenText` - `FailPageMode? ReplaceFailedPageMode` Enum for representing the different available page error handling modes. - `"blank_page"BlankPage` - `"error_message"ErrorMessage` - `"raw_text"RawText` - `string? ReplaceFailedPageWithErrorMessagePrefix` - `string? ReplaceFailedPageWithErrorMessageSuffix` - `Boolean? SaveImages` - `Boolean? SkipDiagonalText` - `Boolean? SpecializedChartParsingAgentic` - `Boolean? SpecializedChartParsingEfficient` - `Boolean? SpecializedChartParsingPlus` - `Boolean? SpecializedImageParsing` - `Boolean? SpreadsheetExtractSubTables` - `Boolean? SpreadsheetForceFormulaComputation` - `Boolean? SpreadsheetIncludeHiddenSheets` - `Boolean? StrictModeBuggyFont` - `Boolean? StrictModeImageExtraction` - `Boolean? StrictModeImageOcr` - `Boolean? StrictModeReconstruction` - `Boolean? StructuredOutput` - `string? StructuredOutputJsonSchema` - `string? StructuredOutputJsonSchemaName` - `string? SystemPrompt` - `string? SystemPromptAppend` - `Boolean? TakeScreenshot` - `string? TargetPages` - `string? Tier` - `Boolean? UseVendorMultimodalModel` - `string? UserPrompt` - `string? VendorMultimodalApiKey` - `string? VendorMultimodalModelName` - `string? Version` - `IReadOnlyList? WebhookConfigurations` Outbound webhook endpoints to notify on job status changes - `IReadOnlyList? WebhookEvents` Events to subscribe to (e.g. 'parse.success', 'extract.error'). If null, all events are delivered. - `"classify.cancelled"ClassifyCancelled` - `"classify.error"ClassifyError` - `"classify.partial_success"ClassifyPartialSuccess` - `"classify.pending"ClassifyPending` - `"classify.running"ClassifyRunning` - `"classify.success"ClassifySuccess` - `"extract.cancelled"ExtractCancelled` - `"extract.error"ExtractError` - `"extract.partial_success"ExtractPartialSuccess` - `"extract.pending"ExtractPending` - `"extract.success"ExtractSuccess` - `"parse.cancelled"ParseCancelled` - `"parse.error"ParseError` - `"parse.partial_success"ParsePartialSuccess` - `"parse.pending"ParsePending` - `"parse.running"ParseRunning` - `"parse.success"ParseSuccess` - `"sheets.cancelled"SheetsCancelled` - `"sheets.error"SheetsError` - `"sheets.partial_success"SheetsPartialSuccess` - `"sheets.pending"SheetsPending` - `"sheets.success"SheetsSuccess` - `"split.cancelled"SplitCancelled` - `"split.error"SplitError` - `"split.pending"SplitPending` - `"split.processing"SplitProcessing` - `"split.success"SplitSuccess` - `"unmapped_event"UnmappedEvent` - `IReadOnlyDictionary? WebhookHeaders` Custom HTTP headers sent with each webhook request (e.g. auth tokens) - `string? WebhookOutputFormat` Response format sent to the webhook: 'string' (default) or 'json' - `string? WebhookSigningSecret` Shared signing secret used to sign webhook deliveries. When set, each request includes an HMAC-SHA256 signature of the request body in the 'LC-Signature' header (value 'sha256='). Recompute the HMAC over the raw request body with this secret to verify the delivery is authentic. - `string? WebhookUrl` URL to receive webhook POST notifications - `string? WebhookUrl` - `string? ManagedPipelineID` The ID of the ManagedPipeline this playground pipeline is linked to. - `PipelineMetadataConfig? MetadataConfig` Metadata configuration for the pipeline. - `IReadOnlyList ExcludedEmbedMetadataKeys` List of metadata keys to exclude from embeddings - `IReadOnlyList ExcludedLlmMetadataKeys` List of metadata keys to exclude from LLM during retrieval - `PipelineType PipelineType` Type of pipeline. Either PLAYGROUND or MANAGED. - `"MANAGED"Managed` - `"PLAYGROUND"Playground` - `PresetRetrievalParams PresetRetrievalParameters` Preset retrieval parameters for the pipeline. - `Double? Alpha` Alpha value for hybrid retrieval to determine the weights between dense and sparse retrieval. 0 is sparse retrieval and 1 is dense retrieval. - `string ClassName` - `Double? DenseSimilarityCutoff` Minimum similarity score wrt query for retrieval - `Long? DenseSimilarityTopK` Number of nodes for dense retrieval. - `Boolean? EnableReranking` Enable reranking for retrieval - `Long? FilesTopK` Number of files to retrieve (only for retrieval mode files_via_metadata and files_via_content). - `Long? RerankTopN` Number of reranked nodes for returning. - `RetrievalMode RetrievalMode` The retrieval mode for the query. - `"auto_routed"AutoRouted` - `"chunks"Chunks` - `"files_via_content"FilesViaContent` - `"files_via_metadata"FilesViaMetadata` - `Boolean RetrieveImageNodes` Whether to retrieve image nodes. - `Boolean RetrievePageFigureNodes` Whether to retrieve page figure nodes. - `Boolean RetrievePageScreenshotNodes` Whether to retrieve page screenshot nodes. - `MetadataFilters? SearchFilters` Metadata filters for vector stores. - `required IReadOnlyList Filters` - `class MetadataFilter:` Comprehensive metadata filter for vector stores to support more operators. Value uses Strict types, as int, float and str are compatible types and were all converted to string before. See: https://docs.pydantic.dev/latest/usage/types/#strict-types - `required string Key` - `required Value? Value` - `Double` - `string` - `IReadOnlyList` - `IReadOnlyList` - `IReadOnlyList` - `Operator Operator` Vector store filter operator. - `"!="` - `"<"` - `"<="` - `"=="` - `">"` - `">="` - `"all"All` - `"any"Any` - `"contains"Contains` - `"in"In` - `"is_empty"IsEmpty` - `"nin"Nin` - `"text_match"TextMatch` - `"text_match_insensitive"TextMatchInsensitive` - `class MetadataFilters:` Metadata filters for vector stores. - `Condition? Condition` Vector store filter conditions to combine different filters. - `"and"And` - `"not"Not` - `"or"Or` - `IReadOnlyDictionary? SearchFiltersInferenceSchema` JSON Schema that will be used to infer search_filters. Omit or leave as null to skip inference. - `IReadOnlyDictionary` - `IReadOnlyList` - `string` - `Double` - `Boolean` - `Long? SparseSimilarityTopK` Number of nodes for sparse retrieval. - `SparseModelConfig? SparseModelConfig` Configuration for sparse embedding models used in hybrid search. This allows users to choose between Splade and BM25 models for sparse retrieval in managed data sinks. - `string ClassName` - `ModelType ModelType` The sparse model type to use. 'bm25' uses Qdrant's FastEmbed BM25 model (default for new pipelines), 'splade' uses HuggingFace Splade model, 'auto' selects based on deployment mode (BYOC uses term frequency, Cloud uses Splade). - `"auto"Auto` - `"bm25"Bm25` - `"splade"Splade` - `Status? Status` Status of the pipeline. - `"CREATED"Created` - `"DELETING"Deleting` - `TransformConfig TransformConfig` Configuration for the transformation. - `class AutoTransformConfig:` - `Long ChunkOverlap` Chunk overlap for the transformation. - `Long ChunkSize` Chunk size for the transformation. - `Mode Mode` - `"auto"Auto` - `class AdvancedModeTransformConfig:` - `ChunkingConfig ChunkingConfig` Configuration for the chunking. - `class NoneChunkingConfig:` - `Mode Mode` - `"none"None` - `class CharacterChunkingConfig:` - `Long ChunkOverlap` - `Long ChunkSize` - `Mode Mode` - `"character"Character` - `class TokenChunkingConfig:` - `Long ChunkOverlap` - `Long ChunkSize` - `Mode Mode` - `"token"Token` - `string Separator` - `class SentenceChunkingConfig:` - `Long ChunkOverlap` - `Long ChunkSize` - `Mode Mode` - `"sentence"Sentence` - `string ParagraphSeparator` - `string Separator` - `class SemanticChunkingConfig:` - `Long BreakpointPercentileThreshold` - `Long BufferSize` - `Mode Mode` - `"semantic"Semantic` - `Mode Mode` - `"advanced"Advanced` - `SegmentationConfig SegmentationConfig` Configuration for the segmentation. - `class NoneSegmentationConfig:` - `Mode Mode` - `"none"None` - `class PageSegmentationConfig:` - `Mode Mode` - `"page"Page` - `string PageSeparator` - `class ElementSegmentationConfig:` - `Mode Mode` - `"element"Element` - `DateTimeOffset? UpdatedAt` Update datetime ### Example ```csharp SyncCancelParams parameters = new() { PipelineID = "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e" }; var pipeline = await client.Pipelines.Sync.Cancel(parameters); Console.WriteLine(pipeline); ``` #### Response ```json { "id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "embedding_config": { "component": { "additional_kwargs": { "foo": "bar" }, "api_base": "api_base", "api_key": "api_key", "api_version": "api_version", "azure_deployment": "azure_deployment", "azure_endpoint": "azure_endpoint", "class_name": "class_name", "default_headers": { "foo": "string" }, "dimensions": 0, "embed_batch_size": 1, "max_retries": 0, "model_name": "model_name", "num_workers": 0, "reuse_client": true, "timeout": 0 }, "type": "AZURE_EMBEDDING" }, "name": "name", "project_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "config_hash": { "embedding_config_hash": "embedding_config_hash", "parsing_config_hash": "parsing_config_hash", "transform_config_hash": "transform_config_hash" }, "created_at": "2019-12-27T18:11:19.117Z", "data_sink": { "id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "component": { "foo": "bar" }, "name": "name", "project_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "sink_type": "ASTRA_DB", "created_at": "2019-12-27T18:11:19.117Z", "updated_at": "2019-12-27T18:11:19.117Z" }, "embedding_model_config": { "id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "embedding_config": { "component": { "additional_kwargs": { "foo": "bar" }, "api_base": "api_base", "api_key": "api_key", "api_version": "api_version", "azure_deployment": "azure_deployment", "azure_endpoint": "azure_endpoint", "class_name": "class_name", "default_headers": { "foo": "string" }, "dimensions": 0, "embed_batch_size": 1, "max_retries": 0, "model_name": "model_name", "num_workers": 0, "reuse_client": true, "timeout": 0 }, "type": "AZURE_EMBEDDING" }, "name": "name", "project_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "created_at": "2019-12-27T18:11:19.117Z", "updated_at": "2019-12-27T18:11:19.117Z" }, "embedding_model_config_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "llama_parse_parameters": { "adaptive_long_table": true, "aggressive_table_extraction": true, "annotate_links": true, "auto_mode": true, "auto_mode_configuration_json": "auto_mode_configuration_json", "auto_mode_trigger_on_image_in_page": true, "auto_mode_trigger_on_regexp_in_page": "auto_mode_trigger_on_regexp_in_page", "auto_mode_trigger_on_table_in_page": true, "auto_mode_trigger_on_text_in_page": "auto_mode_trigger_on_text_in_page", "azure_openai_api_version": "azure_openai_api_version", "azure_openai_deployment_name": "azure_openai_deployment_name", "azure_openai_endpoint": "azure_openai_endpoint", "azure_openai_key": "azure_openai_key", "bbox_bottom": 0, "bbox_left": 0, "bbox_right": 0, "bbox_top": 0, "bounding_box": "bounding_box", "compact_markdown_table": true, "complemental_formatting_instruction": "complemental_formatting_instruction", "confidence_score_effort": "confidence_score_effort", "content_guideline_instruction": "content_guideline_instruction", "continuous_mode": true, "disable_image_extraction": true, "disable_ocr": true, "disable_reconstruction": true, "do_not_cache": true, "do_not_unroll_columns": true, "enable_cost_optimizer": true, "extract_charts": true, "extract_layout": true, "extract_printed_page_number": true, "fast_mode": true, "formatting_instruction": "formatting_instruction", "gpt4o_api_key": "gpt4o_api_key", "gpt4o_mode": true, "guess_xlsx_sheet_name": true, "hide_footers": true, "hide_headers": true, "high_res_ocr": true, "html_make_all_elements_visible": true, "html_remove_fixed_elements": true, "html_remove_navigation_elements": true, "http_proxy": "http_proxy", "ignore_document_elements_for_layout_detection": true, "images_to_save": [ "embedded" ], "inline_images_in_markdown": true, "input_s3_path": "input_s3_path", "input_s3_region": "input_s3_region", "input_url": "input_url", "internal_is_screenshot_job": true, "invalidate_cache": true, "is_formatting_instruction": true, "job_timeout_extra_time_per_page_in_seconds": 0, "job_timeout_in_seconds": 0, "keep_page_separator_when_merging_tables": true, "languages": [ "abq" ], "layout_aware": true, "line_level_bounding_box": true, "markdown_table_multiline_header_separator": "markdown_table_multiline_header_separator", "max_pages": 0, "max_pages_enforced": 0, "merge_tables_across_pages_in_markdown": true, "model": "model", "outlined_table_extraction": true, "output_pdf_of_document": true, "output_s3_path_prefix": "output_s3_path_prefix", "output_s3_region": "output_s3_region", "output_tables_as_HTML": true, "page_error_tolerance": 0, "page_footer_prefix": "page_footer_prefix", "page_footer_suffix": "page_footer_suffix", "page_header_prefix": "page_header_prefix", "page_header_suffix": "page_header_suffix", "page_prefix": "page_prefix", "page_separator": "page_separator", "page_suffix": "page_suffix", "parse_mode": "parse_document_with_agent", "parsing_instruction": "parsing_instruction", "precise_bounding_box": true, "premium_mode": true, "presentation_out_of_bounds_content": true, "presentation_skip_embedded_data": true, "preserve_layout_alignment_across_pages": true, "preserve_very_small_text": true, "preset": "preset", "priority": "critical", "project_id": "project_id", "remove_hidden_text": true, "replace_failed_page_mode": "blank_page", "replace_failed_page_with_error_message_prefix": "replace_failed_page_with_error_message_prefix", "replace_failed_page_with_error_message_suffix": "replace_failed_page_with_error_message_suffix", "save_images": true, "skip_diagonal_text": true, "specialized_chart_parsing_agentic": true, "specialized_chart_parsing_efficient": true, "specialized_chart_parsing_plus": true, "specialized_image_parsing": true, "spreadsheet_extract_sub_tables": true, "spreadsheet_force_formula_computation": true, "spreadsheet_include_hidden_sheets": true, "strict_mode_buggy_font": true, "strict_mode_image_extraction": true, "strict_mode_image_ocr": true, "strict_mode_reconstruction": true, "structured_output": true, "structured_output_json_schema": "structured_output_json_schema", "structured_output_json_schema_name": "structured_output_json_schema_name", "system_prompt": "system_prompt", "system_prompt_append": "system_prompt_append", "take_screenshot": true, "target_pages": "target_pages", "tier": "tier", "use_vendor_multimodal_model": true, "user_prompt": "user_prompt", "vendor_multimodal_api_key": "vendor_multimodal_api_key", "vendor_multimodal_model_name": "vendor_multimodal_model_name", "version": "version", "webhook_configurations": [ { "webhook_events": [ "parse.success", "parse.error" ], "webhook_headers": { "Authorization": "Bearer sk-..." }, "webhook_output_format": "json", "webhook_signing_secret": "whsec_...", "webhook_url": "https://example.com/webhooks/llamacloud" } ], "webhook_url": "webhook_url" }, "managed_pipeline_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "metadata_config": { "excluded_embed_metadata_keys": [ "string" ], "excluded_llm_metadata_keys": [ "string" ] }, "pipeline_type": "MANAGED", "preset_retrieval_parameters": { "alpha": 0, "class_name": "class_name", "dense_similarity_cutoff": 0, "dense_similarity_top_k": 1, "enable_reranking": true, "files_top_k": 1, "rerank_top_n": 1, "retrieval_mode": "auto_routed", "retrieve_image_nodes": true, "retrieve_page_figure_nodes": true, "retrieve_page_screenshot_nodes": true, "search_filters": { "filters": [ { "key": "key", "value": 0, "operator": "!=" } ], "condition": "and" }, "search_filters_inference_schema": { "foo": { "foo": "bar" } }, "sparse_similarity_top_k": 1 }, "sparse_model_config": { "class_name": "class_name", "model_type": "auto" }, "status": "CREATED", "transform_config": { "chunk_overlap": 0, "chunk_size": 1, "mode": "auto" }, "updated_at": "2019-12-27T18:11:19.117Z" } ``` # Data Sources ## List Pipeline Data Sources `IReadOnlyList Pipelines.DataSources.GetDataSources(DataSourceGetDataSourcesParamsparameters, CancellationTokencancellationToken = default)` **get** `/api/v1/pipelines/{pipeline_id}/data-sources` Get data sources for a pipeline. ### Parameters - `DataSourceGetDataSourcesParams parameters` - `required string pipelineID` ### Example ```csharp DataSourceGetDataSourcesParams parameters = new() { PipelineID = "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e" }; var pipelineDataSources = await client.Pipelines.DataSources.GetDataSources(parameters); Console.WriteLine(pipelineDataSources); ``` #### Response ```json [ { "id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "component": { "foo": "bar" }, "data_source_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "last_synced_at": "2019-12-27T18:11:19.117Z", "name": "name", "pipeline_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "project_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "source_type": "AZURE_STORAGE_BLOB", "created_at": "2019-12-27T18:11:19.117Z", "custom_metadata": { "foo": { "foo": "bar" } }, "status": "CANCELLED", "status_updated_at": "2019-12-27T18:11:19.117Z", "sync_interval": 0, "sync_schedule_set_by": "sync_schedule_set_by", "updated_at": "2019-12-27T18:11:19.117Z", "version_metadata": { "reader_version": "1.0" } } ] ``` ## Add Data Sources To Pipeline `IReadOnlyList Pipelines.DataSources.UpdateDataSources(DataSourceUpdateDataSourcesParamsparameters, CancellationTokencancellationToken = default)` **put** `/api/v1/pipelines/{pipeline_id}/data-sources` Add data sources to a pipeline. ### Parameters - `DataSourceUpdateDataSourcesParams parameters` - `required string pipelineID` - `required IReadOnlyList body` - `required string DataSourceID` The ID of the data source. - `Double? SyncInterval` The interval at which the data source should be synced. Valid values are: 21600, 43200, 86400 ### Example ```csharp DataSourceUpdateDataSourcesParams parameters = new() { PipelineID = "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", Body = [ new() { DataSourceID = "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", SyncInterval = 0, }, ], }; var pipelineDataSources = await client.Pipelines.DataSources.UpdateDataSources(parameters); Console.WriteLine(pipelineDataSources); ``` #### Response ```json [ { "id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "component": { "foo": "bar" }, "data_source_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "last_synced_at": "2019-12-27T18:11:19.117Z", "name": "name", "pipeline_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "project_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "source_type": "AZURE_STORAGE_BLOB", "created_at": "2019-12-27T18:11:19.117Z", "custom_metadata": { "foo": { "foo": "bar" } }, "status": "CANCELLED", "status_updated_at": "2019-12-27T18:11:19.117Z", "sync_interval": 0, "sync_schedule_set_by": "sync_schedule_set_by", "updated_at": "2019-12-27T18:11:19.117Z", "version_metadata": { "reader_version": "1.0" } } ] ``` ## Update Pipeline Data Source `PipelineDataSource Pipelines.DataSources.Update(DataSourceUpdateParamsparameters, CancellationTokencancellationToken = default)` **put** `/api/v1/pipelines/{pipeline_id}/data-sources/{data_source_id}` Update the configuration of a data source in a pipeline. ### Parameters - `DataSourceUpdateParams parameters` - `required string pipelineID` Path param - `required string dataSourceID` Path param - `Double? syncInterval` Body param: The interval at which the data source should be synced. ### Returns - `class PipelineDataSource:` Schema for a data source in a pipeline. - `required string ID` Unique identifier - `required Component Component` Component that implements the data source - `IReadOnlyDictionary` - `class CloudS3DataSource:` - `required string Bucket` The name of the S3 bucket to read from. - `string? AwsAccessID` The AWS access ID to use for authentication. - `string? AwsAccessSecret` The AWS access secret to use for authentication. - `string ClassName` - `string? Prefix` The prefix of the S3 objects to read from. - `string? RegexPattern` The regex pattern to filter S3 objects. Must be a valid regex pattern. - `string? S3EndpointUrl` The S3 endpoint URL to use for authentication. - `Boolean SupportsAccessControl` - `class CloudAzStorageBlobDataSource:` - `required string AccountUrl` The Azure Storage Blob account URL to use for authentication. - `required string ContainerName` The name of the Azure Storage Blob container to read from. - `string? AccountKey` The Azure Storage Blob account key to use for authentication. - `string? AccountName` The Azure Storage Blob account name to use for authentication. - `string? Blob` The blob name to read from. - `string ClassName` - `string? ClientID` The Azure AD client ID to use for authentication. - `string? ClientSecret` The Azure AD client secret to use for authentication. - `string? Prefix` The prefix of the Azure Storage Blob objects to read from. - `Boolean SupportsAccessControl` - `string? TenantID` The Azure AD tenant ID to use for authentication. - `class CloudGoogleDriveDataSource:` - `required string FolderID` The ID of the Google Drive folder to read from. - `string ClassName` - `string? FolderName` Human-readable name of the selected folder, for display. - `IReadOnlyDictionary? ServiceAccountKey` A dictionary containing secret values - `Boolean SupportsAccessControl` - `class CloudOneDriveDataSource:` - `required string ClientID` The client ID to use for authentication. - `required string ClientSecret` The client secret to use for authentication. - `required string TenantID` The tenant ID to use for authentication. - `required string UserPrincipalName` The user principal name to use for authentication. - `string ClassName` - `string? FolderID` The ID of the OneDrive folder to read from. - `string? FolderPath` The path of the OneDrive folder to read from. - `IReadOnlyList? RequiredExts` The list of required file extensions. - `SupportsAccessControl SupportsAccessControl` - `trueTrue` - `class CloudSharepointDataSource:` - `required string ClientID` The client ID to use for authentication. - `required string ClientSecret` The client secret to use for authentication. - `required string TenantID` The tenant ID to use for authentication. - `string ClassName` - `string? DriveName` The name of the Sharepoint drive to read from. - `IReadOnlyList? ExcludePathPatterns` List of regex patterns for file paths to exclude. Files whose paths (including filename) match any pattern will be excluded. Example: ['/temp/', '/backup/', '.git/', '.tmp$', '^~'] - `string? FolderID` The ID of the Sharepoint folder to read from. - `string? FolderPath` The path of the Sharepoint folder to read from. - `Boolean GetPermissions` Whether to get permissions for the sharepoint site. - `IReadOnlyList? IncludePathPatterns` List of regex patterns for file paths to include. Full paths (including filename) must match at least one pattern to be included. Example: ['/reports/', '/docs/.*.pdf$', '^Report.*.pdf$'] - `IReadOnlyList? RequiredExts` The list of required file extensions. - `string? SiteID` The ID of the SharePoint site to download from. - `string? SiteName` The name of the SharePoint site to download from. - `SupportsAccessControl SupportsAccessControl` - `trueTrue` - `class CloudSlackDataSource:` - `required string SlackToken` Slack Bot Token. - `string? ChannelIds` Slack Channel. - `string? ChannelPatterns` Slack Channel name pattern. - `string ClassName` - `string? EarliestDate` Earliest date. - `Double? EarliestDateTimestamp` Earliest date timestamp. - `string? LatestDate` Latest date. - `Double? LatestDateTimestamp` Latest date timestamp. - `Boolean SupportsAccessControl` - `class CloudNotionPageDataSource:` - `required string IntegrationToken` The integration token to use for authentication. - `string ClassName` - `string? DatabaseIds` The Notion Database Id to read content from. - `string? PageIds` The Page ID's of the Notion to read from. - `Boolean SupportsAccessControl` - `class CloudConfluenceDataSource:` - `required string AuthenticationMechanism` Type of Authentication for connecting to Confluence APIs. - `required string ServerUrl` The server URL of the Confluence instance. - `string? ApiToken` The API token to use for authentication. - `string ClassName` - `string? Cql` The CQL query to use for fetching pages. - `FailureHandlingConfig FailureHandling` Configuration for handling failures during processing. Key-value object controlling failure handling behaviors. Example: { "skip_list_failures": true } Currently supports: - skip_list_failures: Skip failed batches/lists and continue processing - `Boolean SkipListFailures` Whether to skip failed batches/lists and continue processing - `Boolean IndexRestrictedPages` Whether to index restricted pages. - `Boolean KeepMarkdownFormat` Whether to keep the markdown format. - `string? Label` The label to use for fetching pages. - `string? PageIds` The page IDs of the Confluence to read from. - `string? SpaceKey` The space key to read from. - `Boolean SupportsAccessControl` - `Boolean SyncPermissions` Whether to fetch space-level permissions (allowed users/groups) and attach them to document metadata for access control. Disable for Confluence Server/Data Center versions whose permission APIs are unavailable (e.g. the JSON-RPC API removed in Data Center 9.2.6+), which otherwise surface as 401 errors during sync. - `string? UserName` The username to use for authentication. - `class CloudJiraDataSource:` Cloud Jira Data Source integrating JiraReader. - `required string AuthenticationMechanism` Type of Authentication for connecting to Jira APIs. - `required string Query` JQL (Jira Query Language) query to search. - `string? ApiToken` The API/ Access Token used for Basic, PAT and OAuth2 authentication. - `string ClassName` - `string? CloudID` The cloud ID, used in case of OAuth2. - `string? Email` The email address to use for authentication. - `string? ServerUrl` The server url for Jira Cloud. - `Boolean SupportsAccessControl` - `class CloudJiraDataSourceV2:` Cloud Jira Data Source integrating JiraReaderV2. - `required string AuthenticationMechanism` Type of Authentication for connecting to Jira APIs. - `required string Query` JQL (Jira Query Language) query to search. - `required string ServerUrl` The server url for Jira Cloud. - `string? ApiToken` The API Access Token used for Basic, PAT and OAuth2 authentication. - `ApiVersion ApiVersion` Jira REST API version to use (2 or 3). 3 supports Atlassian Document Format (ADF). - `"2"2` - `"3"3` - `string ClassName` - `string? CloudID` The cloud ID, used in case of OAuth2. - `string? Email` The email address to use for authentication. - `string? Expand` Fields to expand in the response. - `IReadOnlyList? Fields` List of fields to retrieve from Jira. If None, retrieves all fields. - `Boolean GetPermissions` Whether to fetch project role permissions and issue-level security - `Long? RequestsPerMinute` Rate limit for Jira API requests per minute. - `Boolean SupportsAccessControl` - `class CloudBoxDataSource:` - `required AuthenticationMechanism AuthenticationMechanism` The type of authentication to use (Developer Token or CCG) - `"ccg"Ccg` - `"developer_token"DeveloperToken` - `string ClassName` - `string? ClientID` Box API key used for identifying the application the user is authenticating with - `string? ClientSecret` Box API secret used for making auth requests. - `string? DeveloperToken` Developer token for authentication if authentication_mechanism is 'developer_token'. - `string? EnterpriseID` Box Enterprise ID, if provided authenticates as service. - `string? FolderID` The ID of the Box folder to read from. - `Boolean SupportsAccessControl` - `string? UserID` Box User ID, if provided authenticates as user. - `required string DataSourceID` The ID of the data source. - `required DateTimeOffset LastSyncedAt` The last time the data source was automatically synced. - `required string Name` The name of the data source. - `required string PipelineID` The ID of the pipeline. - `required string ProjectID` - `required SourceType SourceType` - `"AZURE_STORAGE_BLOB"AzureStorageBlob` - `"BOX"Box` - `"CONFLUENCE"Confluence` - `"GOOGLE_DRIVE"GoogleDrive` - `"JIRA"Jira` - `"JIRA_V2"JiraV2` - `"MICROSOFT_ONEDRIVE"MicrosoftOnedrive` - `"MICROSOFT_SHAREPOINT"MicrosoftSharepoint` - `"NOTION_PAGE"NotionPage` - `"S3"S3` - `"SLACK"Slack` - `DateTimeOffset? CreatedAt` Creation datetime - `IReadOnlyDictionary? CustomMetadata` Custom metadata that will be present on all data loaded from the data source - `IReadOnlyDictionary` - `IReadOnlyList` - `string` - `Double` - `Boolean` - `Status? Status` The status of the data source in the pipeline. - `"CANCELLED"Cancelled` - `"ERROR"Error` - `"IN_PROGRESS"InProgress` - `"NOT_STARTED"NotStarted` - `"SUCCESS"Success` - `DateTimeOffset? StatusUpdatedAt` The last time the status was updated. - `Double? SyncInterval` The interval at which the data source should be synced. - `string? SyncScheduleSetBy` The id of the user who set the sync schedule. - `DateTimeOffset? UpdatedAt` Update datetime - `DataSourceReaderVersionMetadata? VersionMetadata` Version metadata for the data source - `ReaderVersion? ReaderVersion` The version of the reader to use for this data source. - `"1.0"1_0` - `"2.0"2_0` - `"2.1"2_1` ### Example ```csharp DataSourceUpdateParams parameters = new() { PipelineID = "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", DataSourceID = "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", }; var pipelineDataSource = await client.Pipelines.DataSources.Update(parameters); Console.WriteLine(pipelineDataSource); ``` #### Response ```json { "id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "component": { "foo": "bar" }, "data_source_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "last_synced_at": "2019-12-27T18:11:19.117Z", "name": "name", "pipeline_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "project_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "source_type": "AZURE_STORAGE_BLOB", "created_at": "2019-12-27T18:11:19.117Z", "custom_metadata": { "foo": { "foo": "bar" } }, "status": "CANCELLED", "status_updated_at": "2019-12-27T18:11:19.117Z", "sync_interval": 0, "sync_schedule_set_by": "sync_schedule_set_by", "updated_at": "2019-12-27T18:11:19.117Z", "version_metadata": { "reader_version": "1.0" } } ``` ## Get Pipeline Data Source Status `ManagedIngestionStatusResponse Pipelines.DataSources.GetStatus(DataSourceGetStatusParamsparameters, CancellationTokencancellationToken = default)` **get** `/api/v1/pipelines/{pipeline_id}/data-sources/{data_source_id}/status` Get the status of a data source for a pipeline. ### Parameters - `DataSourceGetStatusParams parameters` - `required string pipelineID` - `required string dataSourceID` ### Returns - `class ManagedIngestionStatusResponse:` - `required Status Status` Status of the ingestion. - `"CANCELLED"Cancelled` - `"ERROR"Error` - `"IN_PROGRESS"InProgress` - `"NOT_STARTED"NotStarted` - `"PARTIAL_SUCCESS"PartialSuccess` - `"SUCCESS"Success` - `DateTimeOffset? DeploymentDate` Date of the deployment. - `DateTimeOffset? EffectiveAt` When the status is effective - `IReadOnlyList? Error` List of errors that occurred during ingestion. - `required string JobID` ID of the job that failed. - `required string Message` List of errors that occurred during ingestion. - `required Step Step` Name of the job that failed. - `"DATA_SOURCE"DataSource` - `"FILE_UPDATER"FileUpdater` - `"INGESTION"Ingestion` - `"MANAGED_INGESTION"ManagedIngestion` - `"METADATA_UPDATE"MetadataUpdate` - `"PARSE"Parse` - `"TRANSFORM"Transform` - `string? JobID` ID of the latest job. ### Example ```csharp DataSourceGetStatusParams parameters = new() { PipelineID = "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", DataSourceID = "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", }; var managedIngestionStatusResponse = await client.Pipelines.DataSources.GetStatus(parameters); Console.WriteLine(managedIngestionStatusResponse); ``` #### Response ```json { "status": "CANCELLED", "deployment_date": "2019-12-27T18:11:19.117Z", "effective_at": "2019-12-27T18:11:19.117Z", "error": [ { "job_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "message": "message", "step": "DATA_SOURCE" } ], "job_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e" } ``` ## Sync Pipeline Data Source `Pipeline Pipelines.DataSources.Sync(DataSourceSyncParamsparameters, CancellationTokencancellationToken = default)` **post** `/api/v1/pipelines/{pipeline_id}/data-sources/{data_source_id}/sync` Run incremental ingestion: pull upstream changes from the data source into the data sink. ### Parameters - `DataSourceSyncParams parameters` - `required string pipelineID` Path param - `required string dataSourceID` Path param - `IReadOnlyList? pipelineFileIds` Body param ### Returns - `class Pipeline:` Schema for a pipeline. - `required string ID` Unique identifier - `required EmbeddingConfig EmbeddingConfig` - `class AzureOpenAIEmbeddingConfig:` - `AzureOpenAIEmbedding Component` Configuration for the Azure OpenAI embedding model. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the OpenAI API. - `string ApiBase` The base URL for Azure deployment. - `string? ApiKey` The OpenAI API key. - `string ApiVersion` The version for Azure OpenAI API. - `string? AzureDeployment` The Azure deployment to use. - `string? AzureEndpoint` The Azure endpoint to use. - `string ClassName` - `IReadOnlyDictionary? DefaultHeaders` The default headers for API requests. - `Long? Dimensions` The number of dimensions on the output embedding vectors. Works only with v3 embedding models. - `Long EmbedBatchSize` The batch size for embedding calls. - `Long MaxRetries` Maximum number of retries. - `string ModelName` The name of the OpenAI embedding model. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Boolean ReuseClient` Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability. - `Double Timeout` Timeout for each request. - `Type Type` Type of the embedding model. - `"AZURE_EMBEDDING"AzureEmbedding` - `class BedrockEmbeddingConfig:` - `BedrockEmbedding Component` Configuration for the Bedrock embedding model. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the bedrock client. - `string? AwsAccessKeyID` AWS Access Key ID to use - `string? AwsSecretAccessKey` AWS Secret Access Key to use - `string? AwsSessionToken` AWS Session Token to use - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `Long MaxRetries` The maximum number of API retries. - `string ModelName` The modelId of the Bedrock model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `string? ProfileName` The name of aws profile to use. If not given, then the default profile is used. - `string? RegionName` AWS region name to use. Uses region configured in AWS CLI if not passed - `Double Timeout` The timeout for the Bedrock API request in seconds. It will be used for both connect and read timeouts. - `Type Type` Type of the embedding model. - `"BEDROCK_EMBEDDING"BedrockEmbedding` - `class CohereEmbeddingConfig:` - `CohereEmbedding Component` Configuration for the Cohere embedding model. - `required string? ApiKey` The Cohere API key. - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `string EmbeddingType` Embedding type. If not provided float embedding_type is used when needed. - `string? InputType` Model Input type. If not provided, search_document and search_query are used when needed. - `string ModelName` The modelId of the Cohere model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `string Truncate` Truncation type - START/ END/ NONE - `Type Type` Type of the embedding model. - `"COHERE_EMBEDDING"CohereEmbedding` - `class GeminiEmbeddingConfig:` - `GeminiEmbedding Component` Configuration for the Gemini embedding model. - `string? ApiBase` API base to access the model. Defaults to None. - `string? ApiKey` API key to access the model. Defaults to None. - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `string ModelName` The modelId of the Gemini model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Long? OutputDimensionality` Optional reduced dimension for output embeddings. Supported by models/text-embedding-004 and newer (e.g. gemini-embedding-001). Not supported by models/embedding-001. - `string? TaskType` The task for embedding model. - `string? Title` Title is only applicable for retrieval_document tasks, and is used to represent a document title. For other tasks, title is invalid. - `string? Transport` Transport to access the model. Defaults to None. - `Type Type` Type of the embedding model. - `"GEMINI_EMBEDDING"GeminiEmbedding` - `class HuggingFaceInferenceApiEmbeddingConfig:` - `HuggingFaceInferenceApiEmbedding Component` Configuration for the HuggingFace Inference API embedding model. - `Token? Token` Hugging Face token. Will default to the locally saved token. Pass token=False if you don’t want to send your token to the server. - `string` - `Boolean` - `string ClassName` - `IReadOnlyDictionary? Cookies` Additional cookies to send to the server. - `Long EmbedBatchSize` The batch size for embedding calls. - `IReadOnlyDictionary? Headers` Additional headers to send to the server. By default only the authorization and user-agent headers are sent. Values in this dictionary will override the default values. - `string? ModelName` Hugging Face model name. If None, the task will be used. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Pooling? Pooling` Enum of possible pooling choices with pooling behaviors. - `"cls"Cls` - `"last"Last` - `"mean"Mean` - `string? QueryInstruction` Instruction to prepend during query embedding. - `string? Task` Optional task to pick Hugging Face's recommended model, used when model_name is left as default of None. - `string? TextInstruction` Instruction to prepend during text embedding. - `Double? Timeout` The maximum number of seconds to wait for a response from the server. Loading a new model in Inference API can take up to several minutes. Defaults to None, meaning it will loop until the server is available. - `Type Type` Type of the embedding model. - `"HUGGINGFACE_API_EMBEDDING"HuggingfaceApiEmbedding` - `class ManagedOpenAIEmbedding:` - `Component Component` Configuration for the Managed OpenAI embedding model. - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `ModelName ModelName` The name of the OpenAI embedding model. - `"openai-text-embedding-3-small"OpenAITextEmbedding3Small` - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Type Type` Type of the embedding model. - `"MANAGED_OPENAI_EMBEDDING"ManagedOpenAIEmbedding` - `class OpenAIEmbeddingConfig:` - `OpenAIEmbedding Component` Configuration for the OpenAI embedding model. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the OpenAI API. - `string? ApiBase` The base URL for OpenAI API. - `string? ApiKey` The OpenAI API key. - `string? ApiVersion` The version for OpenAI API. - `string ClassName` - `IReadOnlyDictionary? DefaultHeaders` The default headers for API requests. - `Long? Dimensions` The number of dimensions on the output embedding vectors. Works only with v3 embedding models. - `Long EmbedBatchSize` The batch size for embedding calls. - `Long MaxRetries` Maximum number of retries. - `string ModelName` The name of the OpenAI embedding model. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Boolean ReuseClient` Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability. - `Double Timeout` Timeout for each request. - `Type Type` Type of the embedding model. - `"OPENAI_EMBEDDING"OpenAIEmbedding` - `class VertexAIEmbeddingConfig:` - `VertexTextEmbedding Component` Configuration for the VertexAI embedding model. - `required string? ClientEmail` The client email for the VertexAI credentials. - `required string Location` The default location to use when making API calls. - `required string? PrivateKey` The private key for the VertexAI credentials. - `required string? PrivateKeyID` The private key ID for the VertexAI credentials. - `required string Project` The default GCP project to use when making Vertex API calls. - `required string? TokenUri` The token URI for the VertexAI credentials. - `IReadOnlyDictionary AdditionalKwargs` Additional kwargs for the Vertex. - `string ClassName` - `Long EmbedBatchSize` The batch size for embedding calls. - `EmbedMode EmbedMode` The embedding mode to use. - `"classification"Classification` - `"clustering"Clustering` - `"default"Default` - `"retrieval"Retrieval` - `"similarity"Similarity` - `string ModelName` The modelId of the VertexAI model to use. - `Long? NumWorkers` The number of workers to use for async embedding calls. - `Type Type` Type of the embedding model. - `"VERTEXAI_EMBEDDING"VertexaiEmbedding` - `required string Name` - `required string ProjectID` - `ConfigHash? ConfigHash` Hashes for the configuration of a pipeline. - `string? EmbeddingConfigHash` Hash of the embedding config. - `string? ParsingConfigHash` Hash of the llama parse parameters. - `string? TransformConfigHash` Hash of the transform config. - `DateTimeOffset? CreatedAt` Creation datetime - `DataSink? DataSink` Schema for a data sink. - `required string ID` Unique identifier - `required Component Component` Component that implements the data sink - `IReadOnlyDictionary` - `class CloudPineconeVectorStore:` Cloud Pinecone Vector Store. This class is used to store the configuration for a Pinecone vector store, so that it can be created and used in LlamaCloud. Args: api_key (str): API key for authenticating with Pinecone index_name (str): name of the Pinecone index namespace (optional[str]): namespace to use in the Pinecone index insert_kwargs (optional[dict]): additional kwargs to pass during insertion - `required string ApiKey` The API key for authenticating with Pinecone - `required string IndexName` - `string ClassName` - `IReadOnlyDictionary? InsertKwargs` - `string? Namespace` - `SupportsNestedMetadataFilters SupportsNestedMetadataFilters` - `trueTrue` - `class CloudPostgresVectorStore:` - `required string Database` - `required Long EmbedDim` - `required string Host` - `required string Password` - `required Long Port` - `required string SchemaName` - `required string TableName` - `required string User` - `string ClassName` - `PgVectorHnswSettings? HnswSettings` HNSW settings for PGVector. - `DistanceMethod DistanceMethod` The distance method to use. - `"cosine"Cosine` - `"hamming"Hamming` - `"ip"IP` - `"jaccard"Jaccard` - `"l1"L1` - `"l2"L2` - `Long EfConstruction` The number of edges to use during the construction phase. - `Long EfSearch` The number of edges to use during the search phase. - `Long M` The number of bi-directional links created for each new element. - `VectorType VectorType` The type of vector to use. - `"bit"Bit` - `"half_vec"HalfVec` - `"sparse_vec"SparseVec` - `"vector"Vector` - `Boolean? HybridSearch` - `Boolean PerformSetup` - `Boolean SupportsNestedMetadataFilters` - `class CloudQdrantVectorStore:` Cloud Qdrant Vector Store. This class is used to store the configuration for a Qdrant vector store, so that it can be created and used in LlamaCloud. Args: collection_name (str): name of the Qdrant collection url (str): url of the Qdrant instance api_key (str): API key for authenticating with Qdrant max_retries (int): maximum number of retries in case of a failure. Defaults to 3 client_kwargs (dict): additional kwargs to pass to the Qdrant client - `required string ApiKey` - `required string CollectionName` - `required string Url` - `string ClassName` - `IReadOnlyDictionary ClientKwargs` - `Long MaxRetries` - `SupportsNestedMetadataFilters SupportsNestedMetadataFilters` - `trueTrue` - `class CloudAzureAISearchVectorStore:` Cloud Azure AI Search Vector Store. - `required string SearchServiceApiKey` - `required string SearchServiceEndpoint` - `string ClassName` - `string? ClientID` - `string? ClientSecret` - `Long? EmbeddingDimension` - `IReadOnlyDictionary? FilterableMetadataFieldKeys` - `string? IndexName` - `string? SearchServiceApiVersion` - `SupportsNestedMetadataFilters SupportsNestedMetadataFilters` - `trueTrue` - `string? TenantID` - `class CloudMongoDBAtlasVectorSearch:` Cloud MongoDB Atlas Vector Store. This class is used to store the configuration for a MongoDB Atlas vector store, so that it can be created and used in LlamaCloud. Args: mongodb_uri (str): URI for connecting to MongoDB Atlas db_name (str): name of the MongoDB database collection_name (str): name of the MongoDB collection vector_index_name (str): name of the MongoDB Atlas vector index fulltext_index_name (str): name of the MongoDB Atlas full-text index - `required string CollectionName` - `required string DBName` - `required string MongoDBUri` - `string ClassName` - `Long? EmbeddingDimension` - `string? FulltextIndexName` - `Boolean SupportsNestedMetadataFilters` - `string? VectorIndexName` - `class CloudMilvusVectorStore:` Cloud Milvus Vector Store. - `required string Uri` - `string? Token` - `string ClassName` - `string? CollectionName` - `Long? EmbeddingDimension` - `Boolean SupportsNestedMetadataFilters` - `class CloudAstraDBVectorStore:` Cloud AstraDB Vector Store. This class is used to store the configuration for an AstraDB vector store, so that it can be created and used in LlamaCloud. Args: token (str): The Astra DB Application Token to use. api_endpoint (str): The Astra DB JSON API endpoint for your database. collection_name (str): Collection name to use. If not existing, it will be created. embedding_dimension (int): Length of the embedding vectors in use. keyspace (optional[str]): The keyspace to use. If not provided, 'default_keyspace' - `required string Token` The Astra DB Application Token to use - `required string ApiEndpoint` The Astra DB JSON API endpoint for your database - `required string CollectionName` Collection name to use. If not existing, it will be created - `required Long EmbeddingDimension` Length of the embedding vectors in use - `string ClassName` - `string? Keyspace` The keyspace to use. If not provided, 'default_keyspace' - `SupportsNestedMetadataFilters SupportsNestedMetadataFilters` - `trueTrue` - `required string Name` The name of the data sink. - `required string ProjectID` - `required SinkType SinkType` - `"ASTRA_DB"AstraDB` - `"AZUREAI_SEARCH"AzureaiSearch` - `"MILVUS"Milvus` - `"MONGODB_ATLAS"MongoDBAtlas` - `"PINECONE"Pinecone` - `"POSTGRES"Postgres` - `"QDRANT"Qdrant` - `DateTimeOffset? CreatedAt` Creation datetime - `DateTimeOffset? UpdatedAt` Update datetime - `EmbeddingModelConfig? EmbeddingModelConfig` Schema for an embedding model config. - `required string ID` Unique identifier - `required EmbeddingConfig EmbeddingConfig` The embedding configuration for the embedding model config. - `class AzureOpenAIEmbeddingConfig:` - `class BedrockEmbeddingConfig:` - `class CohereEmbeddingConfig:` - `class GeminiEmbeddingConfig:` - `class HuggingFaceInferenceApiEmbeddingConfig:` - `class OpenAIEmbeddingConfig:` - `class VertexAIEmbeddingConfig:` - `required string Name` The name of the embedding model config. - `required string ProjectID` - `DateTimeOffset? CreatedAt` Creation datetime - `DateTimeOffset? UpdatedAt` Update datetime - `string? EmbeddingModelConfigID` The ID of the EmbeddingModelConfig this pipeline is using. - `LlamaParseParameters? LlamaParseParameters` Settings that can be configured for how to use LlamaParse to parse files within a LlamaCloud pipeline. - `Boolean? AdaptiveLongTable` - `Boolean? AggressiveTableExtraction` - `Boolean? AnnotateLinks` - `Boolean? AutoMode` - `string? AutoModeConfigurationJson` - `Boolean? AutoModeTriggerOnImageInPage` - `string? AutoModeTriggerOnRegexpInPage` - `Boolean? AutoModeTriggerOnTableInPage` - `string? AutoModeTriggerOnTextInPage` - `string? AzureOpenAIApiVersion` - `string? AzureOpenAIDeploymentName` - `string? AzureOpenAIEndpoint` - `string? AzureOpenAIKey` - `Double? BboxBottom` - `Double? BboxLeft` - `Double? BboxRight` - `Double? BboxTop` - `string? BoundingBox` - `Boolean? CompactMarkdownTable` - `string? ComplementalFormattingInstruction` - `string? ConfidenceScoreEffort` - `string? ContentGuidelineInstruction` - `Boolean? ContinuousMode` - `Boolean? DisableImageExtraction` - `Boolean? DisableOcr` - `Boolean? DisableReconstruction` - `Boolean? DoNotCache` - `Boolean? DoNotUnrollColumns` - `Boolean? EnableCostOptimizer` - `Boolean? ExtractCharts` - `Boolean? ExtractLayout` - `Boolean? ExtractPrintedPageNumber` - `Boolean? FastMode` - `string? FormattingInstruction` - `string? Gpt4oApiKey` - `Boolean? Gpt4oMode` - `Boolean? GuessXlsxSheetName` - `Boolean? HideFooters` - `Boolean? HideHeaders` - `Boolean? HighResOcr` - `Boolean? HtmlMakeAllElementsVisible` - `Boolean? HtmlRemoveFixedElements` - `Boolean? HtmlRemoveNavigationElements` - `string? HttpProxy` - `Boolean? IgnoreDocumentElementsForLayoutDetection` - `IReadOnlyList? ImagesToSave` - `"embedded"Embedded` - `"layout"Layout` - `"screenshot"Screenshot` - `Boolean? InlineImagesInMarkdown` - `string? InputS3Path` - `string? InputS3Region` - `string? InputUrl` - `Boolean? InternalIsScreenshotJob` - `Boolean? InvalidateCache` - `Boolean? IsFormattingInstruction` - `Double? JobTimeoutExtraTimePerPageInSeconds` - `Double? JobTimeoutInSeconds` - `Boolean? KeepPageSeparatorWhenMergingTables` - `IReadOnlyList Languages` - `"abq"Abq` - `"ady"Ady` - `"af"Af` - `"ang"Ang` - `"ar"Ar` - `"as"As` - `"ava"Ava` - `"az"Az` - `"be"Be` - `"bg"Bg` - `"bgc"Bgc` - `"bh"Bh` - `"bho"Bho` - `"bn"Bn` - `"bs"Bs` - `"ch_sim"ChSim` - `"ch_tra"ChTra` - `"che"Che` - `"cs"Cs` - `"cy"Cy` - `"da"Da` - `"dar"Dar` - `"de"De` - `"en"En` - `"es"Es` - `"et"Et` - `"fa"Fa` - `"fr"Fr` - `"ga"Ga` - `"gom"Gom` - `"hi"Hi` - `"hr"Hr` - `"hu"Hu` - `"id"ID` - `"inh"Inh` - `"is"Is` - `"it"It` - `"ja"Ja` - `"kbd"Kbd` - `"kn"Kn` - `"ko"Ko` - `"ku"Ku` - `"la"La` - `"lbe"Lbe` - `"lez"Lez` - `"lt"Lt` - `"lv"Lv` - `"mah"Mah` - `"mai"Mai` - `"mi"Mi` - `"mn"Mn` - `"mni"Mni` - `"mr"Mr` - `"ms"Ms` - `"mt"Mt` - `"ne"Ne` - `"new"New` - `"nl"Nl` - `"no"No` - `"oc"Oc` - `"pi"Pi` - `"pl"Pl` - `"pt"Pt` - `"ro"Ro` - `"rs_cyrillic"RsCyrillic` - `"rs_latin"RsLatin` - `"ru"Ru` - `"sa"Sa` - `"sck"Sck` - `"sk"Sk` - `"sl"Sl` - `"sq"Sq` - `"sv"Sv` - `"sw"Sw` - `"ta"Ta` - `"tab"Tab` - `"te"Te` - `"th"Th` - `"tjk"Tjk` - `"tl"Tl` - `"tr"Tr` - `"ug"Ug` - `"uk"Uk` - `"ur"Ur` - `"uz"Uz` - `"vi"Vi` - `Boolean? LayoutAware` - `Boolean? LineLevelBoundingBox` - `string? MarkdownTableMultilineHeaderSeparator` - `Long? MaxPages` - `Long? MaxPagesEnforced` - `Boolean? MergeTablesAcrossPagesInMarkdown` - `string? Model` - `Boolean? OutlinedTableExtraction` - `Boolean? OutputPdfOfDocument` - `string? OutputS3PathPrefix` - `string? OutputS3Region` - `Boolean? OutputTablesAsHtml` - `Double? PageErrorTolerance` - `string? PageFooterPrefix` - `string? PageFooterSuffix` - `string? PageHeaderPrefix` - `string? PageHeaderSuffix` - `string? PagePrefix` - `string? PageSeparator` - `string? PageSuffix` - `ParsingMode? ParseMode` Enum for representing the mode of parsing to be used. - `"parse_document_with_agent"ParseDocumentWithAgent` - `"parse_document_with_llm"ParseDocumentWithLlm` - `"parse_document_with_lvm"ParseDocumentWithLvm` - `"parse_page_with_agent"ParsePageWithAgent` - `"parse_page_with_layout_agent"ParsePageWithLayoutAgent` - `"parse_page_with_llm"ParsePageWithLlm` - `"parse_page_with_lvm"ParsePageWithLvm` - `"parse_page_without_llm"ParsePageWithoutLlm` - `string? ParsingInstruction` - `Boolean? PreciseBoundingBox` - `Boolean? PremiumMode` - `Boolean? PresentationOutOfBoundsContent` - `Boolean? PresentationSkipEmbeddedData` - `Boolean? PreserveLayoutAlignmentAcrossPages` - `Boolean? PreserveVerySmallText` - `string? Preset` - `Priority? Priority` The priority for the request. This field may be ignored or overwritten depending on the organization tier. - `"critical"Critical` - `"high"High` - `"low"Low` - `"medium"Medium` - `string? ProjectID` - `Boolean? RemoveHiddenText` - `FailPageMode? ReplaceFailedPageMode` Enum for representing the different available page error handling modes. - `"blank_page"BlankPage` - `"error_message"ErrorMessage` - `"raw_text"RawText` - `string? ReplaceFailedPageWithErrorMessagePrefix` - `string? ReplaceFailedPageWithErrorMessageSuffix` - `Boolean? SaveImages` - `Boolean? SkipDiagonalText` - `Boolean? SpecializedChartParsingAgentic` - `Boolean? SpecializedChartParsingEfficient` - `Boolean? SpecializedChartParsingPlus` - `Boolean? SpecializedImageParsing` - `Boolean? SpreadsheetExtractSubTables` - `Boolean? SpreadsheetForceFormulaComputation` - `Boolean? SpreadsheetIncludeHiddenSheets` - `Boolean? StrictModeBuggyFont` - `Boolean? StrictModeImageExtraction` - `Boolean? StrictModeImageOcr` - `Boolean? StrictModeReconstruction` - `Boolean? StructuredOutput` - `string? StructuredOutputJsonSchema` - `string? StructuredOutputJsonSchemaName` - `string? SystemPrompt` - `string? SystemPromptAppend` - `Boolean? TakeScreenshot` - `string? TargetPages` - `string? Tier` - `Boolean? UseVendorMultimodalModel` - `string? UserPrompt` - `string? VendorMultimodalApiKey` - `string? VendorMultimodalModelName` - `string? Version` - `IReadOnlyList? WebhookConfigurations` Outbound webhook endpoints to notify on job status changes - `IReadOnlyList? WebhookEvents` Events to subscribe to (e.g. 'parse.success', 'extract.error'). If null, all events are delivered. - `"classify.cancelled"ClassifyCancelled` - `"classify.error"ClassifyError` - `"classify.partial_success"ClassifyPartialSuccess` - `"classify.pending"ClassifyPending` - `"classify.running"ClassifyRunning` - `"classify.success"ClassifySuccess` - `"extract.cancelled"ExtractCancelled` - `"extract.error"ExtractError` - `"extract.partial_success"ExtractPartialSuccess` - `"extract.pending"ExtractPending` - `"extract.success"ExtractSuccess` - `"parse.cancelled"ParseCancelled` - `"parse.error"ParseError` - `"parse.partial_success"ParsePartialSuccess` - `"parse.pending"ParsePending` - `"parse.running"ParseRunning` - `"parse.success"ParseSuccess` - `"sheets.cancelled"SheetsCancelled` - `"sheets.error"SheetsError` - `"sheets.partial_success"SheetsPartialSuccess` - `"sheets.pending"SheetsPending` - `"sheets.success"SheetsSuccess` - `"split.cancelled"SplitCancelled` - `"split.error"SplitError` - `"split.pending"SplitPending` - `"split.processing"SplitProcessing` - `"split.success"SplitSuccess` - `"unmapped_event"UnmappedEvent` - `IReadOnlyDictionary? WebhookHeaders` Custom HTTP headers sent with each webhook request (e.g. auth tokens) - `string? WebhookOutputFormat` Response format sent to the webhook: 'string' (default) or 'json' - `string? WebhookSigningSecret` Shared signing secret used to sign webhook deliveries. When set, each request includes an HMAC-SHA256 signature of the request body in the 'LC-Signature' header (value 'sha256='). Recompute the HMAC over the raw request body with this secret to verify the delivery is authentic. - `string? WebhookUrl` URL to receive webhook POST notifications - `string? WebhookUrl` - `string? ManagedPipelineID` The ID of the ManagedPipeline this playground pipeline is linked to. - `PipelineMetadataConfig? MetadataConfig` Metadata configuration for the pipeline. - `IReadOnlyList ExcludedEmbedMetadataKeys` List of metadata keys to exclude from embeddings - `IReadOnlyList ExcludedLlmMetadataKeys` List of metadata keys to exclude from LLM during retrieval - `PipelineType PipelineType` Type of pipeline. Either PLAYGROUND or MANAGED. - `"MANAGED"Managed` - `"PLAYGROUND"Playground` - `PresetRetrievalParams PresetRetrievalParameters` Preset retrieval parameters for the pipeline. - `Double? Alpha` Alpha value for hybrid retrieval to determine the weights between dense and sparse retrieval. 0 is sparse retrieval and 1 is dense retrieval. - `string ClassName` - `Double? DenseSimilarityCutoff` Minimum similarity score wrt query for retrieval - `Long? DenseSimilarityTopK` Number of nodes for dense retrieval. - `Boolean? EnableReranking` Enable reranking for retrieval - `Long? FilesTopK` Number of files to retrieve (only for retrieval mode files_via_metadata and files_via_content). - `Long? RerankTopN` Number of reranked nodes for returning. - `RetrievalMode RetrievalMode` The retrieval mode for the query. - `"auto_routed"AutoRouted` - `"chunks"Chunks` - `"files_via_content"FilesViaContent` - `"files_via_metadata"FilesViaMetadata` - `Boolean RetrieveImageNodes` Whether to retrieve image nodes. - `Boolean RetrievePageFigureNodes` Whether to retrieve page figure nodes. - `Boolean RetrievePageScreenshotNodes` Whether to retrieve page screenshot nodes. - `MetadataFilters? SearchFilters` Metadata filters for vector stores. - `required IReadOnlyList Filters` - `class MetadataFilter:` Comprehensive metadata filter for vector stores to support more operators. Value uses Strict types, as int, float and str are compatible types and were all converted to string before. See: https://docs.pydantic.dev/latest/usage/types/#strict-types - `required string Key` - `required Value? Value` - `Double` - `string` - `IReadOnlyList` - `IReadOnlyList` - `IReadOnlyList` - `Operator Operator` Vector store filter operator. - `"!="` - `"<"` - `"<="` - `"=="` - `">"` - `">="` - `"all"All` - `"any"Any` - `"contains"Contains` - `"in"In` - `"is_empty"IsEmpty` - `"nin"Nin` - `"text_match"TextMatch` - `"text_match_insensitive"TextMatchInsensitive` - `class MetadataFilters:` Metadata filters for vector stores. - `Condition? Condition` Vector store filter conditions to combine different filters. - `"and"And` - `"not"Not` - `"or"Or` - `IReadOnlyDictionary? SearchFiltersInferenceSchema` JSON Schema that will be used to infer search_filters. Omit or leave as null to skip inference. - `IReadOnlyDictionary` - `IReadOnlyList` - `string` - `Double` - `Boolean` - `Long? SparseSimilarityTopK` Number of nodes for sparse retrieval. - `SparseModelConfig? SparseModelConfig` Configuration for sparse embedding models used in hybrid search. This allows users to choose between Splade and BM25 models for sparse retrieval in managed data sinks. - `string ClassName` - `ModelType ModelType` The sparse model type to use. 'bm25' uses Qdrant's FastEmbed BM25 model (default for new pipelines), 'splade' uses HuggingFace Splade model, 'auto' selects based on deployment mode (BYOC uses term frequency, Cloud uses Splade). - `"auto"Auto` - `"bm25"Bm25` - `"splade"Splade` - `Status? Status` Status of the pipeline. - `"CREATED"Created` - `"DELETING"Deleting` - `TransformConfig TransformConfig` Configuration for the transformation. - `class AutoTransformConfig:` - `Long ChunkOverlap` Chunk overlap for the transformation. - `Long ChunkSize` Chunk size for the transformation. - `Mode Mode` - `"auto"Auto` - `class AdvancedModeTransformConfig:` - `ChunkingConfig ChunkingConfig` Configuration for the chunking. - `class NoneChunkingConfig:` - `Mode Mode` - `"none"None` - `class CharacterChunkingConfig:` - `Long ChunkOverlap` - `Long ChunkSize` - `Mode Mode` - `"character"Character` - `class TokenChunkingConfig:` - `Long ChunkOverlap` - `Long ChunkSize` - `Mode Mode` - `"token"Token` - `string Separator` - `class SentenceChunkingConfig:` - `Long ChunkOverlap` - `Long ChunkSize` - `Mode Mode` - `"sentence"Sentence` - `string ParagraphSeparator` - `string Separator` - `class SemanticChunkingConfig:` - `Long BreakpointPercentileThreshold` - `Long BufferSize` - `Mode Mode` - `"semantic"Semantic` - `Mode Mode` - `"advanced"Advanced` - `SegmentationConfig SegmentationConfig` Configuration for the segmentation. - `class NoneSegmentationConfig:` - `Mode Mode` - `"none"None` - `class PageSegmentationConfig:` - `Mode Mode` - `"page"Page` - `string PageSeparator` - `class ElementSegmentationConfig:` - `Mode Mode` - `"element"Element` - `DateTimeOffset? UpdatedAt` Update datetime ### Example ```csharp DataSourceSyncParams parameters = new() { PipelineID = "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", DataSourceID = "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", }; var pipeline = await client.Pipelines.DataSources.Sync(parameters); Console.WriteLine(pipeline); ``` #### Response ```json { "id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "embedding_config": { "component": { "additional_kwargs": { "foo": "bar" }, "api_base": "api_base", "api_key": "api_key", "api_version": "api_version", "azure_deployment": "azure_deployment", "azure_endpoint": "azure_endpoint", "class_name": "class_name", "default_headers": { "foo": "string" }, "dimensions": 0, "embed_batch_size": 1, "max_retries": 0, "model_name": "model_name", "num_workers": 0, "reuse_client": true, "timeout": 0 }, "type": "AZURE_EMBEDDING" }, "name": "name", "project_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "config_hash": { "embedding_config_hash": "embedding_config_hash", "parsing_config_hash": "parsing_config_hash", "transform_config_hash": "transform_config_hash" }, "created_at": "2019-12-27T18:11:19.117Z", "data_sink": { "id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "component": { "foo": "bar" }, "name": "name", "project_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "sink_type": "ASTRA_DB", "created_at": "2019-12-27T18:11:19.117Z", "updated_at": "2019-12-27T18:11:19.117Z" }, "embedding_model_config": { "id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "embedding_config": { "component": { "additional_kwargs": { "foo": "bar" }, "api_base": "api_base", "api_key": "api_key", "api_version": "api_version", "azure_deployment": "azure_deployment", "azure_endpoint": "azure_endpoint", "class_name": "class_name", "default_headers": { "foo": "string" }, "dimensions": 0, "embed_batch_size": 1, "max_retries": 0, "model_name": "model_name", "num_workers": 0, "reuse_client": true, "timeout": 0 }, "type": "AZURE_EMBEDDING" }, "name": "name", "project_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "created_at": "2019-12-27T18:11:19.117Z", "updated_at": "2019-12-27T18:11:19.117Z" }, "embedding_model_config_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "llama_parse_parameters": { "adaptive_long_table": true, "aggressive_table_extraction": true, "annotate_links": true, "auto_mode": true, "auto_mode_configuration_json": "auto_mode_configuration_json", "auto_mode_trigger_on_image_in_page": true, "auto_mode_trigger_on_regexp_in_page": "auto_mode_trigger_on_regexp_in_page", "auto_mode_trigger_on_table_in_page": true, "auto_mode_trigger_on_text_in_page": "auto_mode_trigger_on_text_in_page", "azure_openai_api_version": "azure_openai_api_version", "azure_openai_deployment_name": "azure_openai_deployment_name", "azure_openai_endpoint": "azure_openai_endpoint", "azure_openai_key": "azure_openai_key", "bbox_bottom": 0, "bbox_left": 0, "bbox_right": 0, "bbox_top": 0, "bounding_box": "bounding_box", "compact_markdown_table": true, "complemental_formatting_instruction": "complemental_formatting_instruction", "confidence_score_effort": "confidence_score_effort", "content_guideline_instruction": "content_guideline_instruction", "continuous_mode": true, "disable_image_extraction": true, "disable_ocr": true, "disable_reconstruction": true, "do_not_cache": true, "do_not_unroll_columns": true, "enable_cost_optimizer": true, "extract_charts": true, "extract_layout": true, "extract_printed_page_number": true, "fast_mode": true, "formatting_instruction": "formatting_instruction", "gpt4o_api_key": "gpt4o_api_key", "gpt4o_mode": true, "guess_xlsx_sheet_name": true, "hide_footers": true, "hide_headers": true, "high_res_ocr": true, "html_make_all_elements_visible": true, "html_remove_fixed_elements": true, "html_remove_navigation_elements": true, "http_proxy": "http_proxy", "ignore_document_elements_for_layout_detection": true, "images_to_save": [ "embedded" ], "inline_images_in_markdown": true, "input_s3_path": "input_s3_path", "input_s3_region": "input_s3_region", "input_url": "input_url", "internal_is_screenshot_job": true, "invalidate_cache": true, "is_formatting_instruction": true, "job_timeout_extra_time_per_page_in_seconds": 0, "job_timeout_in_seconds": 0, "keep_page_separator_when_merging_tables": true, "languages": [ "abq" ], "layout_aware": true, "line_level_bounding_box": true, "markdown_table_multiline_header_separator": "markdown_table_multiline_header_separator", "max_pages": 0, "max_pages_enforced": 0, "merge_tables_across_pages_in_markdown": true, "model": "model", "outlined_table_extraction": true, "output_pdf_of_document": true, "output_s3_path_prefix": "output_s3_path_prefix", "output_s3_region": "output_s3_region", "output_tables_as_HTML": true, "page_error_tolerance": 0, "page_footer_prefix": "page_footer_prefix", "page_footer_suffix": "page_footer_suffix", "page_header_prefix": "page_header_prefix", "page_header_suffix": "page_header_suffix", "page_prefix": "page_prefix", "page_separator": "page_separator", "page_suffix": "page_suffix", "parse_mode": "parse_document_with_agent", "parsing_instruction": "parsing_instruction", "precise_bounding_box": true, "premium_mode": true, "presentation_out_of_bounds_content": true, "presentation_skip_embedded_data": true, "preserve_layout_alignment_across_pages": true, "preserve_very_small_text": true, "preset": "preset", "priority": "critical", "project_id": "project_id", "remove_hidden_text": true, "replace_failed_page_mode": "blank_page", "replace_failed_page_with_error_message_prefix": "replace_failed_page_with_error_message_prefix", "replace_failed_page_with_error_message_suffix": "replace_failed_page_with_error_message_suffix", "save_images": true, "skip_diagonal_text": true, "specialized_chart_parsing_agentic": true, "specialized_chart_parsing_efficient": true, "specialized_chart_parsing_plus": true, "specialized_image_parsing": true, "spreadsheet_extract_sub_tables": true, "spreadsheet_force_formula_computation": true, "spreadsheet_include_hidden_sheets": true, "strict_mode_buggy_font": true, "strict_mode_image_extraction": true, "strict_mode_image_ocr": true, "strict_mode_reconstruction": true, "structured_output": true, "structured_output_json_schema": "structured_output_json_schema", "structured_output_json_schema_name": "structured_output_json_schema_name", "system_prompt": "system_prompt", "system_prompt_append": "system_prompt_append", "take_screenshot": true, "target_pages": "target_pages", "tier": "tier", "use_vendor_multimodal_model": true, "user_prompt": "user_prompt", "vendor_multimodal_api_key": "vendor_multimodal_api_key", "vendor_multimodal_model_name": "vendor_multimodal_model_name", "version": "version", "webhook_configurations": [ { "webhook_events": [ "parse.success", "parse.error" ], "webhook_headers": { "Authorization": "Bearer sk-..." }, "webhook_output_format": "json", "webhook_signing_secret": "whsec_...", "webhook_url": "https://example.com/webhooks/llamacloud" } ], "webhook_url": "webhook_url" }, "managed_pipeline_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "metadata_config": { "excluded_embed_metadata_keys": [ "string" ], "excluded_llm_metadata_keys": [ "string" ] }, "pipeline_type": "MANAGED", "preset_retrieval_parameters": { "alpha": 0, "class_name": "class_name", "dense_similarity_cutoff": 0, "dense_similarity_top_k": 1, "enable_reranking": true, "files_top_k": 1, "rerank_top_n": 1, "retrieval_mode": "auto_routed", "retrieve_image_nodes": true, "retrieve_page_figure_nodes": true, "retrieve_page_screenshot_nodes": true, "search_filters": { "filters": [ { "key": "key", "value": 0, "operator": "!=" } ], "condition": "and" }, "search_filters_inference_schema": { "foo": { "foo": "bar" } }, "sparse_similarity_top_k": 1 }, "sparse_model_config": { "class_name": "class_name", "model_type": "auto" }, "status": "CREATED", "transform_config": { "chunk_overlap": 0, "chunk_size": 1, "mode": "auto" }, "updated_at": "2019-12-27T18:11:19.117Z" } ``` ## Domain Types ### Pipeline Data Source - `class PipelineDataSource:` Schema for a data source in a pipeline. - `required string ID` Unique identifier - `required Component Component` Component that implements the data source - `IReadOnlyDictionary` - `class CloudS3DataSource:` - `required string Bucket` The name of the S3 bucket to read from. - `string? AwsAccessID` The AWS access ID to use for authentication. - `string? AwsAccessSecret` The AWS access secret to use for authentication. - `string ClassName` - `string? Prefix` The prefix of the S3 objects to read from. - `string? RegexPattern` The regex pattern to filter S3 objects. Must be a valid regex pattern. - `string? S3EndpointUrl` The S3 endpoint URL to use for authentication. - `Boolean SupportsAccessControl` - `class CloudAzStorageBlobDataSource:` - `required string AccountUrl` The Azure Storage Blob account URL to use for authentication. - `required string ContainerName` The name of the Azure Storage Blob container to read from. - `string? AccountKey` The Azure Storage Blob account key to use for authentication. - `string? AccountName` The Azure Storage Blob account name to use for authentication. - `string? Blob` The blob name to read from. - `string ClassName` - `string? ClientID` The Azure AD client ID to use for authentication. - `string? ClientSecret` The Azure AD client secret to use for authentication. - `string? Prefix` The prefix of the Azure Storage Blob objects to read from. - `Boolean SupportsAccessControl` - `string? TenantID` The Azure AD tenant ID to use for authentication. - `class CloudGoogleDriveDataSource:` - `required string FolderID` The ID of the Google Drive folder to read from. - `string ClassName` - `string? FolderName` Human-readable name of the selected folder, for display. - `IReadOnlyDictionary? ServiceAccountKey` A dictionary containing secret values - `Boolean SupportsAccessControl` - `class CloudOneDriveDataSource:` - `required string ClientID` The client ID to use for authentication. - `required string ClientSecret` The client secret to use for authentication. - `required string TenantID` The tenant ID to use for authentication. - `required string UserPrincipalName` The user principal name to use for authentication. - `string ClassName` - `string? FolderID` The ID of the OneDrive folder to read from. - `string? FolderPath` The path of the OneDrive folder to read from. - `IReadOnlyList? RequiredExts` The list of required file extensions. - `SupportsAccessControl SupportsAccessControl` - `trueTrue` - `class CloudSharepointDataSource:` - `required string ClientID` The client ID to use for authentication. - `required string ClientSecret` The client secret to use for authentication. - `required string TenantID` The tenant ID to use for authentication. - `string ClassName` - `string? DriveName` The name of the Sharepoint drive to read from. - `IReadOnlyList? ExcludePathPatterns` List of regex patterns for file paths to exclude. Files whose paths (including filename) match any pattern will be excluded. Example: ['/temp/', '/backup/', '.git/', '.tmp$', '^~'] - `string? FolderID` The ID of the Sharepoint folder to read from. - `string? FolderPath` The path of the Sharepoint folder to read from. - `Boolean GetPermissions` Whether to get permissions for the sharepoint site. - `IReadOnlyList? IncludePathPatterns` List of regex patterns for file paths to include. Full paths (including filename) must match at least one pattern to be included. Example: ['/reports/', '/docs/.*.pdf$', '^Report.*.pdf$'] - `IReadOnlyList? RequiredExts` The list of required file extensions. - `string? SiteID` The ID of the SharePoint site to download from. - `string? SiteName` The name of the SharePoint site to download from. - `SupportsAccessControl SupportsAccessControl` - `trueTrue` - `class CloudSlackDataSource:` - `required string SlackToken` Slack Bot Token. - `string? ChannelIds` Slack Channel. - `string? ChannelPatterns` Slack Channel name pattern. - `string ClassName` - `string? EarliestDate` Earliest date. - `Double? EarliestDateTimestamp` Earliest date timestamp. - `string? LatestDate` Latest date. - `Double? LatestDateTimestamp` Latest date timestamp. - `Boolean SupportsAccessControl` - `class CloudNotionPageDataSource:` - `required string IntegrationToken` The integration token to use for authentication. - `string ClassName` - `string? DatabaseIds` The Notion Database Id to read content from. - `string? PageIds` The Page ID's of the Notion to read from. - `Boolean SupportsAccessControl` - `class CloudConfluenceDataSource:` - `required string AuthenticationMechanism` Type of Authentication for connecting to Confluence APIs. - `required string ServerUrl` The server URL of the Confluence instance. - `string? ApiToken` The API token to use for authentication. - `string ClassName` - `string? Cql` The CQL query to use for fetching pages. - `FailureHandlingConfig FailureHandling` Configuration for handling failures during processing. Key-value object controlling failure handling behaviors. Example: { "skip_list_failures": true } Currently supports: - skip_list_failures: Skip failed batches/lists and continue processing - `Boolean SkipListFailures` Whether to skip failed batches/lists and continue processing - `Boolean IndexRestrictedPages` Whether to index restricted pages. - `Boolean KeepMarkdownFormat` Whether to keep the markdown format. - `string? Label` The label to use for fetching pages. - `string? PageIds` The page IDs of the Confluence to read from. - `string? SpaceKey` The space key to read from. - `Boolean SupportsAccessControl` - `Boolean SyncPermissions` Whether to fetch space-level permissions (allowed users/groups) and attach them to document metadata for access control. Disable for Confluence Server/Data Center versions whose permission APIs are unavailable (e.g. the JSON-RPC API removed in Data Center 9.2.6+), which otherwise surface as 401 errors during sync. - `string? UserName` The username to use for authentication. - `class CloudJiraDataSource:` Cloud Jira Data Source integrating JiraReader. - `required string AuthenticationMechanism` Type of Authentication for connecting to Jira APIs. - `required string Query` JQL (Jira Query Language) query to search. - `string? ApiToken` The API/ Access Token used for Basic, PAT and OAuth2 authentication. - `string ClassName` - `string? CloudID` The cloud ID, used in case of OAuth2. - `string? Email` The email address to use for authentication. - `string? ServerUrl` The server url for Jira Cloud. - `Boolean SupportsAccessControl` - `class CloudJiraDataSourceV2:` Cloud Jira Data Source integrating JiraReaderV2. - `required string AuthenticationMechanism` Type of Authentication for connecting to Jira APIs. - `required string Query` JQL (Jira Query Language) query to search. - `required string ServerUrl` The server url for Jira Cloud. - `string? ApiToken` The API Access Token used for Basic, PAT and OAuth2 authentication. - `ApiVersion ApiVersion` Jira REST API version to use (2 or 3). 3 supports Atlassian Document Format (ADF). - `"2"2` - `"3"3` - `string ClassName` - `string? CloudID` The cloud ID, used in case of OAuth2. - `string? Email` The email address to use for authentication. - `string? Expand` Fields to expand in the response. - `IReadOnlyList? Fields` List of fields to retrieve from Jira. If None, retrieves all fields. - `Boolean GetPermissions` Whether to fetch project role permissions and issue-level security - `Long? RequestsPerMinute` Rate limit for Jira API requests per minute. - `Boolean SupportsAccessControl` - `class CloudBoxDataSource:` - `required AuthenticationMechanism AuthenticationMechanism` The type of authentication to use (Developer Token or CCG) - `"ccg"Ccg` - `"developer_token"DeveloperToken` - `string ClassName` - `string? ClientID` Box API key used for identifying the application the user is authenticating with - `string? ClientSecret` Box API secret used for making auth requests. - `string? DeveloperToken` Developer token for authentication if authentication_mechanism is 'developer_token'. - `string? EnterpriseID` Box Enterprise ID, if provided authenticates as service. - `string? FolderID` The ID of the Box folder to read from. - `Boolean SupportsAccessControl` - `string? UserID` Box User ID, if provided authenticates as user. - `required string DataSourceID` The ID of the data source. - `required DateTimeOffset LastSyncedAt` The last time the data source was automatically synced. - `required string Name` The name of the data source. - `required string PipelineID` The ID of the pipeline. - `required string ProjectID` - `required SourceType SourceType` - `"AZURE_STORAGE_BLOB"AzureStorageBlob` - `"BOX"Box` - `"CONFLUENCE"Confluence` - `"GOOGLE_DRIVE"GoogleDrive` - `"JIRA"Jira` - `"JIRA_V2"JiraV2` - `"MICROSOFT_ONEDRIVE"MicrosoftOnedrive` - `"MICROSOFT_SHAREPOINT"MicrosoftSharepoint` - `"NOTION_PAGE"NotionPage` - `"S3"S3` - `"SLACK"Slack` - `DateTimeOffset? CreatedAt` Creation datetime - `IReadOnlyDictionary? CustomMetadata` Custom metadata that will be present on all data loaded from the data source - `IReadOnlyDictionary` - `IReadOnlyList` - `string` - `Double` - `Boolean` - `Status? Status` The status of the data source in the pipeline. - `"CANCELLED"Cancelled` - `"ERROR"Error` - `"IN_PROGRESS"InProgress` - `"NOT_STARTED"NotStarted` - `"SUCCESS"Success` - `DateTimeOffset? StatusUpdatedAt` The last time the status was updated. - `Double? SyncInterval` The interval at which the data source should be synced. - `string? SyncScheduleSetBy` The id of the user who set the sync schedule. - `DateTimeOffset? UpdatedAt` Update datetime - `DataSourceReaderVersionMetadata? VersionMetadata` Version metadata for the data source - `ReaderVersion? ReaderVersion` The version of the reader to use for this data source. - `"1.0"1_0` - `"2.0"2_0` - `"2.1"2_1` # Images ## List File Page Screenshots `IReadOnlyList Pipelines.Images.ListPageScreenshots(ImageListPageScreenshotsParamsparameters, CancellationTokencancellationToken = default)` **get** `/api/v1/files/{id}/page_screenshots` List metadata for all screenshots of pages from a file. ### Parameters - `ImageListPageScreenshotsParams parameters` - `required string id` - `string? organizationID` - `string? projectID` ### Example ```csharp ImageListPageScreenshotsParams parameters = new() { ID = "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e" }; var response = await client.Pipelines.Images.ListPageScreenshots(parameters); Console.WriteLine(response); ``` #### Response ```json [ { "file_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "image_size": 0, "page_index": 0, "metadata": { "foo": "bar" } } ] ``` ## Get File Page Screenshot `JsonElement Pipelines.Images.GetPageScreenshot(ImageGetPageScreenshotParamsparameters, CancellationTokencancellationToken = default)` **get** `/api/v1/files/{id}/page_screenshots/{page_index}` Get screenshot of a page from a file. ### Parameters - `ImageGetPageScreenshotParams parameters` - `required string id` Path param - `required Long pageIndex` Path param - `string? organizationID` Query param - `string? projectID` Query param ### Example ```csharp ImageGetPageScreenshotParams parameters = new() { ID = "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", PageIndex = 0, }; var response = await client.Pipelines.Images.GetPageScreenshot(parameters); Console.WriteLine(response); ``` #### Response ```json {} ``` ## Get File Page Figure `JsonElement Pipelines.Images.GetPageFigure(ImageGetPageFigureParamsparameters, CancellationTokencancellationToken = default)` **get** `/api/v1/files/{id}/page-figures/{page_index}/{figure_name}` Get a specific figure from a page of a file. ### Parameters - `ImageGetPageFigureParams parameters` - `required string id` Path param - `required Long pageIndex` Path param - `required string figureName` Path param - `string? organizationID` Query param - `string? projectID` Query param ### Example ```csharp ImageGetPageFigureParams parameters = new() { ID = "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", PageIndex = 0, FigureName = "figure_name", }; var response = await client.Pipelines.Images.GetPageFigure(parameters); Console.WriteLine(response); ``` #### Response ```json {} ``` ## List File Pages Figures `IReadOnlyList Pipelines.Images.ListPageFigures(ImageListPageFiguresParamsparameters, CancellationTokencancellationToken = default)` **get** `/api/v1/files/{id}/page-figures` List metadata for all figures from all pages of a file. ### Parameters - `ImageListPageFiguresParams parameters` - `required string id` - `string? organizationID` - `string? projectID` ### Example ```csharp ImageListPageFiguresParams parameters = new() { ID = "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e" }; var response = await client.Pipelines.Images.ListPageFigures(parameters); Console.WriteLine(response); ``` #### Response ```json [ { "confidence": 0, "figure_name": "figure_name", "figure_size": 0, "file_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "page_index": 0, "is_likely_noise": true, "metadata": { "foo": "bar" } } ] ``` # Files ## Get Pipeline File Status Counts `FileGetStatusCountsResponse Pipelines.Files.GetStatusCounts(FileGetStatusCountsParamsparameters, CancellationTokencancellationToken = default)` **get** `/api/v1/pipelines/{pipeline_id}/files/status-counts` Get files for a pipeline. ### Parameters - `FileGetStatusCountsParams parameters` - `required string pipelineID` - `string? dataSourceID` - `Boolean onlyManuallyUploaded` ### Returns - `class FileGetStatusCountsResponse:` - `required IReadOnlyDictionary Counts` The counts of files by status - `required Long TotalCount` The total number of files - `string? DataSourceID` The ID of the data source that the files belong to - `Boolean OnlyManuallyUploaded` Whether to only count manually uploaded files - `string? PipelineID` The ID of the pipeline that the files belong to ### Example ```csharp FileGetStatusCountsParams parameters = new() { PipelineID = "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e" }; var response = await client.Pipelines.Files.GetStatusCounts(parameters); Console.WriteLine(response); ``` #### Response ```json { "counts": { "foo": 0 }, "total_count": 0, "data_source_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "only_manually_uploaded": true, "pipeline_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e" } ``` ## Get Pipeline File Status `ManagedIngestionStatusResponse Pipelines.Files.GetStatus(FileGetStatusParamsparameters, CancellationTokencancellationToken = default)` **get** `/api/v1/pipelines/{pipeline_id}/files/{file_id}/status` Get status of a file for a pipeline. ### Parameters - `FileGetStatusParams parameters` - `required string pipelineID` - `required string fileID` ### Returns - `class ManagedIngestionStatusResponse:` - `required Status Status` Status of the ingestion. - `"CANCELLED"Cancelled` - `"ERROR"Error` - `"IN_PROGRESS"InProgress` - `"NOT_STARTED"NotStarted` - `"PARTIAL_SUCCESS"PartialSuccess` - `"SUCCESS"Success` - `DateTimeOffset? DeploymentDate` Date of the deployment. - `DateTimeOffset? EffectiveAt` When the status is effective - `IReadOnlyList? Error` List of errors that occurred during ingestion. - `required string JobID` ID of the job that failed. - `required string Message` List of errors that occurred during ingestion. - `required Step Step` Name of the job that failed. - `"DATA_SOURCE"DataSource` - `"FILE_UPDATER"FileUpdater` - `"INGESTION"Ingestion` - `"MANAGED_INGESTION"ManagedIngestion` - `"METADATA_UPDATE"MetadataUpdate` - `"PARSE"Parse` - `"TRANSFORM"Transform` - `string? JobID` ID of the latest job. ### Example ```csharp FileGetStatusParams parameters = new() { PipelineID = "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", FileID = "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", }; var managedIngestionStatusResponse = await client.Pipelines.Files.GetStatus(parameters); Console.WriteLine(managedIngestionStatusResponse); ``` #### Response ```json { "status": "CANCELLED", "deployment_date": "2019-12-27T18:11:19.117Z", "effective_at": "2019-12-27T18:11:19.117Z", "error": [ { "job_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "message": "message", "step": "DATA_SOURCE" } ], "job_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e" } ``` ## Add Files To Pipeline Api `IReadOnlyList Pipelines.Files.Create(FileCreateParamsparameters, CancellationTokencancellationToken = default)` **put** `/api/v1/pipelines/{pipeline_id}/files` Add files to a pipeline. ### Parameters - `FileCreateParams parameters` - `required string pipelineID` - `required IReadOnlyList body` - `required string FileID` The ID of the file - `IReadOnlyDictionary? CustomMetadata` Custom metadata for the file - `IReadOnlyDictionary` - `IReadOnlyList` - `string` - `Double` - `Boolean` ### Example ```csharp FileCreateParams parameters = new() { PipelineID = "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", Body = [ new() { FileID = "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", CustomMetadata = new Dictionary() { { "foo", new( new Dictionary() { { "foo", JsonSerializer.SerializeToElement("bar") } } ) }, }, }, ], }; var pipelineFiles = await client.Pipelines.Files.Create(parameters); Console.WriteLine(pipelineFiles); ``` #### Response ```json [ { "id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "pipeline_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "config_hash": { "foo": { "foo": "bar" } }, "created_at": "2019-12-27T18:11:19.117Z", "custom_metadata": { "foo": { "foo": "bar" } }, "data_source_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "external_file_id": "external_file_id", "file_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "file_size": 0, "file_type": "file_type", "indexed_page_count": 0, "last_modified_at": "2019-12-27T18:11:19.117Z", "name": "name", "permission_info": { "foo": { "foo": "bar" } }, "project_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "resource_info": { "foo": { "foo": "bar" } }, "status": "CANCELLED", "status_updated_at": "2019-12-27T18:11:19.117Z", "updated_at": "2019-12-27T18:11:19.117Z" } ] ``` ## Update Pipeline File `PipelineFile Pipelines.Files.Update(FileUpdateParamsparameters, CancellationTokencancellationToken = default)` **put** `/api/v1/pipelines/{pipeline_id}/files/{file_id}` Update a file for a pipeline. ### Parameters - `FileUpdateParams parameters` - `required string pipelineID` Path param - `required string fileID` Path param - `IReadOnlyDictionary? customMetadata` Body param: Custom metadata for the file - `IReadOnlyDictionary` - `IReadOnlyList` - `string` - `Double` - `Boolean` ### Returns - `class PipelineFile:` A file associated with a pipeline. - `required string ID` Unique identifier for the pipeline file. - `required string PipelineID` The ID of the pipeline that the file is associated with. - `IReadOnlyDictionary? ConfigHash` Hashes for the configuration of the pipeline. - `IReadOnlyDictionary` - `IReadOnlyList` - `string` - `Double` - `Boolean` - `DateTimeOffset? CreatedAt` When the pipeline file was created. - `IReadOnlyDictionary? CustomMetadata` Custom metadata for the file. - `IReadOnlyDictionary` - `IReadOnlyList` - `string` - `Double` - `Boolean` - `string? DataSourceID` The ID of the data source that the file belongs to. - `string? ExternalFileID` The ID of the file in the external system. - `string? FileID` The ID of the file. - `Long? FileSize` Size of the file in bytes. - `string? FileType` File type (e.g. pdf, docx, etc.). - `Long? IndexedPageCount` The number of pages that have been indexed for this file. - `DateTimeOffset? LastModifiedAt` The last modified time of the file. - `string? Name` Name of the file. - `IReadOnlyDictionary? PermissionInfo` Permission information for the file. - `IReadOnlyDictionary` - `IReadOnlyList` - `string` - `Double` - `Boolean` - `string? ProjectID` The ID of the project that the file belongs to. - `IReadOnlyDictionary? ResourceInfo` Resource information for the file. - `IReadOnlyDictionary` - `IReadOnlyList` - `string` - `Double` - `Boolean` - `Status? Status` Status of the pipeline file. - `"CANCELLED"Cancelled` - `"ERROR"Error` - `"IN_PROGRESS"InProgress` - `"NOT_STARTED"NotStarted` - `"SUCCESS"Success` - `DateTimeOffset? StatusUpdatedAt` The last time the status was updated. - `DateTimeOffset? UpdatedAt` When the pipeline file was last updated. ### Example ```csharp FileUpdateParams parameters = new() { PipelineID = "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", FileID = "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", }; var pipelineFile = await client.Pipelines.Files.Update(parameters); Console.WriteLine(pipelineFile); ``` #### Response ```json { "id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "pipeline_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "config_hash": { "foo": { "foo": "bar" } }, "created_at": "2019-12-27T18:11:19.117Z", "custom_metadata": { "foo": { "foo": "bar" } }, "data_source_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "external_file_id": "external_file_id", "file_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "file_size": 0, "file_type": "file_type", "indexed_page_count": 0, "last_modified_at": "2019-12-27T18:11:19.117Z", "name": "name", "permission_info": { "foo": { "foo": "bar" } }, "project_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "resource_info": { "foo": { "foo": "bar" } }, "status": "CANCELLED", "status_updated_at": "2019-12-27T18:11:19.117Z", "updated_at": "2019-12-27T18:11:19.117Z" } ``` ## Delete Pipeline File `Pipelines.Files.Delete(FileDeleteParamsparameters, CancellationTokencancellationToken = default)` **delete** `/api/v1/pipelines/{pipeline_id}/files/{file_id}` Delete a file from a pipeline. ### Parameters - `FileDeleteParams parameters` - `required string pipelineID` - `required string fileID` ### Example ```csharp FileDeleteParams parameters = new() { PipelineID = "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", FileID = "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", }; await client.Pipelines.Files.Delete(parameters); ``` ## List Pipeline Files2 `FileListPageResponse Pipelines.Files.List(FileListParamsparameters, CancellationTokencancellationToken = default)` **get** `/api/v1/pipelines/{pipeline_id}/files2` List files for a pipeline with optional filtering, sorting, and pagination. ### Parameters - `FileListParams parameters` - `required string pipelineID` - `string? dataSourceID` - `string? fileNameContains` - `Long? limit` - `Long? offset` - `Boolean onlyManuallyUploaded` - `string? orderBy` - `IReadOnlyList? statuses` Filter by file statuses - `"CANCELLED"Cancelled` - `"ERROR"Error` - `"IN_PROGRESS"InProgress` - `"NOT_STARTED"NotStarted` - `"SUCCESS"Success` ### Returns - `class FileListPageResponse:` Paginated list of pipeline files. - `required IReadOnlyList Files` The files to list - `required string ID` Unique identifier for the pipeline file. - `required string PipelineID` The ID of the pipeline that the file is associated with. - `IReadOnlyDictionary? ConfigHash` Hashes for the configuration of the pipeline. - `IReadOnlyDictionary` - `IReadOnlyList` - `string` - `Double` - `Boolean` - `DateTimeOffset? CreatedAt` When the pipeline file was created. - `IReadOnlyDictionary? CustomMetadata` Custom metadata for the file. - `IReadOnlyDictionary` - `IReadOnlyList` - `string` - `Double` - `Boolean` - `string? DataSourceID` The ID of the data source that the file belongs to. - `string? ExternalFileID` The ID of the file in the external system. - `string? FileID` The ID of the file. - `Long? FileSize` Size of the file in bytes. - `string? FileType` File type (e.g. pdf, docx, etc.). - `Long? IndexedPageCount` The number of pages that have been indexed for this file. - `DateTimeOffset? LastModifiedAt` The last modified time of the file. - `string? Name` Name of the file. - `IReadOnlyDictionary? PermissionInfo` Permission information for the file. - `IReadOnlyDictionary` - `IReadOnlyList` - `string` - `Double` - `Boolean` - `string? ProjectID` The ID of the project that the file belongs to. - `IReadOnlyDictionary? ResourceInfo` Resource information for the file. - `IReadOnlyDictionary` - `IReadOnlyList` - `string` - `Double` - `Boolean` - `Status? Status` Status of the pipeline file. - `"CANCELLED"Cancelled` - `"ERROR"Error` - `"IN_PROGRESS"InProgress` - `"NOT_STARTED"NotStarted` - `"SUCCESS"Success` - `DateTimeOffset? StatusUpdatedAt` The last time the status was updated. - `DateTimeOffset? UpdatedAt` When the pipeline file was last updated. - `required Long Limit` The limit of the files - `required Long Offset` The offset of the files - `required Long TotalCount` The total number of files ### Example ```csharp FileListParams parameters = new() { PipelineID = "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e" }; var page = await client.Pipelines.Files.List(parameters); await foreach (var item in page.Paginate()) { Console.WriteLine(item); } ``` #### Response ```json { "files": [ { "id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "pipeline_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "config_hash": { "foo": { "foo": "bar" } }, "created_at": "2019-12-27T18:11:19.117Z", "custom_metadata": { "foo": { "foo": "bar" } }, "data_source_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "external_file_id": "external_file_id", "file_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "file_size": 0, "file_type": "file_type", "indexed_page_count": 0, "last_modified_at": "2019-12-27T18:11:19.117Z", "name": "name", "permission_info": { "foo": { "foo": "bar" } }, "project_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "resource_info": { "foo": { "foo": "bar" } }, "status": "CANCELLED", "status_updated_at": "2019-12-27T18:11:19.117Z", "updated_at": "2019-12-27T18:11:19.117Z" } ], "limit": 0, "offset": 0, "total_count": 0 } ``` ## Domain Types ### Pipeline File - `class PipelineFile:` A file associated with a pipeline. - `required string ID` Unique identifier for the pipeline file. - `required string PipelineID` The ID of the pipeline that the file is associated with. - `IReadOnlyDictionary? ConfigHash` Hashes for the configuration of the pipeline. - `IReadOnlyDictionary` - `IReadOnlyList` - `string` - `Double` - `Boolean` - `DateTimeOffset? CreatedAt` When the pipeline file was created. - `IReadOnlyDictionary? CustomMetadata` Custom metadata for the file. - `IReadOnlyDictionary` - `IReadOnlyList` - `string` - `Double` - `Boolean` - `string? DataSourceID` The ID of the data source that the file belongs to. - `string? ExternalFileID` The ID of the file in the external system. - `string? FileID` The ID of the file. - `Long? FileSize` Size of the file in bytes. - `string? FileType` File type (e.g. pdf, docx, etc.). - `Long? IndexedPageCount` The number of pages that have been indexed for this file. - `DateTimeOffset? LastModifiedAt` The last modified time of the file. - `string? Name` Name of the file. - `IReadOnlyDictionary? PermissionInfo` Permission information for the file. - `IReadOnlyDictionary` - `IReadOnlyList` - `string` - `Double` - `Boolean` - `string? ProjectID` The ID of the project that the file belongs to. - `IReadOnlyDictionary? ResourceInfo` Resource information for the file. - `IReadOnlyDictionary` - `IReadOnlyList` - `string` - `Double` - `Boolean` - `Status? Status` Status of the pipeline file. - `"CANCELLED"Cancelled` - `"ERROR"Error` - `"IN_PROGRESS"InProgress` - `"NOT_STARTED"NotStarted` - `"SUCCESS"Success` - `DateTimeOffset? StatusUpdatedAt` The last time the status was updated. - `DateTimeOffset? UpdatedAt` When the pipeline file was last updated. # Metadata ## Import Pipeline Metadata `IReadOnlyDictionary Pipelines.Metadata.Create(MetadataCreateParamsparameters, CancellationTokencancellationToken = default)` **put** `/api/v1/pipelines/{pipeline_id}/metadata` Import metadata for a pipeline. ### Parameters - `MetadataCreateParams parameters` - `required string pipelineID` - `required string uploadFile` ### Example ```csharp MetadataCreateParams parameters = new() { PipelineID = "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", UploadFile = Encoding.UTF8.GetBytes("Example data"), }; var metadata = await client.Pipelines.Metadata.Create(parameters); Console.WriteLine(metadata); ``` #### Response ```json { "foo": "string" } ``` ## Delete Pipeline Files Metadata `Pipelines.Metadata.DeleteAll(MetadataDeleteAllParamsparameters, CancellationTokencancellationToken = default)` **delete** `/api/v1/pipelines/{pipeline_id}/metadata` Delete metadata for all files in a pipeline. ### Parameters - `MetadataDeleteAllParams parameters` - `required string pipelineID` ### Example ```csharp MetadataDeleteAllParams parameters = new() { PipelineID = "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e" }; await client.Pipelines.Metadata.DeleteAll(parameters); ``` # Documents ## Create Batch Pipeline Documents `IReadOnlyList Pipelines.Documents.Create(DocumentCreateParamsparameters, CancellationTokencancellationToken = default)` **post** `/api/v1/pipelines/{pipeline_id}/documents` Batch create documents for a pipeline. ### Parameters - `DocumentCreateParams parameters` - `required string pipelineID` - `required IReadOnlyList body` - `required IReadOnlyDictionary Metadata` - `required string Text` - `string? ID` - `IReadOnlyList ExcludedEmbedMetadataKeys` - `IReadOnlyList ExcludedLlmMetadataKeys` - `IReadOnlyList? PagePositions` indices in the CloudDocument.text where a new page begins. e.g. Second page starts at index specified by page_positions[1]. ### Example ```csharp DocumentCreateParams parameters = new() { PipelineID = "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", Body = [ new() { Metadata = new Dictionary() { { "foo", JsonSerializer.SerializeToElement("bar") } }, Text = "text", ID = "id", ExcludedEmbedMetadataKeys = [ "string" ], ExcludedLlmMetadataKeys = [ "string" ], PagePositions = [ 0 ], }, ], }; var cloudDocuments = await client.Pipelines.Documents.Create(parameters); Console.WriteLine(cloudDocuments); ``` #### Response ```json [ { "id": "id", "metadata": { "foo": "bar" }, "text": "text", "excluded_embed_metadata_keys": [ "string" ], "excluded_llm_metadata_keys": [ "string" ], "page_positions": [ 0 ], "status_metadata": { "foo": "bar" } } ] ``` ## Paginated List Pipeline Documents `DocumentListPageResponse Pipelines.Documents.List(DocumentListParamsparameters, CancellationTokencancellationToken = default)` **get** `/api/v1/pipelines/{pipeline_id}/documents/paginated` Return a list of documents for a pipeline. ### Parameters - `DocumentListParams parameters` - `required string pipelineID` - `string? fileID` - `Long limit` - `Boolean? onlyApiDataSourceDocuments` - `Boolean? onlyDirectUpload` - `Long skip` - `StatusRefreshPolicy statusRefreshPolicy` - `"cached"Cached` - `"ttl"Ttl` ### Returns - `class DocumentListPageResponse:` - `required IReadOnlyList Documents` The documents to list - `required string ID` - `required IReadOnlyDictionary Metadata` - `required string Text` - `IReadOnlyList ExcludedEmbedMetadataKeys` - `IReadOnlyList ExcludedLlmMetadataKeys` - `IReadOnlyList? PagePositions` indices in the CloudDocument.text where a new page begins. e.g. Second page starts at index specified by page_positions[1]. - `IReadOnlyDictionary? StatusMetadata` - `required Long Limit` The limit of the documents - `required Long Offset` The offset of the documents - `required Long TotalCount` The total number of documents ### Example ```csharp DocumentListParams parameters = new() { PipelineID = "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e" }; var page = await client.Pipelines.Documents.List(parameters); await foreach (var item in page.Paginate()) { Console.WriteLine(item); } ``` #### Response ```json { "documents": [ { "id": "id", "metadata": { "foo": "bar" }, "text": "text", "excluded_embed_metadata_keys": [ "string" ], "excluded_llm_metadata_keys": [ "string" ], "page_positions": [ 0 ], "status_metadata": { "foo": "bar" } } ], "limit": 0, "offset": 0, "total_count": 0 } ``` ## Get Pipeline Document `CloudDocument Pipelines.Documents.Get(DocumentGetParamsparameters, CancellationTokencancellationToken = default)` **get** `/api/v1/pipelines/{pipeline_id}/documents/{document_id}` Return a single document for a pipeline. ### Parameters - `DocumentGetParams parameters` - `required string pipelineID` - `required string documentID` ### Returns - `class CloudDocument:` Cloud document stored in S3. - `required string ID` - `required IReadOnlyDictionary Metadata` - `required string Text` - `IReadOnlyList ExcludedEmbedMetadataKeys` - `IReadOnlyList ExcludedLlmMetadataKeys` - `IReadOnlyList? PagePositions` indices in the CloudDocument.text where a new page begins. e.g. Second page starts at index specified by page_positions[1]. - `IReadOnlyDictionary? StatusMetadata` ### Example ```csharp DocumentGetParams parameters = new() { PipelineID = "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", DocumentID = "document_id", }; var cloudDocument = await client.Pipelines.Documents.Get(parameters); Console.WriteLine(cloudDocument); ``` #### Response ```json { "id": "id", "metadata": { "foo": "bar" }, "text": "text", "excluded_embed_metadata_keys": [ "string" ], "excluded_llm_metadata_keys": [ "string" ], "page_positions": [ 0 ], "status_metadata": { "foo": "bar" } } ``` ## Delete Pipeline Document `Pipelines.Documents.Delete(DocumentDeleteParamsparameters, CancellationTokencancellationToken = default)` **delete** `/api/v1/pipelines/{pipeline_id}/documents/{document_id}` Delete a document from a pipeline; runs async (vectors first, then MongoDB record). ### Parameters - `DocumentDeleteParams parameters` - `required string pipelineID` - `required string documentID` ### Example ```csharp DocumentDeleteParams parameters = new() { PipelineID = "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", DocumentID = "document_id", }; await client.Pipelines.Documents.Delete(parameters); ``` ## Get Pipeline Document Status `ManagedIngestionStatusResponse Pipelines.Documents.GetStatus(DocumentGetStatusParamsparameters, CancellationTokencancellationToken = default)` **get** `/api/v1/pipelines/{pipeline_id}/documents/{document_id}/status` Return a single document for a pipeline. ### Parameters - `DocumentGetStatusParams parameters` - `required string pipelineID` - `required string documentID` ### Returns - `class ManagedIngestionStatusResponse:` - `required Status Status` Status of the ingestion. - `"CANCELLED"Cancelled` - `"ERROR"Error` - `"IN_PROGRESS"InProgress` - `"NOT_STARTED"NotStarted` - `"PARTIAL_SUCCESS"PartialSuccess` - `"SUCCESS"Success` - `DateTimeOffset? DeploymentDate` Date of the deployment. - `DateTimeOffset? EffectiveAt` When the status is effective - `IReadOnlyList? Error` List of errors that occurred during ingestion. - `required string JobID` ID of the job that failed. - `required string Message` List of errors that occurred during ingestion. - `required Step Step` Name of the job that failed. - `"DATA_SOURCE"DataSource` - `"FILE_UPDATER"FileUpdater` - `"INGESTION"Ingestion` - `"MANAGED_INGESTION"ManagedIngestion` - `"METADATA_UPDATE"MetadataUpdate` - `"PARSE"Parse` - `"TRANSFORM"Transform` - `string? JobID` ID of the latest job. ### Example ```csharp DocumentGetStatusParams parameters = new() { PipelineID = "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", DocumentID = "document_id", }; var managedIngestionStatusResponse = await client.Pipelines.Documents.GetStatus(parameters); Console.WriteLine(managedIngestionStatusResponse); ``` #### Response ```json { "status": "CANCELLED", "deployment_date": "2019-12-27T18:11:19.117Z", "effective_at": "2019-12-27T18:11:19.117Z", "error": [ { "job_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "message": "message", "step": "DATA_SOURCE" } ], "job_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e" } ``` ## Sync Pipeline Document `JsonElement Pipelines.Documents.Sync(DocumentSyncParamsparameters, CancellationTokencancellationToken = default)` **post** `/api/v1/pipelines/{pipeline_id}/documents/{document_id}/sync` Sync a specific document for a pipeline. ### Parameters - `DocumentSyncParams parameters` - `required string pipelineID` - `required string documentID` ### Example ```csharp DocumentSyncParams parameters = new() { PipelineID = "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", DocumentID = "document_id", }; var response = await client.Pipelines.Documents.Sync(parameters); Console.WriteLine(response); ``` #### Response ```json {} ``` ## List Pipeline Document Chunks `IReadOnlyList Pipelines.Documents.GetChunks(DocumentGetChunksParamsparameters, CancellationTokencancellationToken = default)` **get** `/api/v1/pipelines/{pipeline_id}/documents/{document_id}/chunks` Return a list of chunks for a pipeline document. ### Parameters - `DocumentGetChunksParams parameters` - `required string pipelineID` - `required string documentID` ### Example ```csharp DocumentGetChunksParams parameters = new() { PipelineID = "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", DocumentID = "document_id", }; var textNodes = await client.Pipelines.Documents.GetChunks(parameters); Console.WriteLine(textNodes); ``` #### Response ```json [ { "class_name": "class_name", "embedding": [ 0 ], "end_char_idx": 0, "excluded_embed_metadata_keys": [ "string" ], "excluded_llm_metadata_keys": [ "string" ], "extra_info": { "foo": "bar" }, "id_": "id_", "metadata_seperator": "metadata_seperator", "metadata_template": "metadata_template", "mimetype": "mimetype", "relationships": { "foo": { "node_id": "node_id", "class_name": "class_name", "hash": "hash", "metadata": { "foo": "bar" }, "node_type": "1" } }, "start_char_idx": 0, "text": "text", "text_template": "text_template" } ] ``` ## Upsert Batch Pipeline Documents `IReadOnlyList Pipelines.Documents.Upsert(DocumentUpsertParamsparameters, CancellationTokencancellationToken = default)` **put** `/api/v1/pipelines/{pipeline_id}/documents` Batch create or update a document for a pipeline. ### Parameters - `DocumentUpsertParams parameters` - `required string pipelineID` - `required IReadOnlyList body` - `required IReadOnlyDictionary Metadata` - `required string Text` - `string? ID` - `IReadOnlyList ExcludedEmbedMetadataKeys` - `IReadOnlyList ExcludedLlmMetadataKeys` - `IReadOnlyList? PagePositions` indices in the CloudDocument.text where a new page begins. e.g. Second page starts at index specified by page_positions[1]. ### Example ```csharp DocumentUpsertParams parameters = new() { PipelineID = "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", Body = [ new() { Metadata = new Dictionary() { { "foo", JsonSerializer.SerializeToElement("bar") } }, Text = "text", ID = "id", ExcludedEmbedMetadataKeys = [ "string" ], ExcludedLlmMetadataKeys = [ "string" ], PagePositions = [ 0 ], }, ], }; var cloudDocuments = await client.Pipelines.Documents.Upsert(parameters); Console.WriteLine(cloudDocuments); ``` #### Response ```json [ { "id": "id", "metadata": { "foo": "bar" }, "text": "text", "excluded_embed_metadata_keys": [ "string" ], "excluded_llm_metadata_keys": [ "string" ], "page_positions": [ 0 ], "status_metadata": { "foo": "bar" } } ] ``` ## Domain Types ### Cloud Document - `class CloudDocument:` Cloud document stored in S3. - `required string ID` - `required IReadOnlyDictionary Metadata` - `required string Text` - `IReadOnlyList ExcludedEmbedMetadataKeys` - `IReadOnlyList ExcludedLlmMetadataKeys` - `IReadOnlyList? PagePositions` indices in the CloudDocument.text where a new page begins. e.g. Second page starts at index specified by page_positions[1]. - `IReadOnlyDictionary? StatusMetadata` ### Cloud Document Create - `class CloudDocumentCreate:` Create a new cloud document. - `required IReadOnlyDictionary Metadata` - `required string Text` - `string? ID` - `IReadOnlyList ExcludedEmbedMetadataKeys` - `IReadOnlyList ExcludedLlmMetadataKeys` - `IReadOnlyList? PagePositions` indices in the CloudDocument.text where a new page begins. e.g. Second page starts at index specified by page_positions[1]. ### Text Node - `class TextNode:` Provided for backward compatibility. - `string ClassName` - `IReadOnlyList? Embedding` Embedding of the node. - `Long? EndCharIdx` End char index of the node. - `IReadOnlyList ExcludedEmbedMetadataKeys` Metadata keys that are excluded from text for the embed model. - `IReadOnlyList ExcludedLlmMetadataKeys` Metadata keys that are excluded from text for the LLM. - `IReadOnlyDictionary ExtraInfo` A flat dictionary of metadata fields - `string ID` Unique ID of the node. - `string MetadataSeperator` Separator between metadata fields when converting to string. - `string MetadataTemplate` Template for how metadata is formatted, with {key} and {value} placeholders. - `string Mimetype` MIME type of the node content. - `IReadOnlyDictionary Relationships` A mapping of relationships to other node information. - `class RelatedNodeInfo:` - `required string NodeID` - `string ClassName` - `string? Hash` - `IReadOnlyDictionary Metadata` - `NodeType? NodeType` - `"1"1` - `"2"2` - `"3"3` - `"4"4` - `"5"5` - `IReadOnlyList` - `required string NodeID` - `string ClassName` - `string? Hash` - `IReadOnlyDictionary Metadata` - `NodeType? NodeType` - `"1"1` - `"2"2` - `"3"3` - `"4"4` - `"5"5` - `Long? StartCharIdx` Start char index of the node. - `string Text` Text content of the node. - `string TextTemplate` Template for how text is formatted, with {content} and {metadata_str} placeholders.