Skip to content

Pipelines

Search Pipelines
Deprecated
IReadOnlyList<Pipeline> Pipelines.List(PipelineListParams?parameters, CancellationTokencancellationToken = default)
GET/api/v1/pipelines
Create Pipeline
Deprecated
Pipeline Pipelines.Create(PipelineCreateParamsparameters, CancellationTokencancellationToken = default)
POST/api/v1/pipelines
Get Pipeline
Deprecated
Pipeline Pipelines.Get(PipelineGetParamsparameters, CancellationTokencancellationToken = default)
GET/api/v1/pipelines/{pipeline_id}
Update Existing Pipeline
Deprecated
Pipeline Pipelines.Update(PipelineUpdateParamsparameters, CancellationTokencancellationToken = default)
PUT/api/v1/pipelines/{pipeline_id}
Delete Pipeline
Deprecated
Pipelines.Delete(PipelineDeleteParamsparameters, CancellationTokencancellationToken = default)
DELETE/api/v1/pipelines/{pipeline_id}
Get Pipeline Status
Deprecated
ManagedIngestionStatusResponse Pipelines.GetStatus(PipelineGetStatusParamsparameters, CancellationTokencancellationToken = default)
GET/api/v1/pipelines/{pipeline_id}/status
Upsert Pipeline
Deprecated
Pipeline Pipelines.Upsert(PipelineUpsertParamsparameters, CancellationTokencancellationToken = default)
PUT/api/v1/pipelines
Run Search
Deprecated
PipelineRetrieveResponse Pipelines.Retrieve(PipelineRetrieveParamsparameters, CancellationTokencancellationToken = default)
POST/api/v1/pipelines/{pipeline_id}/retrieve
ModelsExpand Collapse
class AdvancedModeTransformConfig:
ChunkingConfig ChunkingConfig

Configuration for the chunking.

One of the following:
class NoneChunkingConfig:
Mode Mode
class CharacterChunkingConfig:
Long ChunkOverlap
Long ChunkSize
Mode Mode
class TokenChunkingConfig:
Long ChunkOverlap
Long ChunkSize
Mode Mode
string Separator
class SentenceChunkingConfig:
Long ChunkOverlap
Long ChunkSize
Mode Mode
string ParagraphSeparator
string Separator
class SemanticChunkingConfig:
Long BreakpointPercentileThreshold
Long BufferSize
Mode Mode
Mode Mode
SegmentationConfig SegmentationConfig

Configuration for the segmentation.

One of the following:
class NoneSegmentationConfig:
Mode Mode
class PageSegmentationConfig:
Mode Mode
string PageSeparator
class ElementSegmentationConfig:
Mode Mode
class AutoTransformConfig:
Long ChunkOverlap

Chunk overlap for the transformation.

Long ChunkSize

Chunk size for the transformation.

exclusiveMinimum0
Mode Mode
class AzureOpenAIEmbedding:
IReadOnlyDictionary<string, JsonElement> 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<string, string>? 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.

exclusiveMinimum0
maximum2048
Long MaxRetries

Maximum number of retries.

minimum0
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.

minimum0
class AzureOpenAIEmbeddingConfig:

Configuration for the Azure OpenAI embedding model.

IReadOnlyDictionary<string, JsonElement> 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<string, string>? 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.

exclusiveMinimum0
maximum2048
Long MaxRetries

Maximum number of retries.

minimum0
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.

minimum0
Type Type

Type of the embedding model.

class BedrockEmbedding:
IReadOnlyDictionary<string, JsonElement> 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.

exclusiveMinimum0
maximum2048
Long MaxRetries

The maximum number of API retries.

exclusiveMinimum0
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.

class BedrockEmbeddingConfig:

Configuration for the Bedrock embedding model.

IReadOnlyDictionary<string, JsonElement> 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.

exclusiveMinimum0
maximum2048
Long MaxRetries

The maximum number of API retries.

exclusiveMinimum0
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.

class CohereEmbedding:
required string? ApiKey

The Cohere API key.

string ClassName
Long EmbedBatchSize

The batch size for embedding calls.

exclusiveMinimum0
maximum2048
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

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.

exclusiveMinimum0
maximum2048
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.

class DataSinkCreate:

Schema for creating a data sink.

required Component Component

Component that implements the data sink

One of the following:
IReadOnlyDictionary<string, JsonElement>
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

formatpassword
required string IndexName
string ClassName
IReadOnlyDictionary<string, JsonElement>? InsertKwargs
string? Namespace
SupportsNestedMetadataFilters SupportsNestedMetadataFilters
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.

One of the following:
"cosine"Cosine
"hamming"Hamming
"ip"IP
"jaccard"Jaccard
"l1"L1
"l2"L2
Long EfConstruction

The number of edges to use during the construction phase.

minimum1

The number of edges to use during the search phase.

minimum1
Long M

The number of bi-directional links created for each new element.

minimum1
VectorType VectorType

The type of vector to use.

One of the following:
"bit"Bit
"half_vec"HalfVec
"sparse_vec"SparseVec
"vector"Vector
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<string, JsonElement> ClientKwargs
Long MaxRetries
SupportsNestedMetadataFilters SupportsNestedMetadataFilters
class CloudAzureAISearchVectorStore:

Cloud Azure AI Search Vector Store.

required string SearchServiceApiKey
required string SearchServiceEndpoint
string ClassName
string? ClientID
string? ClientSecret
Long? EmbeddingDimension
IReadOnlyDictionary<string, JsonElement>? FilterableMetadataFieldKeys
string? IndexName
string? SearchServiceApiVersion
SupportsNestedMetadataFilters SupportsNestedMetadataFilters
string? TenantID

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

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

formatpassword
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
required string Name

The name of the data sink.

required SinkType SinkType
One of the following:
"ASTRA_DB"AstraDB
"AZUREAI_SEARCH"AzureaiSearch
"MILVUS"Milvus
"MONGODB_ATLAS"MongoDBAtlas
"PINECONE"Pinecone
"POSTGRES"Postgres
"QDRANT"Qdrant
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.

exclusiveMinimum0
maximum2048
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.

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.

exclusiveMinimum0
maximum2048
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.

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.

One of the following:
string
Boolean
string ClassName
IReadOnlyDictionary<string, string>? Cookies

Additional cookies to send to the server.

Long EmbedBatchSize

The batch size for embedding calls.

exclusiveMinimum0
maximum2048
IReadOnlyDictionary<string, string>? 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.

One of the following:
"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.

class HuggingFaceInferenceApiEmbeddingConfig:

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.

One of the following:
string
Boolean
string ClassName
IReadOnlyDictionary<string, string>? Cookies

Additional cookies to send to the server.

Long EmbedBatchSize

The batch size for embedding calls.

exclusiveMinimum0
maximum2048
IReadOnlyDictionary<string, string>? 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.

One of the following:
"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.

class LlamaParseParameters:
Boolean? AdaptiveLongTable
Boolean? AggressiveTableExtraction
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>? ImagesToSave
One of the following:
"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<ParsingLanguages> Languages
One of the following:
"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? PageHeaderPrefix
string? PageHeaderSuffix
string? PagePrefix
string? PageSeparator
string? PageSuffix
ParsingMode? ParseMode

Enum for representing the mode of parsing to be used.

One of the following:
"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.

One of the following:
"critical"Critical
"high"High
"low"Low
"medium"Medium
string? ProjectID
Boolean? RemoveHiddenText
FailPageMode? ReplaceFailedPageMode

Enum for representing the different available page error handling modes.

One of the following:
"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<WebhookConfiguration>? WebhookConfigurations

Outbound webhook endpoints to notify on job status changes

IReadOnlyList<WebhookEvent>? WebhookEvents

Events to subscribe to (e.g. ‘parse.success’, ‘extract.error’). If null, all events are delivered.

One of the following:
"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<string, string>? 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
class LlmParameters:
string ClassName
ModelName ModelName

The name of the model to use for LLM completions.

One of the following:
"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.

maxLength3000
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.

class ManagedIngestionStatusResponse:
required Status Status

Status of the ingestion.

One of the following:
"CANCELLED"Cancelled
"ERROR"Error
"IN_PROGRESS"InProgress
"NOT_STARTED"NotStarted
"PARTIAL_SUCCESS"PartialSuccess
"SUCCESS"Success
DateTimeOffset? DeploymentDate

Date of the deployment.

formatdate-time
DateTimeOffset? EffectiveAt

When the status is effective

formatdate-time
IReadOnlyList<Error>? Error

List of errors that occurred during ingestion.

required string JobID

ID of the job that failed.

formatuuid
required string Message

List of errors that occurred during ingestion.

required Step Step

Name of the job that failed.

One of the following:
"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.

formatuuid
enum MessageRole:

Message role.

"assistant"Assistant
"chatbot"Chatbot
"developer"Developer
"function"Function
"model"Model
"system"System
"tool"Tool
"user"User
class MetadataFilters:

Metadata filters for vector stores.

required IReadOnlyList<Filter> Filters
One of the following:
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
One of the following:
Double
string
IReadOnlyList<string>
IReadOnlyList<Double>
IReadOnlyList<Long>
Operator Operator

Vector store filter operator.

One of the following:
"!="
"<"
"<="
"=="
">"
">="
"all"All
"any"Any
"contains"Contains
"in"In
"is_empty"IsEmpty
"nin"Nin
"text_match"TextMatch
"text_match_insensitive"TextMatchInsensitive
MetadataFilters
Condition? Condition

Vector store filter conditions to combine different filters.

One of the following:
"and"And
"not"Not
"or"Or
class OpenAIEmbedding:
IReadOnlyDictionary<string, JsonElement> 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<string, string>? 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.

exclusiveMinimum0
maximum2048
Long MaxRetries

Maximum number of retries.

minimum0
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.

minimum0
class OpenAIEmbeddingConfig:
OpenAIEmbedding Component

Configuration for the OpenAI embedding model.

IReadOnlyDictionary<string, JsonElement> 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<string, string>? 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.

exclusiveMinimum0
maximum2048
Long MaxRetries

Maximum number of retries.

minimum0
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.

minimum0
Type Type

Type of the embedding model.

class PageFigureNodeWithScore:

Page figure metadata with score

required Node Node
required Double Confidence

The confidence of the figure

maximum1
minimum0
required string FigureName

The name of the figure

required Long FigureSize

The size of the figure in bytes

minimum0
required string FileID

The ID of the file that the figure was taken from

formatuuid
required Long PageIndex

The index of the page for which the figure is taken (0-indexed)

minimum0
Boolean IsLikelyNoise

Whether the figure is likely to be noise

IReadOnlyDictionary<string, JsonElement>? Metadata

Metadata for the figure

required Double Score

The score of the figure node

string ClassName
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

formatuuid
required Long ImageSize

The size of the image in bytes

minimum0
required Long PageIndex

The index of the page for which the screenshot is taken (0-indexed)

minimum0
IReadOnlyDictionary<string, JsonElement>? Metadata

Metadata for the screenshot

required Double Score

The score of the screenshot node

string ClassName
class Pipeline:

Schema for a pipeline.

required string ID

Unique identifier

formatuuid
required EmbeddingConfig EmbeddingConfig
One of the following:
class AzureOpenAIEmbeddingConfig:

Configuration for the Azure OpenAI embedding model.

IReadOnlyDictionary<string, JsonElement> 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<string, string>? 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.

exclusiveMinimum0
maximum2048
Long MaxRetries

Maximum number of retries.

minimum0
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.

minimum0
Type Type

Type of the embedding model.

class BedrockEmbeddingConfig:

Configuration for the Bedrock embedding model.

IReadOnlyDictionary<string, JsonElement> 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.

exclusiveMinimum0
maximum2048
Long MaxRetries

The maximum number of API retries.

exclusiveMinimum0
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.

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.

exclusiveMinimum0
maximum2048
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.

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.

exclusiveMinimum0
maximum2048
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.

class HuggingFaceInferenceApiEmbeddingConfig:

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.

One of the following:
string
Boolean
string ClassName
IReadOnlyDictionary<string, string>? Cookies

Additional cookies to send to the server.

Long EmbedBatchSize

The batch size for embedding calls.

exclusiveMinimum0
maximum2048
IReadOnlyDictionary<string, string>? 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.

One of the following:
"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.

class ManagedOpenAIEmbedding:
Component Component

Configuration for the Managed OpenAI embedding model.

string ClassName
Long EmbedBatchSize

The batch size for embedding calls.

exclusiveMinimum0
maximum2048
ModelName ModelName

The name of the OpenAI embedding model.

Long? NumWorkers

The number of workers to use for async embedding calls.

Type Type

Type of the embedding model.

class OpenAIEmbeddingConfig:
OpenAIEmbedding Component

Configuration for the OpenAI embedding model.

IReadOnlyDictionary<string, JsonElement> 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<string, string>? 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.

exclusiveMinimum0
maximum2048
Long MaxRetries

Maximum number of retries.

minimum0
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.

minimum0
Type Type

Type of the embedding model.

class VertexAIEmbeddingConfig:

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<string, JsonElement> AdditionalKwargs

Additional kwargs for the Vertex.

string ClassName
Long EmbedBatchSize

The batch size for embedding calls.

exclusiveMinimum0
maximum2048
EmbedMode EmbedMode

The embedding mode to use.

One of the following:
"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.

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

formatdate-time
DataSink? DataSink

Schema for a data sink.

required string ID

Unique identifier

formatuuid
required Component Component

Component that implements the data sink

One of the following:
IReadOnlyDictionary<string, JsonElement>
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

formatpassword
required string IndexName
string ClassName
IReadOnlyDictionary<string, JsonElement>? InsertKwargs
string? Namespace
SupportsNestedMetadataFilters SupportsNestedMetadataFilters
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.

One of the following:
"cosine"Cosine
"hamming"Hamming
"ip"IP
"jaccard"Jaccard
"l1"L1
"l2"L2
Long EfConstruction

The number of edges to use during the construction phase.

minimum1

The number of edges to use during the search phase.

minimum1
Long M

The number of bi-directional links created for each new element.

minimum1
VectorType VectorType

The type of vector to use.

One of the following:
"bit"Bit
"half_vec"HalfVec
"sparse_vec"SparseVec
"vector"Vector
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<string, JsonElement> ClientKwargs
Long MaxRetries
SupportsNestedMetadataFilters SupportsNestedMetadataFilters
class CloudAzureAISearchVectorStore:

Cloud Azure AI Search Vector Store.

required string SearchServiceApiKey
required string SearchServiceEndpoint
string ClassName
string? ClientID
string? ClientSecret
Long? EmbeddingDimension
IReadOnlyDictionary<string, JsonElement>? FilterableMetadataFieldKeys
string? IndexName
string? SearchServiceApiVersion
SupportsNestedMetadataFilters SupportsNestedMetadataFilters
string? TenantID

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

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

formatpassword
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
required string Name

The name of the data sink.

required string ProjectID
required SinkType SinkType
One of the following:
"ASTRA_DB"AstraDB
"AZUREAI_SEARCH"AzureaiSearch
"MILVUS"Milvus
"MONGODB_ATLAS"MongoDBAtlas
"PINECONE"Pinecone
"POSTGRES"Postgres
"QDRANT"Qdrant
DateTimeOffset? CreatedAt

Creation datetime

formatdate-time
DateTimeOffset? UpdatedAt

Update datetime

formatdate-time
EmbeddingModelConfig? EmbeddingModelConfig

Schema for an embedding model config.

required string ID

Unique identifier

formatuuid
required EmbeddingConfig EmbeddingConfig

The embedding configuration for the embedding model config.

One of the following:
class AzureOpenAIEmbeddingConfig:

Configuration for the Azure OpenAI embedding model.

IReadOnlyDictionary<string, JsonElement> 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<string, string>? 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.

exclusiveMinimum0
maximum2048
Long MaxRetries

Maximum number of retries.

minimum0
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.

minimum0
Type Type

Type of the embedding model.

class BedrockEmbeddingConfig:

Configuration for the Bedrock embedding model.

IReadOnlyDictionary<string, JsonElement> 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.

exclusiveMinimum0
maximum2048
Long MaxRetries

The maximum number of API retries.

exclusiveMinimum0
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.

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.

exclusiveMinimum0
maximum2048
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.

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.

exclusiveMinimum0
maximum2048
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.

class HuggingFaceInferenceApiEmbeddingConfig:

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.

One of the following:
string
Boolean
string ClassName
IReadOnlyDictionary<string, string>? Cookies

Additional cookies to send to the server.

Long EmbedBatchSize

The batch size for embedding calls.

exclusiveMinimum0
maximum2048
IReadOnlyDictionary<string, string>? 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.

One of the following:
"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.

class OpenAIEmbeddingConfig:
OpenAIEmbedding Component

Configuration for the OpenAI embedding model.

IReadOnlyDictionary<string, JsonElement> 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<string, string>? 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.

exclusiveMinimum0
maximum2048
Long MaxRetries

Maximum number of retries.

minimum0
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.

minimum0
Type Type

Type of the embedding model.

class VertexAIEmbeddingConfig:

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<string, JsonElement> AdditionalKwargs

Additional kwargs for the Vertex.

string ClassName
Long EmbedBatchSize

The batch size for embedding calls.

exclusiveMinimum0
maximum2048
EmbedMode EmbedMode

The embedding mode to use.

One of the following:
"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.

required string Name

The name of the embedding model config.

required string ProjectID
DateTimeOffset? CreatedAt

Creation datetime

formatdate-time
DateTimeOffset? UpdatedAt

Update datetime

formatdate-time
string? EmbeddingModelConfigID

The ID of the EmbeddingModelConfig this pipeline is using.

formatuuid
LlamaParseParameters? LlamaParseParameters

Settings that can be configured for how to use LlamaParse to parse files within a LlamaCloud pipeline.

Boolean? AdaptiveLongTable
Boolean? AggressiveTableExtraction
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>? ImagesToSave
One of the following:
"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<ParsingLanguages> Languages
One of the following:
"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? PageHeaderPrefix
string? PageHeaderSuffix
string? PagePrefix
string? PageSeparator
string? PageSuffix
ParsingMode? ParseMode

Enum for representing the mode of parsing to be used.

One of the following:
"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.

One of the following:
"critical"Critical
"high"High
"low"Low
"medium"Medium
string? ProjectID
Boolean? RemoveHiddenText
FailPageMode? ReplaceFailedPageMode

Enum for representing the different available page error handling modes.

One of the following:
"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<WebhookConfiguration>? WebhookConfigurations

Outbound webhook endpoints to notify on job status changes

IReadOnlyList<WebhookEvent>? WebhookEvents

Events to subscribe to (e.g. ‘parse.success’, ‘extract.error’). If null, all events are delivered.

One of the following:
"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<string, string>? 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.

formatuuid
PipelineMetadataConfig? MetadataConfig

Metadata configuration for the pipeline.

IReadOnlyList<string> ExcludedEmbedMetadataKeys

List of metadata keys to exclude from embeddings

IReadOnlyList<string> ExcludedLlmMetadataKeys

List of metadata keys to exclude from LLM during retrieval

PipelineType PipelineType

Type of pipeline. Either PLAYGROUND or MANAGED.

One of the following:
"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.

maximum1
minimum0
string ClassName
Double? DenseSimilarityCutoff

Minimum similarity score wrt query for retrieval

maximum1
minimum0
Long? DenseSimilarityTopK

Number of nodes for dense retrieval.

maximum100
minimum1
Boolean? EnableReranking

Enable reranking for retrieval

Long? FilesTopK

Number of files to retrieve (only for retrieval mode files_via_metadata and files_via_content).

maximum5
minimum1
Long? RerankTopN

Number of reranked nodes for returning.

maximum100
minimum1
RetrievalMode RetrievalMode

The retrieval mode for the query.

One of the following:
"auto_routed"AutoRouted
"chunks"Chunks
"files_via_content"FilesViaContent
"files_via_metadata"FilesViaMetadata
DeprecatedBoolean 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<Filter> Filters
One of the following:
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
One of the following:
Double
string
IReadOnlyList<string>
IReadOnlyList<Double>
IReadOnlyList<Long>
Operator Operator

Vector store filter operator.

One of the following:
"!="
"<"
"<="
"=="
">"
">="
"all"All
"any"Any
"contains"Contains
"in"In
"is_empty"IsEmpty
"nin"Nin
"text_match"TextMatch
"text_match_insensitive"TextMatchInsensitive
MetadataFilters
Condition? Condition

Vector store filter conditions to combine different filters.

One of the following:
"and"And
"not"Not
"or"Or
IReadOnlyDictionary<string, SearchFiltersInferenceSchema?>? SearchFiltersInferenceSchema

JSON Schema that will be used to infer search_filters. Omit or leave as null to skip inference.

One of the following:
IReadOnlyDictionary<string, JsonElement>
IReadOnlyList<JsonElement>
string
Double
Boolean
Long? SparseSimilarityTopK

Number of nodes for sparse retrieval.

maximum100
minimum1
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).

One of the following:
"auto"Auto
"bm25"Bm25
"splade"Splade
Status? Status

Status of the pipeline.

One of the following:
"CREATED"Created
"DELETING"Deleting
TransformConfig TransformConfig

Configuration for the transformation.

One of the following:
class AutoTransformConfig:
Long ChunkOverlap

Chunk overlap for the transformation.

Long ChunkSize

Chunk size for the transformation.

exclusiveMinimum0
Mode Mode
class AdvancedModeTransformConfig:
ChunkingConfig ChunkingConfig

Configuration for the chunking.

One of the following:
class NoneChunkingConfig:
Mode Mode
class CharacterChunkingConfig:
Long ChunkOverlap
Long ChunkSize
Mode Mode
class TokenChunkingConfig:
Long ChunkOverlap
Long ChunkSize
Mode Mode
string Separator
class SentenceChunkingConfig:
Long ChunkOverlap
Long ChunkSize
Mode Mode
string ParagraphSeparator
string Separator
class SemanticChunkingConfig:
Long BreakpointPercentileThreshold
Long BufferSize
Mode Mode
Mode Mode
SegmentationConfig SegmentationConfig

Configuration for the segmentation.

One of the following:
class NoneSegmentationConfig:
Mode Mode
class PageSegmentationConfig:
Mode Mode
string PageSeparator
class ElementSegmentationConfig:
Mode Mode
DateTimeOffset? UpdatedAt

Update datetime

formatdate-time
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

One of the following:
IReadOnlyDictionary<string, JsonElement>
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

formatpassword
required string IndexName
string ClassName
IReadOnlyDictionary<string, JsonElement>? InsertKwargs
string? Namespace
SupportsNestedMetadataFilters SupportsNestedMetadataFilters
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.

One of the following:
"cosine"Cosine
"hamming"Hamming
"ip"IP
"jaccard"Jaccard
"l1"L1
"l2"L2
Long EfConstruction

The number of edges to use during the construction phase.

minimum1

The number of edges to use during the search phase.

minimum1
Long M

The number of bi-directional links created for each new element.

minimum1
VectorType VectorType

The type of vector to use.

One of the following:
"bit"Bit
"half_vec"HalfVec
"sparse_vec"SparseVec
"vector"Vector
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<string, JsonElement> ClientKwargs
Long MaxRetries
SupportsNestedMetadataFilters SupportsNestedMetadataFilters
class CloudAzureAISearchVectorStore:

Cloud Azure AI Search Vector Store.

required string SearchServiceApiKey
required string SearchServiceEndpoint
string ClassName
string? ClientID
string? ClientSecret
Long? EmbeddingDimension
IReadOnlyDictionary<string, JsonElement>? FilterableMetadataFieldKeys
string? IndexName
string? SearchServiceApiVersion
SupportsNestedMetadataFilters SupportsNestedMetadataFilters
string? TenantID

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

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

formatpassword
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
required string Name

The name of the data sink.

required SinkType SinkType
One of the following:
"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.

formatuuid
EmbeddingConfig? EmbeddingConfig
One of the following:
class AzureOpenAIEmbeddingConfig:

Configuration for the Azure OpenAI embedding model.

IReadOnlyDictionary<string, JsonElement> 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<string, string>? 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.

exclusiveMinimum0
maximum2048
Long MaxRetries

Maximum number of retries.

minimum0
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.

minimum0
Type Type

Type of the embedding model.

class BedrockEmbeddingConfig:

Configuration for the Bedrock embedding model.

IReadOnlyDictionary<string, JsonElement> 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.

exclusiveMinimum0
maximum2048
Long MaxRetries

The maximum number of API retries.

exclusiveMinimum0
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.

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.

exclusiveMinimum0
maximum2048
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.

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.

exclusiveMinimum0
maximum2048
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.

class HuggingFaceInferenceApiEmbeddingConfig:

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.

One of the following:
string
Boolean
string ClassName
IReadOnlyDictionary<string, string>? Cookies

Additional cookies to send to the server.

Long EmbedBatchSize

The batch size for embedding calls.

exclusiveMinimum0
maximum2048
IReadOnlyDictionary<string, string>? 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.

One of the following:
"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.

class OpenAIEmbeddingConfig:
OpenAIEmbedding Component

Configuration for the OpenAI embedding model.

IReadOnlyDictionary<string, JsonElement> 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<string, string>? 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.

exclusiveMinimum0
maximum2048
Long MaxRetries

Maximum number of retries.

minimum0
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.

minimum0
Type Type

Type of the embedding model.

class VertexAIEmbeddingConfig:

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<string, JsonElement> AdditionalKwargs

Additional kwargs for the Vertex.

string ClassName
Long EmbedBatchSize

The batch size for embedding calls.

exclusiveMinimum0
maximum2048
EmbedMode EmbedMode

The embedding mode to use.

One of the following:
"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.

string? EmbeddingModelConfigID

Embedding model config ID. When provided instead of embedding_config, the embedding model config will be looked up by ID.

formatuuid
LlamaParseParameters LlamaParseParameters

Settings that can be configured for how to use LlamaParse to parse files within a LlamaCloud pipeline.

Boolean? AdaptiveLongTable
Boolean? AggressiveTableExtraction
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>? ImagesToSave
One of the following:
"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<ParsingLanguages> Languages
One of the following:
"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? PageHeaderPrefix
string? PageHeaderSuffix
string? PagePrefix
string? PageSeparator
string? PageSuffix
ParsingMode? ParseMode

Enum for representing the mode of parsing to be used.

One of the following:
"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.

One of the following:
"critical"Critical
"high"High
"low"Low
"medium"Medium
string? ProjectID
Boolean? RemoveHiddenText
FailPageMode? ReplaceFailedPageMode

Enum for representing the different available page error handling modes.

One of the following:
"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<WebhookConfiguration>? WebhookConfigurations

Outbound webhook endpoints to notify on job status changes

IReadOnlyList<WebhookEvent>? WebhookEvents

Events to subscribe to (e.g. ‘parse.success’, ‘extract.error’). If null, all events are delivered.

One of the following:
"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<string, string>? 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.

formatuuid
PipelineMetadataConfig? MetadataConfig

Metadata configuration for the pipeline.

IReadOnlyList<string> ExcludedEmbedMetadataKeys

List of metadata keys to exclude from embeddings

IReadOnlyList<string> ExcludedLlmMetadataKeys

List of metadata keys to exclude from LLM during retrieval

PipelineType PipelineType

Type of pipeline. Either PLAYGROUND or MANAGED.

One of the following:
"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.

maximum1
minimum0
string ClassName
Double? DenseSimilarityCutoff

Minimum similarity score wrt query for retrieval

maximum1
minimum0
Long? DenseSimilarityTopK

Number of nodes for dense retrieval.

maximum100
minimum1
Boolean? EnableReranking

Enable reranking for retrieval

Long? FilesTopK

Number of files to retrieve (only for retrieval mode files_via_metadata and files_via_content).

maximum5
minimum1
Long? RerankTopN

Number of reranked nodes for returning.

maximum100
minimum1
RetrievalMode RetrievalMode

The retrieval mode for the query.

One of the following:
"auto_routed"AutoRouted
"chunks"Chunks
"files_via_content"FilesViaContent
"files_via_metadata"FilesViaMetadata
DeprecatedBoolean 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<Filter> Filters
One of the following:
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
One of the following:
Double
string
IReadOnlyList<string>
IReadOnlyList<Double>
IReadOnlyList<Long>
Operator Operator

Vector store filter operator.

One of the following:
"!="
"<"
"<="
"=="
">"
">="
"all"All
"any"Any
"contains"Contains
"in"In
"is_empty"IsEmpty
"nin"Nin
"text_match"TextMatch
"text_match_insensitive"TextMatchInsensitive
MetadataFilters
Condition? Condition

Vector store filter conditions to combine different filters.

One of the following:
"and"And
"not"Not
"or"Or
IReadOnlyDictionary<string, SearchFiltersInferenceSchema?>? SearchFiltersInferenceSchema

JSON Schema that will be used to infer search_filters. Omit or leave as null to skip inference.

One of the following:
IReadOnlyDictionary<string, JsonElement>
IReadOnlyList<JsonElement>
string
Double
Boolean
Long? SparseSimilarityTopK

Number of nodes for sparse retrieval.

maximum100
minimum1
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).

One of the following:
"auto"Auto
"bm25"Bm25
"splade"Splade
string? Status

Status of the pipeline deployment.

TransformConfig? TransformConfig

Configuration for the transformation.

One of the following:
class AutoTransformConfig:
Long ChunkOverlap

Chunk overlap for the transformation.

Long ChunkSize

Chunk size for the transformation.

exclusiveMinimum0
Mode Mode
class AdvancedModeTransformConfig:
ChunkingConfig ChunkingConfig

Configuration for the chunking.

One of the following:
class NoneChunkingConfig:
Mode Mode
class CharacterChunkingConfig:
Long ChunkOverlap
Long ChunkSize
Mode Mode
class TokenChunkingConfig:
Long ChunkOverlap
Long ChunkSize
Mode Mode
string Separator
class SentenceChunkingConfig:
Long ChunkOverlap
Long ChunkSize
Mode Mode
string ParagraphSeparator
string Separator
class SemanticChunkingConfig:
Long BreakpointPercentileThreshold
Long BufferSize
Mode Mode
Mode Mode
SegmentationConfig SegmentationConfig

Configuration for the segmentation.

One of the following:
class NoneSegmentationConfig:
Mode Mode
class PageSegmentationConfig:
Mode Mode
string PageSeparator
class ElementSegmentationConfig:
Mode Mode
class PipelineMetadataConfig:
IReadOnlyList<string> ExcludedEmbedMetadataKeys

List of metadata keys to exclude from embeddings

IReadOnlyList<string> ExcludedLlmMetadataKeys

List of metadata keys to exclude from LLM during retrieval

enum PipelineType:

Enum for representing the type of a pipeline

"MANAGED"Managed
"PLAYGROUND"Playground
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.

maximum1
minimum0
string ClassName
Double? DenseSimilarityCutoff

Minimum similarity score wrt query for retrieval

maximum1
minimum0
Long? DenseSimilarityTopK

Number of nodes for dense retrieval.

maximum100
minimum1
Boolean? EnableReranking

Enable reranking for retrieval

Long? FilesTopK

Number of files to retrieve (only for retrieval mode files_via_metadata and files_via_content).

maximum5
minimum1
Long? RerankTopN

Number of reranked nodes for returning.

maximum100
minimum1
RetrievalMode RetrievalMode

The retrieval mode for the query.

One of the following:
"auto_routed"AutoRouted
"chunks"Chunks
"files_via_content"FilesViaContent
"files_via_metadata"FilesViaMetadata
DeprecatedBoolean 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<Filter> Filters
One of the following:
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
One of the following:
Double
string
IReadOnlyList<string>
IReadOnlyList<Double>
IReadOnlyList<Long>
Operator Operator

Vector store filter operator.

One of the following:
"!="
"<"
"<="
"=="
">"
">="
"all"All
"any"Any
"contains"Contains
"in"In
"is_empty"IsEmpty
"nin"Nin
"text_match"TextMatch
"text_match_insensitive"TextMatchInsensitive
MetadataFilters
Condition? Condition

Vector store filter conditions to combine different filters.

One of the following:
"and"And
"not"Not
"or"Or
IReadOnlyDictionary<string, SearchFiltersInferenceSchema?>? SearchFiltersInferenceSchema

JSON Schema that will be used to infer search_filters. Omit or leave as null to skip inference.

One of the following:
IReadOnlyDictionary<string, JsonElement>
IReadOnlyList<JsonElement>
string
Double
Boolean
Long? SparseSimilarityTopK

Number of nodes for sparse retrieval.

maximum100
minimum1
enum RetrievalMode:
"auto_routed"AutoRouted
"chunks"Chunks
"files_via_content"FilesViaContent
"files_via_metadata"FilesViaMetadata
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).

One of the following:
"auto"Auto
"bm25"Bm25
"splade"Splade
class VertexAIEmbeddingConfig:

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<string, JsonElement> AdditionalKwargs

Additional kwargs for the Vertex.

string ClassName
Long EmbedBatchSize

The batch size for embedding calls.

exclusiveMinimum0
maximum2048
EmbedMode EmbedMode

The embedding mode to use.

One of the following:
"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.

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<string, JsonElement> AdditionalKwargs

Additional kwargs for the Vertex.

string ClassName
Long EmbedBatchSize

The batch size for embedding calls.

exclusiveMinimum0
maximum2048
EmbedMode EmbedMode

The embedding mode to use.

One of the following:
"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.

PipelinesSync

Sync Pipeline
Deprecated
Pipeline Pipelines.Sync.Create(SyncCreateParamsparameters, CancellationTokencancellationToken = default)
POST/api/v1/pipelines/{pipeline_id}/sync
Cancel Pipeline Sync
Deprecated
Pipeline Pipelines.Sync.Cancel(SyncCancelParamsparameters, CancellationTokencancellationToken = default)
POST/api/v1/pipelines/{pipeline_id}/sync/cancel

PipelinesData Sources

List Pipeline Data Sources
Deprecated
IReadOnlyList<PipelineDataSource> Pipelines.DataSources.GetDataSources(DataSourceGetDataSourcesParamsparameters, CancellationTokencancellationToken = default)
GET/api/v1/pipelines/{pipeline_id}/data-sources
Add Data Sources To Pipeline
Deprecated
IReadOnlyList<PipelineDataSource> Pipelines.DataSources.UpdateDataSources(DataSourceUpdateDataSourcesParamsparameters, CancellationTokencancellationToken = default)
PUT/api/v1/pipelines/{pipeline_id}/data-sources
Update Pipeline Data Source
Deprecated
PipelineDataSource Pipelines.DataSources.Update(DataSourceUpdateParamsparameters, CancellationTokencancellationToken = default)
PUT/api/v1/pipelines/{pipeline_id}/data-sources/{data_source_id}
Get Pipeline Data Source Status
Deprecated
ManagedIngestionStatusResponse Pipelines.DataSources.GetStatus(DataSourceGetStatusParamsparameters, CancellationTokencancellationToken = default)
GET/api/v1/pipelines/{pipeline_id}/data-sources/{data_source_id}/status
Sync Pipeline Data Source
Deprecated
Pipeline Pipelines.DataSources.Sync(DataSourceSyncParamsparameters, CancellationTokencancellationToken = default)
POST/api/v1/pipelines/{pipeline_id}/data-sources/{data_source_id}/sync
ModelsExpand Collapse
class PipelineDataSource:

Schema for a data source in a pipeline.

required string ID

Unique identifier

formatuuid
required Component Component

Component that implements the data source

One of the following:
IReadOnlyDictionary<string, JsonElement>
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.

formatpassword
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.

formatpassword
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.

formatpassword
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<string, string>? 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.

formatpassword
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<string>? RequiredExts

The list of required file extensions.

SupportsAccessControl SupportsAccessControl
class CloudSharepointDataSource:
required string ClientID

The client ID to use for authentication.

required string ClientSecret

The client secret to use for authentication.

formatpassword
required string TenantID

The tenant ID to use for authentication.

string ClassName
string? DriveName

The name of the Sharepoint drive to read from.

IReadOnlyList<string>? 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<string>? 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<string>? 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
class CloudSlackDataSource:
required string SlackToken

Slack Bot Token.

formatpassword
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.

formatpassword
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.

formatpassword
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.

formatpassword
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.

formatpassword
ApiVersion ApiVersion

Jira REST API version to use (2 or 3). 3 supports Atlassian Document Format (ADF).

One of the following:
"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<string>? 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)

One of the following:
"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.

formatpassword
string? DeveloperToken

Developer token for authentication if authentication_mechanism is ‘developer_token’.

formatpassword
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.

formatuuid
required DateTimeOffset LastSyncedAt

The last time the data source was automatically synced.

formatdate-time
required string Name

The name of the data source.

required string PipelineID

The ID of the pipeline.

formatuuid
required string ProjectID
required SourceType SourceType
One of the following:
"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

formatdate-time
IReadOnlyDictionary<string, CustomMetadata?>? CustomMetadata

Custom metadata that will be present on all data loaded from the data source

One of the following:
IReadOnlyDictionary<string, JsonElement>
IReadOnlyList<JsonElement>
string
Double
Boolean
Status? Status

The status of the data source in the pipeline.

One of the following:
"CANCELLED"Cancelled
"ERROR"Error
"IN_PROGRESS"InProgress
"NOT_STARTED"NotStarted
"SUCCESS"Success
DateTimeOffset? StatusUpdatedAt

The last time the status was updated.

formatdate-time
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

formatdate-time

Version metadata for the data source

ReaderVersion? ReaderVersion

The version of the reader to use for this data source.

One of the following:
"1.0"1_0
"2.0"2_0
"2.1"2_1

PipelinesImages

List File Page Screenshots
IReadOnlyList<ImageListPageScreenshotsResponse> Pipelines.Images.ListPageScreenshots(ImageListPageScreenshotsParamsparameters, CancellationTokencancellationToken = default)
GET/api/v1/files/{id}/page_screenshots
Get File Page Screenshot
JsonElement Pipelines.Images.GetPageScreenshot(ImageGetPageScreenshotParamsparameters, CancellationTokencancellationToken = default)
GET/api/v1/files/{id}/page_screenshots/{page_index}
Get File Page Figure
JsonElement Pipelines.Images.GetPageFigure(ImageGetPageFigureParamsparameters, CancellationTokencancellationToken = default)
GET/api/v1/files/{id}/page-figures/{page_index}/{figure_name}
List File Pages Figures
IReadOnlyList<ImageListPageFiguresResponse> Pipelines.Images.ListPageFigures(ImageListPageFiguresParamsparameters, CancellationTokencancellationToken = default)
GET/api/v1/files/{id}/page-figures

PipelinesFiles

Get Pipeline File Status Counts
Deprecated
FileGetStatusCountsResponse Pipelines.Files.GetStatusCounts(FileGetStatusCountsParamsparameters, CancellationTokencancellationToken = default)
GET/api/v1/pipelines/{pipeline_id}/files/status-counts
Get Pipeline File Status
Deprecated
ManagedIngestionStatusResponse Pipelines.Files.GetStatus(FileGetStatusParamsparameters, CancellationTokencancellationToken = default)
GET/api/v1/pipelines/{pipeline_id}/files/{file_id}/status
Add Files To Pipeline Api
Deprecated
IReadOnlyList<PipelineFile> Pipelines.Files.Create(FileCreateParamsparameters, CancellationTokencancellationToken = default)
PUT/api/v1/pipelines/{pipeline_id}/files
Update Pipeline File
Deprecated
PipelineFile Pipelines.Files.Update(FileUpdateParamsparameters, CancellationTokencancellationToken = default)
PUT/api/v1/pipelines/{pipeline_id}/files/{file_id}
Delete Pipeline File
Deprecated
Pipelines.Files.Delete(FileDeleteParamsparameters, CancellationTokencancellationToken = default)
DELETE/api/v1/pipelines/{pipeline_id}/files/{file_id}
List Pipeline Files2
Deprecated
FileListPageResponse Pipelines.Files.List(FileListParamsparameters, CancellationTokencancellationToken = default)
GET/api/v1/pipelines/{pipeline_id}/files2
ModelsExpand Collapse
class PipelineFile:

A file associated with a pipeline.

required string ID

Unique identifier for the pipeline file.

formatuuid
required string PipelineID

The ID of the pipeline that the file is associated with.

formatuuid
IReadOnlyDictionary<string, ConfigHash?>? ConfigHash

Hashes for the configuration of the pipeline.

One of the following:
IReadOnlyDictionary<string, JsonElement>
IReadOnlyList<JsonElement>
string
Double
Boolean
DateTimeOffset? CreatedAt

When the pipeline file was created.

formatdate-time
IReadOnlyDictionary<string, CustomMetadata?>? CustomMetadata

Custom metadata for the file.

One of the following:
IReadOnlyDictionary<string, JsonElement>
IReadOnlyList<JsonElement>
string
Double
Boolean
string? DataSourceID

The ID of the data source that the file belongs to.

formatuuid
string? ExternalFileID

The ID of the file in the external system.

string? FileID

The ID of the file.

formatuuid
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.

formatdate-time
string? Name

Name of the file.

IReadOnlyDictionary<string, PermissionInfo?>? PermissionInfo

Permission information for the file.

One of the following:
IReadOnlyDictionary<string, JsonElement>
IReadOnlyList<JsonElement>
string
Double
Boolean
string? ProjectID

The ID of the project that the file belongs to.

formatuuid
IReadOnlyDictionary<string, ResourceInfo?>? ResourceInfo

Resource information for the file.

One of the following:
IReadOnlyDictionary<string, JsonElement>
IReadOnlyList<JsonElement>
string
Double
Boolean
Status? Status

Status of the pipeline file.

One of the following:
"CANCELLED"Cancelled
"ERROR"Error
"IN_PROGRESS"InProgress
"NOT_STARTED"NotStarted
"SUCCESS"Success
DateTimeOffset? StatusUpdatedAt

The last time the status was updated.

formatdate-time
DateTimeOffset? UpdatedAt

When the pipeline file was last updated.

formatdate-time

PipelinesMetadata

Import Pipeline Metadata
Deprecated
IReadOnlyDictionary<string, string> Pipelines.Metadata.Create(MetadataCreateParamsparameters, CancellationTokencancellationToken = default)
PUT/api/v1/pipelines/{pipeline_id}/metadata
Delete Pipeline Files Metadata
Deprecated
Pipelines.Metadata.DeleteAll(MetadataDeleteAllParamsparameters, CancellationTokencancellationToken = default)
DELETE/api/v1/pipelines/{pipeline_id}/metadata

PipelinesDocuments

Create Batch Pipeline Documents
Deprecated
IReadOnlyList<CloudDocument> Pipelines.Documents.Create(DocumentCreateParamsparameters, CancellationTokencancellationToken = default)
POST/api/v1/pipelines/{pipeline_id}/documents
Paginated List Pipeline Documents
Deprecated
DocumentListPageResponse Pipelines.Documents.List(DocumentListParamsparameters, CancellationTokencancellationToken = default)
GET/api/v1/pipelines/{pipeline_id}/documents/paginated
Get Pipeline Document
Deprecated
CloudDocument Pipelines.Documents.Get(DocumentGetParamsparameters, CancellationTokencancellationToken = default)
GET/api/v1/pipelines/{pipeline_id}/documents/{document_id}
Delete Pipeline Document
Deprecated
Pipelines.Documents.Delete(DocumentDeleteParamsparameters, CancellationTokencancellationToken = default)
DELETE/api/v1/pipelines/{pipeline_id}/documents/{document_id}
Get Pipeline Document Status
Deprecated
ManagedIngestionStatusResponse Pipelines.Documents.GetStatus(DocumentGetStatusParamsparameters, CancellationTokencancellationToken = default)
GET/api/v1/pipelines/{pipeline_id}/documents/{document_id}/status
Sync Pipeline Document
Deprecated
JsonElement Pipelines.Documents.Sync(DocumentSyncParamsparameters, CancellationTokencancellationToken = default)
POST/api/v1/pipelines/{pipeline_id}/documents/{document_id}/sync
List Pipeline Document Chunks
Deprecated
IReadOnlyList<TextNode> Pipelines.Documents.GetChunks(DocumentGetChunksParamsparameters, CancellationTokencancellationToken = default)
GET/api/v1/pipelines/{pipeline_id}/documents/{document_id}/chunks
Upsert Batch Pipeline Documents
Deprecated
IReadOnlyList<CloudDocument> Pipelines.Documents.Upsert(DocumentUpsertParamsparameters, CancellationTokencancellationToken = default)
PUT/api/v1/pipelines/{pipeline_id}/documents
ModelsExpand Collapse
class CloudDocument:

Cloud document stored in S3.

required string ID
required IReadOnlyDictionary<string, JsonElement> Metadata
required string Text
IReadOnlyList<string> ExcludedEmbedMetadataKeys
IReadOnlyList<string> ExcludedLlmMetadataKeys
IReadOnlyList<Long>? PagePositions

indices in the CloudDocument.text where a new page begins. e.g. Second page starts at index specified by page_positions[1].

IReadOnlyDictionary<string, JsonElement>? StatusMetadata
class CloudDocumentCreate:

Create a new cloud document.

required IReadOnlyDictionary<string, JsonElement> Metadata
required string Text
string? ID
IReadOnlyList<string> ExcludedEmbedMetadataKeys
IReadOnlyList<string> ExcludedLlmMetadataKeys
IReadOnlyList<Long>? PagePositions

indices in the CloudDocument.text where a new page begins. e.g. Second page starts at index specified by page_positions[1].

class TextNode:

Provided for backward compatibility.

string ClassName
IReadOnlyList<Double>? Embedding

Embedding of the node.

Long? EndCharIdx

End char index of the node.

IReadOnlyList<string> ExcludedEmbedMetadataKeys

Metadata keys that are excluded from text for the embed model.

IReadOnlyList<string> ExcludedLlmMetadataKeys

Metadata keys that are excluded from text for the LLM.

IReadOnlyDictionary<string, JsonElement> 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<string, Relationship> Relationships

A mapping of relationships to other node information.

One of the following:
class RelatedNodeInfo:
required string NodeID
string ClassName
string? Hash
IReadOnlyDictionary<string, JsonElement> Metadata
NodeType? NodeType
One of the following:
"1"1
"2"2
"3"3
"4"4
"5"5
IReadOnlyList<RelatedNodeInfo>
required string NodeID
string ClassName
string? Hash
IReadOnlyDictionary<string, JsonElement> Metadata
NodeType? NodeType
One of the following:
"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.

Note for AI agents: this documentation is built for programmatic access. - Overview of all docs: https://developers.llamaindex.ai/llms.txt - Any page is available as raw Markdown by appending index.md to its URL — e.g. https://developers.llamaindex.ai/llamaparse/parse/getting_started/index.md - Agent-friendly REST search APIs live under https://developers.llamaindex.ai/api/ — search (BM25 full-text), grep (regex), read (fetch a page), and list (browse the doc tree). See https://developers.llamaindex.ai/llms.txt for parameters. - A hosted documentation MCP server is available at https://developers.llamaindex.ai/mcp. If you support MCP, you can ask the user to install it for browsing these docs directly (an alternative to the REST API). Setup: https://developers.llamaindex.ai/for-agents/mcp/ - Other LlamaIndex tooling for agents — the LlamaParse Platform MCP server, agent skills and plugins, and the n8n node — is mapped at https://developers.llamaindex.ai/for-agents/