## Run Search `PipelineRetrieveResponse Pipelines.Retrieve(PipelineRetrieveParamsparameters, CancellationTokencancellationToken = default)` **post** `/api/v1/pipelines/{pipeline_id}/retrieve` Run a retrieval query against a managed pipeline. Searches the pipeline's vector store using the provided query and retrieval parameters. Supports dense, sparse, and hybrid search modes with configurable top-k and reranking. ### Parameters - `PipelineRetrieveParams parameters` - `required string pipelineID` Path param - `required string query` Body param: The query to retrieve against. - `string? organizationID` Query param - `string? projectID` Query param - `Double? alpha` Body param: Alpha value for hybrid retrieval to determine the weights between dense and sparse retrieval. 0 is sparse retrieval and 1 is dense retrieval. - `string className` Body param - `Double? denseSimilarityCutoff` Body param: Minimum similarity score wrt query for retrieval - `Long? denseSimilarityTopK` Body param: Number of nodes for dense retrieval. - `Boolean? enableReranking` Body param: Enable reranking for retrieval - `Long? filesTopK` Body param: Number of files to retrieve (only for retrieval mode files_via_metadata and files_via_content). - `Long? rerankTopN` Body param: Number of reranked nodes for returning. - `RetrievalMode retrievalMode` Body param: The retrieval mode for the query. - `Boolean retrieveImageNodes` Body param: Whether to retrieve image nodes. - `Boolean retrievePageFigureNodes` Body param: Whether to retrieve page figure nodes. - `Boolean retrievePageScreenshotNodes` Body param: Whether to retrieve page screenshot nodes. - `MetadataFilters? searchFilters` Body param: Metadata filters for vector stores. - `IReadOnlyDictionary? searchFiltersInferenceSchema` Body param: JSON Schema that will be used to infer search_filters. Omit or leave as null to skip inference. - `IReadOnlyDictionary` - `IReadOnlyList` - `string` - `Double` - `Boolean` - `Long? sparseSimilarityTopK` Body param: Number of nodes for sparse retrieval. ### Returns - `class PipelineRetrieveResponse:` Schema for the result of an retrieval execution. - `required string PipelineID` The ID of the pipeline that the query was retrieved against. - `required IReadOnlyList RetrievalNodes` The nodes retrieved by the pipeline for the given query. - `required TextNode Node` Provided for backward compatibility. - `string ClassName` - `IReadOnlyList? Embedding` Embedding of the node. - `Long? EndCharIdx` End char index of the node. - `IReadOnlyList ExcludedEmbedMetadataKeys` Metadata keys that are excluded from text for the embed model. - `IReadOnlyList ExcludedLlmMetadataKeys` Metadata keys that are excluded from text for the LLM. - `IReadOnlyDictionary ExtraInfo` A flat dictionary of metadata fields - `string ID` Unique ID of the node. - `string MetadataSeperator` Separator between metadata fields when converting to string. - `string MetadataTemplate` Template for how metadata is formatted, with {key} and {value} placeholders. - `string Mimetype` MIME type of the node content. - `IReadOnlyDictionary Relationships` A mapping of relationships to other node information. - `class RelatedNodeInfo:` - `required string NodeID` - `string ClassName` - `string? Hash` - `IReadOnlyDictionary Metadata` - `NodeType? NodeType` - `"1"1` - `"2"2` - `"3"3` - `"4"4` - `"5"5` - `IReadOnlyList` - `required string NodeID` - `string ClassName` - `string? Hash` - `IReadOnlyDictionary Metadata` - `NodeType? NodeType` - `"1"1` - `"2"2` - `"3"3` - `"4"4` - `"5"5` - `Long? StartCharIdx` Start char index of the node. - `string Text` Text content of the node. - `string TextTemplate` Template for how text is formatted, with {content} and {metadata_str} placeholders. - `string ClassName` - `Double? Score` - `string ClassName` - `IReadOnlyList ImageNodes` The image nodes retrieved by the pipeline for the given query. Deprecated - will soon be replaced with 'page_screenshot_nodes'. - `required Node Node` - `required string FileID` The ID of the file that the page screenshot was taken from - `required Long ImageSize` The size of the image in bytes - `required Long PageIndex` The index of the page for which the screenshot is taken (0-indexed) - `IReadOnlyDictionary? Metadata` Metadata for the screenshot - `required Double Score` The score of the screenshot node - `string ClassName` - `MetadataFilters? InferredSearchFilters` Metadata filters for vector stores. - `required IReadOnlyList Filters` - `class MetadataFilter:` Comprehensive metadata filter for vector stores to support more operators. Value uses Strict types, as int, float and str are compatible types and were all converted to string before. See: https://docs.pydantic.dev/latest/usage/types/#strict-types - `required string Key` - `required Value? Value` - `Double` - `string` - `IReadOnlyList` - `IReadOnlyList` - `IReadOnlyList` - `Operator Operator` Vector store filter operator. - `"!="` - `"<"` - `"<="` - `"=="` - `">"` - `">="` - `"all"All` - `"any"Any` - `"contains"Contains` - `"in"In` - `"is_empty"IsEmpty` - `"nin"Nin` - `"text_match"TextMatch` - `"text_match_insensitive"TextMatchInsensitive` - `class MetadataFilters:` Metadata filters for vector stores. - `Condition? Condition` Vector store filter conditions to combine different filters. - `"and"And` - `"not"Not` - `"or"Or` - `IReadOnlyDictionary Metadata` Metadata associated with the retrieval execution - `IReadOnlyList PageFigureNodes` The page figure nodes retrieved by the pipeline for the given query. - `required Node Node` - `required Double Confidence` The confidence of the figure - `required string FigureName` The name of the figure - `required Long FigureSize` The size of the figure in bytes - `required string FileID` The ID of the file that the figure was taken from - `required Long PageIndex` The index of the page for which the figure is taken (0-indexed) - `Boolean IsLikelyNoise` Whether the figure is likely to be noise - `IReadOnlyDictionary? Metadata` Metadata for the figure - `required Double Score` The score of the figure node - `string ClassName` - `IReadOnlyDictionary RetrievalLatency` The end-to-end latency for retrieval and reranking. ### Example ```csharp PipelineRetrieveParams parameters = new() { PipelineID = "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", Query = "x", }; var pipeline = await client.Pipelines.Retrieve(parameters); Console.WriteLine(pipeline); ``` #### Response ```json { "pipeline_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "retrieval_nodes": [ { "node": { "class_name": "class_name", "embedding": [ 0 ], "end_char_idx": 0, "excluded_embed_metadata_keys": [ "string" ], "excluded_llm_metadata_keys": [ "string" ], "extra_info": { "foo": "bar" }, "id_": "id_", "metadata_seperator": "metadata_seperator", "metadata_template": "metadata_template", "mimetype": "mimetype", "relationships": { "foo": { "node_id": "node_id", "class_name": "class_name", "hash": "hash", "metadata": { "foo": "bar" }, "node_type": "1" } }, "start_char_idx": 0, "text": "text", "text_template": "text_template" }, "class_name": "class_name", "score": 0 } ], "class_name": "class_name", "image_nodes": [ { "node": { "file_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "image_size": 0, "page_index": 0, "metadata": { "foo": "bar" } }, "score": 0, "class_name": "class_name" } ], "inferred_search_filters": { "filters": [ { "key": "key", "value": 0, "operator": "!=" } ], "condition": "and" }, "metadata": { "foo": "string" }, "page_figure_nodes": [ { "node": { "confidence": 0, "figure_name": "figure_name", "figure_size": 0, "file_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "page_index": 0, "is_likely_noise": true, "metadata": { "foo": "bar" } }, "score": 0, "class_name": "class_name" } ], "retrieval_latency": { "foo": 0 } } ```