API Reference

Pipelines

Copy Markdown

Open in Claude

Open in ChatGPT

Open in Cursor

---

Copy Markdown

View as Markdown

Run Search

client.Pipelines.Get(ctx, pipelineID, params) (*PipelineGetResponse, error)

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.

ParametersExpand Collapse

pipelineID string

params PipelineGetParams

Query param.Field[string]

Body param: The query to retrieve against.

minLength1

OrganizationID param.Field[string]optional

Query param

formatuuid

ProjectID param.Field[string]optional

Query param

formatuuid

Alpha param.Field[float64]optional

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.

maximum1

minimum0

ClassName param.Field[string]optional

Body param

DenseSimilarityCutoff param.Field[float64]optional

Body param: Minimum similarity score wrt query for retrieval

maximum1

minimum0

DenseSimilarityTopK param.Field[int64]optional

Body param: Number of nodes for dense retrieval.

maximum100

minimum1

EnableReranking param.Field[bool]optional

Body param: Enable reranking for retrieval

FilesTopK param.Field[int64]optional

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

maximum5

minimum1

RerankTopN param.Field[int64]optional

Body param: Number of reranked nodes for returning.

maximum100

minimum1

RetrievalMode param.Field[RetrievalMode]optional

Body param: The retrieval mode for the query.

DeprecatedRetrieveImageNodes param.Field[bool]optional

Body param: Whether to retrieve image nodes.

RetrievePageFigureNodes param.Field[bool]optional

Body param: Whether to retrieve page figure nodes.

RetrievePageScreenshotNodes param.Field[bool]optional

Body param: Whether to retrieve page screenshot nodes.

SearchFilters param.Field[MetadataFilters]optional

Body param: Metadata filters for vector stores.

SearchFiltersInferenceSchema param.Field[map[string, PipelineGetParamsSearchFiltersInferenceSchemaUnion]]optional

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

type PipelineGetParamsSearchFiltersInferenceSchemaMap map[string, any]

type PipelineGetParamsSearchFiltersInferenceSchemaArray []any

string

float64

bool

SparseSimilarityTopK param.Field[int64]optional

Body param: Number of nodes for sparse retrieval.

maximum100

minimum1

ReturnsExpand Collapse

type PipelineGetResponse struct{…}

Schema for the result of an retrieval execution.

PipelineID string

The ID of the pipeline that the query was retrieved against.

formatuuid

RetrievalNodes []PipelineGetResponseRetrievalNode

The nodes retrieved by the pipeline for the given query.

Node TextNode

Provided for backward compatibility.

ClassName stringoptional

Embedding []float64optional

Embedding of the node.

EndCharIdx int64optional

End char index of the node.

ExcludedEmbedMetadataKeys []stringoptional

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

ExcludedLlmMetadataKeys []stringoptional

Metadata keys that are excluded from text for the LLM.

ExtraInfo map[string, any]optional

A flat dictionary of metadata fields

ID stringoptional

Unique ID of the node.

MetadataSeperator stringoptional

Separator between metadata fields when converting to string.

MetadataTemplate stringoptional

Template for how metadata is formatted, with {key} and {value} placeholders.

Mimetype stringoptional

MIME type of the node content.

Relationships map[string, TextNodeRelationshipUnion]optional

A mapping of relationships to other node information.

One of the following:

type TextNodeRelationshipRelatedNodeInfo struct{…}

NodeID string

ClassName stringoptional

Hash stringoptional

Metadata map[string, any]optional

NodeType stringoptional

One of the following:

string

One of the following:

const TextNodeRelationshipRelatedNodeInfoNodeType1 TextNodeRelationshipRelatedNodeInfoNodeType = "1"

const TextNodeRelationshipRelatedNodeInfoNodeType2 TextNodeRelationshipRelatedNodeInfoNodeType = "2"

const TextNodeRelationshipRelatedNodeInfoNodeType3 TextNodeRelationshipRelatedNodeInfoNodeType = "3"

const TextNodeRelationshipRelatedNodeInfoNodeType4 TextNodeRelationshipRelatedNodeInfoNodeType = "4"

const TextNodeRelationshipRelatedNodeInfoNodeType5 TextNodeRelationshipRelatedNodeInfoNodeType = "5"

string

type TextNodeRelationshipArray []TextNodeRelationshipArrayItem

NodeID string

ClassName stringoptional

Hash stringoptional

Metadata map[string, any]optional

NodeType stringoptional

One of the following:

string

One of the following:

const TextNodeRelationshipArrayItemNodeType1 TextNodeRelationshipArrayItemNodeType = "1"

const TextNodeRelationshipArrayItemNodeType2 TextNodeRelationshipArrayItemNodeType = "2"

const TextNodeRelationshipArrayItemNodeType3 TextNodeRelationshipArrayItemNodeType = "3"

const TextNodeRelationshipArrayItemNodeType4 TextNodeRelationshipArrayItemNodeType = "4"

const TextNodeRelationshipArrayItemNodeType5 TextNodeRelationshipArrayItemNodeType = "5"

string

StartCharIdx int64optional

Start char index of the node.

Text stringoptional

Text content of the node.

TextTemplate stringoptional

Template for how text is formatted, with {content} and {metadata_str} placeholders.

ClassName stringoptional

Score float64optional

ClassName stringoptional

DeprecatedImageNodes []PageScreenshotNodeWithScoreoptional

The image nodes retrieved by the pipeline for the given query. Deprecated - will soon be replaced with ‘page_screenshot_nodes’.

Node PageScreenshotNodeWithScoreNode

FileID string

The ID of the file that the page screenshot was taken from

formatuuid

ImageSize int64

The size of the image in bytes

minimum0

PageIndex int64

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

minimum0

Metadata map[string, any]optional

Metadata for the screenshot

Score float64

The score of the screenshot node

ClassName stringoptional

InferredSearchFilters MetadataFiltersoptional

Metadata filters for vector stores.

Filters []MetadataFiltersFilterUnion

One of the following:

type MetadataFiltersFilterMetadataFilter struct{…}

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

Key string

Value MetadataFiltersFilterMetadataFilterValueUnion

One of the following:

float64

string

type MetadataFiltersFilterMetadataFilterValueArray []string

type MetadataFiltersFilterMetadataFilterValueArray []float64

type MetadataFiltersFilterMetadataFilterValueArray []int64

Operator stringoptional

Vector store filter operator.

One of the following:

const MetadataFiltersFilterMetadataFilterOperatorEquals MetadataFiltersFilterMetadataFilterOperator = "=="

const MetadataFiltersFilterMetadataFilterOperatorGreater MetadataFiltersFilterMetadataFilterOperator = ">"

const MetadataFiltersFilterMetadataFilterOperatorLess MetadataFiltersFilterMetadataFilterOperator = "<"

const MetadataFiltersFilterMetadataFilterOperatorNotEquals MetadataFiltersFilterMetadataFilterOperator = "!="

const MetadataFiltersFilterMetadataFilterOperatorGreaterOrEquals MetadataFiltersFilterMetadataFilterOperator = ">="

const MetadataFiltersFilterMetadataFilterOperatorLessOrEquals MetadataFiltersFilterMetadataFilterOperator = "<="

const MetadataFiltersFilterMetadataFilterOperatorIn MetadataFiltersFilterMetadataFilterOperator = "in"

const MetadataFiltersFilterMetadataFilterOperatorNin MetadataFiltersFilterMetadataFilterOperator = "nin"

const MetadataFiltersFilterMetadataFilterOperatorAny MetadataFiltersFilterMetadataFilterOperator = "any"

const MetadataFiltersFilterMetadataFilterOperatorAll MetadataFiltersFilterMetadataFilterOperator = "all"

const MetadataFiltersFilterMetadataFilterOperatorTextMatch MetadataFiltersFilterMetadataFilterOperator = "text_match"

const MetadataFiltersFilterMetadataFilterOperatorTextMatchInsensitive MetadataFiltersFilterMetadataFilterOperator = "text_match_insensitive"

const MetadataFiltersFilterMetadataFilterOperatorContains MetadataFiltersFilterMetadataFilterOperator = "contains"

const MetadataFiltersFilterMetadataFilterOperatorIsEmpty MetadataFiltersFilterMetadataFilterOperator = "is_empty"

type MetadataFilters MetadataFilters

Metadata filters for vector stores.

Condition MetadataFiltersConditionoptional

Vector store filter conditions to combine different filters.

One of the following:

const MetadataFiltersConditionAnd MetadataFiltersCondition = "and"

const MetadataFiltersConditionOr MetadataFiltersCondition = "or"

const MetadataFiltersConditionNot MetadataFiltersCondition = "not"

Metadata map[string, string]optional

Metadata associated with the retrieval execution

PageFigureNodes []PageFigureNodeWithScoreoptional

The page figure nodes retrieved by the pipeline for the given query.

Node PageFigureNodeWithScoreNode

Confidence float64

The confidence of the figure

maximum1

minimum0

FigureName string

The name of the figure

FigureSize int64

The size of the figure in bytes

minimum0

FileID string

The ID of the file that the figure was taken from

formatuuid

PageIndex int64

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

minimum0

IsLikelyNoise booloptional

Whether the figure is likely to be noise

Metadata map[string, any]optional

Metadata for the figure

Score float64

The score of the figure node

ClassName stringoptional

RetrievalLatency map[string, float64]optional

The end-to-end latency for retrieval and reranking.

Run Search

Go

HTTP

TypeScript

Python

Go

CLI Tool

package main

import (
  "context"
  "fmt"

  "github.com/stainless-sdks/llamacloud-prod-go"
  "github.com/stainless-sdks/llamacloud-prod-go/option"
)

func main() {
  client := llamacloudprod.NewClient(
    option.WithAPIKey("My API Key"),
  )
  pipeline, err := client.Pipelines.Get(
    context.TODO(),
    "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
    llamacloudprod.PipelineGetParams{
      Query: "x",
    },
  )
  if err != nil {
    panic(err.Error())
  }
  fmt.Printf("%+v\n", pipeline.PipelineID)
}

200 example

{
  "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
  }
}

Returns Examples

200 example

{
  "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
  }
}