API Reference

Copy Markdown

Open in Claude

Open in ChatGPT

Open in Cursor

---

Copy Markdown

View as Markdown

Retrievers

Create Retriever

client.Retrievers.New(ctx, params) (*Retriever, error)

POST/api/v1/retrievers

Upsert Retriever

client.Retrievers.Upsert(ctx, params) (*Retriever, error)

PUT/api/v1/retrievers

List Retrievers

client.Retrievers.List(ctx, query) (*[]Retriever, error)

GET/api/v1/retrievers

Get Retriever

client.Retrievers.Get(ctx, retrieverID, query) (*Retriever, error)

GET/api/v1/retrievers/{retriever_id}

Update Retriever

client.Retrievers.Update(ctx, retrieverID, params) (*Retriever, error)

PUT/api/v1/retrievers/{retriever_id}

Delete Retriever

client.Retrievers.Delete(ctx, retrieverID, body) error

DELETE/api/v1/retrievers/{retriever_id}

Direct Retrieve

client.Retrievers.Search(ctx, params) (*CompositeRetrievalResult, error)

POST/api/v1/retrievers/retrieve

ModelsExpand Collapse

type CompositeRetrievalMode string

Enum for the mode of composite retrieval.

One of the following:

const CompositeRetrievalModeRouting CompositeRetrievalMode = "routing"

const CompositeRetrievalModeFull CompositeRetrievalMode = "full"

type CompositeRetrievalResult struct{…}

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

Nodes []CompositeRetrievalResultNodeoptional

The retrieved nodes from the composite retrieval.

Node CompositeRetrievalResultNodeNode

ID string

The ID of the retrieved node.

formatuuid

EndCharIdx int64

The end character index of the retrieved node in the document

PipelineID string

The ID of the pipeline this node was retrieved from.

formatuuid

RetrieverID string

The ID of the retriever this node was retrieved from.

formatuuid

RetrieverPipelineName string

The name of the retrieval pipeline this node was retrieved from.

StartCharIdx int64

The start character index of the retrieved node in the document

Text string

The text of the retrieved node.

Metadata map[string, any]optional

Metadata associated with the retrieved node.

ClassName stringoptional

Score float64optional

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

type ReRankConfig struct{…}

TopN int64optional

The number of nodes to retrieve after reranking over retrieved nodes from all retrieval tools.

minimum1

Type ReRankConfigTypeoptional

The type of reranker to use.

One of the following:

const ReRankConfigTypeSystemDefault ReRankConfigType = "system_default"

const ReRankConfigTypeLlm ReRankConfigType = "llm"

const ReRankConfigTypeCohere ReRankConfigType = "cohere"

const ReRankConfigTypeBedrock ReRankConfigType = "bedrock"

const ReRankConfigTypeScore ReRankConfigType = "score"

const ReRankConfigTypeDisabled ReRankConfigType = "disabled"

type Retriever struct{…}

An entity that retrieves context nodes from several sub RetrieverTools.

ID string

Unique identifier

formatuuid

Name string

A name for the retriever tool. Will default to the pipeline name if not provided.

maxLength3000

minLength1

ProjectID string

The ID of the project this retriever resides in.

formatuuid

CreatedAt Timeoptional

Creation datetime

formatdate-time

Pipelines []RetrieverPipelineoptional

The pipelines this retriever uses.

Description string

A description of the retriever tool.

maxLength15000

Name string

A name for the retriever tool. Will default to the pipeline name if not provided.

maxLength3000

minLength1

PipelineID string

The ID of the pipeline this tool uses.

formatuuid

PresetRetrievalParameters PresetRetrievalParamsRespoptional

Parameters for retrieval configuration.

Alpha float64optional

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 stringoptional

DenseSimilarityCutoff float64optional

Minimum similarity score wrt query for retrieval

maximum1

minimum0

DenseSimilarityTopK int64optional

Number of nodes for dense retrieval.

maximum100

minimum1

EnableReranking booloptional

Enable reranking for retrieval

FilesTopK int64optional

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

maximum5

minimum1

RerankTopN int64optional

Number of reranked nodes for returning.

maximum100

minimum1

RetrievalMode RetrievalModeoptional

The retrieval mode for the query.

One of the following:

const RetrievalModeChunks RetrievalMode = "chunks"

const RetrievalModeFilesViaMetadata RetrievalMode = "files_via_metadata"

const RetrievalModeFilesViaContent RetrievalMode = "files_via_content"

const RetrievalModeAutoRouted RetrievalMode = "auto_routed"

DeprecatedRetrieveImageNodes booloptional

Whether to retrieve image nodes.

RetrievePageFigureNodes booloptional

Whether to retrieve page figure nodes.

RetrievePageScreenshotNodes booloptional

Whether to retrieve page screenshot nodes.

SearchFilters 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"

SearchFiltersInferenceSchema map[string, PresetRetrievalParamsSearchFiltersInferenceSchemaUnionResp]optional

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

One of the following:

type PresetRetrievalParamsSearchFiltersInferenceSchemaMap map[string, any]

type PresetRetrievalParamsSearchFiltersInferenceSchemaArray []any

string

float64

bool

SparseSimilarityTopK int64optional

Number of nodes for sparse retrieval.

maximum100

minimum1

UpdatedAt Timeoptional

Update datetime

formatdate-time

type RetrieverCreate struct{…}

Name string

A name for the retriever tool. Will default to the pipeline name if not provided.

maxLength3000

minLength1

Pipelines []RetrieverPipelineoptional

The pipelines this retriever uses.

Description string

A description of the retriever tool.

maxLength15000

Name string

A name for the retriever tool. Will default to the pipeline name if not provided.

maxLength3000

minLength1

PipelineID string

The ID of the pipeline this tool uses.

formatuuid

PresetRetrievalParameters PresetRetrievalParamsRespoptional

Parameters for retrieval configuration.

Alpha float64optional

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 stringoptional

DenseSimilarityCutoff float64optional

Minimum similarity score wrt query for retrieval

maximum1

minimum0

DenseSimilarityTopK int64optional

Number of nodes for dense retrieval.

maximum100

minimum1

EnableReranking booloptional

Enable reranking for retrieval

FilesTopK int64optional

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

maximum5

minimum1

RerankTopN int64optional

Number of reranked nodes for returning.

maximum100

minimum1

RetrievalMode RetrievalModeoptional

The retrieval mode for the query.

One of the following:

const RetrievalModeChunks RetrievalMode = "chunks"

const RetrievalModeFilesViaMetadata RetrievalMode = "files_via_metadata"

const RetrievalModeFilesViaContent RetrievalMode = "files_via_content"

const RetrievalModeAutoRouted RetrievalMode = "auto_routed"

DeprecatedRetrieveImageNodes booloptional

Whether to retrieve image nodes.

RetrievePageFigureNodes booloptional

Whether to retrieve page figure nodes.

RetrievePageScreenshotNodes booloptional

Whether to retrieve page screenshot nodes.

SearchFilters 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"

SearchFiltersInferenceSchema map[string, PresetRetrievalParamsSearchFiltersInferenceSchemaUnionResp]optional

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

One of the following:

type PresetRetrievalParamsSearchFiltersInferenceSchemaMap map[string, any]

type PresetRetrievalParamsSearchFiltersInferenceSchemaArray []any

string

float64

bool

SparseSimilarityTopK int64optional

Number of nodes for sparse retrieval.

maximum100

minimum1

type RetrieverPipeline struct{…}

Description string

A description of the retriever tool.

maxLength15000

Name string

A name for the retriever tool. Will default to the pipeline name if not provided.

maxLength3000

minLength1

PipelineID string

The ID of the pipeline this tool uses.

formatuuid

PresetRetrievalParameters PresetRetrievalParamsRespoptional

Parameters for retrieval configuration.

Alpha float64optional

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 stringoptional

DenseSimilarityCutoff float64optional

Minimum similarity score wrt query for retrieval

maximum1

minimum0

DenseSimilarityTopK int64optional

Number of nodes for dense retrieval.

maximum100

minimum1

EnableReranking booloptional

Enable reranking for retrieval

FilesTopK int64optional

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

maximum5

minimum1

RerankTopN int64optional

Number of reranked nodes for returning.

maximum100

minimum1

RetrievalMode RetrievalModeoptional

The retrieval mode for the query.

One of the following:

const RetrievalModeChunks RetrievalMode = "chunks"

const RetrievalModeFilesViaMetadata RetrievalMode = "files_via_metadata"

const RetrievalModeFilesViaContent RetrievalMode = "files_via_content"

const RetrievalModeAutoRouted RetrievalMode = "auto_routed"

DeprecatedRetrieveImageNodes booloptional

Whether to retrieve image nodes.

RetrievePageFigureNodes booloptional

Whether to retrieve page figure nodes.

RetrievePageScreenshotNodes booloptional

Whether to retrieve page screenshot nodes.

SearchFilters 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"

SearchFiltersInferenceSchema map[string, PresetRetrievalParamsSearchFiltersInferenceSchemaUnionResp]optional

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

One of the following:

type PresetRetrievalParamsSearchFiltersInferenceSchemaMap map[string, any]

type PresetRetrievalParamsSearchFiltersInferenceSchemaArray []any

string

float64

bool

SparseSimilarityTopK int64optional

Number of nodes for sparse retrieval.

maximum100

minimum1

RetrieversRetriever

Retrieve

client.Retrievers.Retriever.Search(ctx, retrieverID, params) (*CompositeRetrievalResult, error)

POST/api/v1/retrievers/{retriever_id}/retrieve