API Reference

Retrievers

Copy Markdown

Open in Claude

Open in ChatGPT

Open in Cursor

---

Copy Markdown

View as Markdown

Upsert Retriever

Retriever Retrievers.Upsert(RetrieverUpsertParamsparameters, CancellationTokencancellationToken = default)

PUT/api/v1/retrievers

Upsert a new Retriever.

ParametersExpand Collapse

RetrieverUpsertParams parameters

required string name

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

maxLength3000

minLength1

string? organizationID

Query param

formatuuid

string? projectID

Query param

formatuuid

IReadOnlyList<RetrieverPipeline> pipelines

Body param: The pipelines this retriever uses.

required string? Description

A description of the retriever tool.

maxLength15000

required string? Name

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

maxLength3000

minLength1

required string PipelineID

The ID of the pipeline this tool uses.

formatuuid

PresetRetrievalParams PresetRetrievalParameters

Parameters for retrieval configuration.

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

ReturnsExpand Collapse

class Retriever:

An entity that retrieves context nodes from several sub RetrieverTools.

required string ID

Unique identifier

formatuuid

required string Name

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

maxLength3000

minLength1

required string ProjectID

The ID of the project this retriever resides in.

formatuuid

DateTimeOffset? CreatedAt

Creation datetime

formatdate-time

IReadOnlyList<RetrieverPipeline> Pipelines

The pipelines this retriever uses.

required string? Description

A description of the retriever tool.

maxLength15000

required string? Name

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

maxLength3000

minLength1

required string PipelineID

The ID of the pipeline this tool uses.

formatuuid

PresetRetrievalParams PresetRetrievalParameters

Parameters for retrieval configuration.

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

DateTimeOffset? UpdatedAt

Update datetime

formatdate-time

Upsert Retriever

C#

HTTP

TypeScript

Python

Go

Java

C#

CLI Tool

RetrieverUpsertParams parameters = new() { Name = "x" };

var retriever = await client.Retrievers.Upsert(parameters);

Console.WriteLine(retriever);

200 example

{
  "id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
  "name": "x",
  "project_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
  "created_at": "2019-12-27T18:11:19.117Z",
  "pipelines": [
    {
      "description": "description",
      "name": "x",
      "pipeline_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
      "preset_retrieval_parameters": {
        "alpha": 0,
        "class_name": "class_name",
        "dense_similarity_cutoff": 0,
        "dense_similarity_top_k": 1,
        "enable_reranking": true,
        "files_top_k": 1,
        "rerank_top_n": 1,
        "retrieval_mode": "auto_routed",
        "retrieve_image_nodes": true,
        "retrieve_page_figure_nodes": true,
        "retrieve_page_screenshot_nodes": true,
        "search_filters": {
          "filters": [
            {
              "key": "key",
              "value": 0,
              "operator": "!="
            }
          ],
          "condition": "and"
        },
        "search_filters_inference_schema": {
          "foo": {
            "foo": "bar"
          }
        },
        "sparse_similarity_top_k": 1
      }
    }
  ],
  "updated_at": "2019-12-27T18:11:19.117Z"
}

Returns Examples

200 example

{
  "id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
  "name": "x",
  "project_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
  "created_at": "2019-12-27T18:11:19.117Z",
  "pipelines": [
    {
      "description": "description",
      "name": "x",
      "pipeline_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
      "preset_retrieval_parameters": {
        "alpha": 0,
        "class_name": "class_name",
        "dense_similarity_cutoff": 0,
        "dense_similarity_top_k": 1,
        "enable_reranking": true,
        "files_top_k": 1,
        "rerank_top_n": 1,
        "retrieval_mode": "auto_routed",
        "retrieve_image_nodes": true,
        "retrieve_page_figure_nodes": true,
        "retrieve_page_screenshot_nodes": true,
        "search_filters": {
          "filters": [
            {
              "key": "key",
              "value": 0,
              "operator": "!="
            }
          ],
          "condition": "and"
        },
        "search_filters_inference_schema": {
          "foo": {
            "foo": "bar"
          }
        },
        "sparse_similarity_top_k": 1
      }
    }
  ],
  "updated_at": "2019-12-27T18:11:19.117Z"
}