Retrievers
Create Retriever
Upsert Retriever
List Retrievers
Get Retriever
Update Retriever
Delete Retriever
Direct Retrieve
ModelsExpand Collapse
CompositeRetrievalMode = "routing" | "full"
Enum for the mode of composite retrieval.
CompositeRetrievalResult { image_nodes, nodes, page_figure_nodes }
The image nodes retrieved by the pipeline for the given query. Deprecated - will soon be replaced with 'page_screenshot_nodes'.
node: Node { file_id, image_size, page_index, metadata }
file_id: string
The ID of the file that the page screenshot was taken from
image_size: number
The size of the image in bytes
page_index: number
The index of the page for which the screenshot is taken (0-indexed)
metadata?: Record<string, unknown> | null
Metadata for the screenshot
score: number
The score of the screenshot node
nodes?: Array<Node>
The retrieved nodes from the composite retrieval.
node: Node { id, end_char_idx, pipeline_id, 5 more }
id: string
The ID of the retrieved node.
end_char_idx: number | null
The end character index of the retrieved node in the document
pipeline_id: string
The ID of the pipeline this node was retrieved from.
retriever_id: string
The ID of the retriever this node was retrieved from.
retriever_pipeline_name: string
The name of the retrieval pipeline this node was retrieved from.
start_char_idx: number | null
The start character index of the retrieved node in the document
text: string
The text of the retrieved node.
metadata?: Record<string, unknown>
Metadata associated with the retrieved node.
The page figure nodes retrieved by the pipeline for the given query.
node: Node { confidence, figure_name, figure_size, 4 more }
confidence: number
The confidence of the figure
figure_name: string
The name of the figure
figure_size: number
The size of the figure in bytes
file_id: string
The ID of the file that the figure was taken from
page_index: number
The index of the page for which the figure is taken (0-indexed)
is_likely_noise?: boolean
Whether the figure is likely to be noise
metadata?: Record<string, unknown> | null
Metadata for the figure
score: number
The score of the figure node
ReRankConfig { top_n, type }
top_n?: number
The number of nodes to retrieve after reranking over retrieved nodes from all retrieval tools.
type?: "system_default" | "llm" | "cohere" | 3 more
The type of reranker to use.
Retriever { id, name, project_id, 3 more }
An entity that retrieves context nodes from several sub RetrieverTools.
id: string
Unique identifier
name: string
A name for the retriever tool. Will default to the pipeline name if not provided.
project_id: string
The ID of the project this retriever resides in.
created_at?: string | null
Creation datetime
pipelines?: Array<RetrieverPipeline { description, name, pipeline_id, preset_retrieval_parameters } >
The pipelines this retriever uses.
description: string | null
A description of the retriever tool.
name: string | null
A name for the retriever tool. Will default to the pipeline name if not provided.
pipeline_id: string
The ID of the pipeline this tool uses.
preset_retrieval_parameters?: PresetRetrievalParams { alpha, class_name, dense_similarity_cutoff, 11 more }
Parameters for retrieval configuration.
alpha?: number | null
Alpha value for hybrid retrieval to determine the weights between dense and sparse retrieval. 0 is sparse retrieval and 1 is dense retrieval.
dense_similarity_cutoff?: number | null
Minimum similarity score wrt query for retrieval
dense_similarity_top_k?: number | null
Number of nodes for dense retrieval.
enable_reranking?: boolean | null
Enable reranking for retrieval
files_top_k?: number | null
Number of files to retrieve (only for retrieval mode files_via_metadata and files_via_content).
rerank_top_n?: number | null
Number of reranked nodes for returning.
The retrieval mode for the query.
Deprecatedretrieve_image_nodes?: boolean
Whether to retrieve image nodes.
retrieve_page_figure_nodes?: boolean
Whether to retrieve page figure nodes.
retrieve_page_screenshot_nodes?: boolean
Whether to retrieve page screenshot nodes.
Metadata filters for vector stores.
MetadataFilter { key, value, operator }
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
value: number | string | Array<string> | 2 more | null
operator?: "==" | ">" | "<" | 11 more
Vector store filter operator.
MetadataFilters { filters, condition }
Metadata filters for vector stores.
MetadataFilter { key, value, operator }
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
value: number | string | Array<string> | 2 more | null
operator?: "==" | ">" | "<" | 11 more
Vector store filter operator.
condition?: "and" | "or" | "not" | null
Vector store filter conditions to combine different filters.
condition?: "and" | "or" | "not" | null
Vector store filter conditions to combine different filters.
search_filters_inference_schema?: Record<string, Record<string, unknown> | Array<unknown> | string | 2 more | null> | null
JSON Schema that will be used to infer search_filters. Omit or leave as null to skip inference.
sparse_similarity_top_k?: number | null
Number of nodes for sparse retrieval.
updated_at?: string | null
Update datetime
RetrieverCreate { name, pipelines }
name: string
A name for the retriever tool. Will default to the pipeline name if not provided.
pipelines?: Array<RetrieverPipeline { description, name, pipeline_id, preset_retrieval_parameters } >
The pipelines this retriever uses.
description: string | null
A description of the retriever tool.
name: string | null
A name for the retriever tool. Will default to the pipeline name if not provided.
pipeline_id: string
The ID of the pipeline this tool uses.
preset_retrieval_parameters?: PresetRetrievalParams { alpha, class_name, dense_similarity_cutoff, 11 more }
Parameters for retrieval configuration.
alpha?: number | null
Alpha value for hybrid retrieval to determine the weights between dense and sparse retrieval. 0 is sparse retrieval and 1 is dense retrieval.
dense_similarity_cutoff?: number | null
Minimum similarity score wrt query for retrieval
dense_similarity_top_k?: number | null
Number of nodes for dense retrieval.
enable_reranking?: boolean | null
Enable reranking for retrieval
files_top_k?: number | null
Number of files to retrieve (only for retrieval mode files_via_metadata and files_via_content).
rerank_top_n?: number | null
Number of reranked nodes for returning.
The retrieval mode for the query.
Deprecatedretrieve_image_nodes?: boolean
Whether to retrieve image nodes.
retrieve_page_figure_nodes?: boolean
Whether to retrieve page figure nodes.
retrieve_page_screenshot_nodes?: boolean
Whether to retrieve page screenshot nodes.
Metadata filters for vector stores.
MetadataFilter { key, value, operator }
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
value: number | string | Array<string> | 2 more | null
operator?: "==" | ">" | "<" | 11 more
Vector store filter operator.
MetadataFilters { filters, condition }
Metadata filters for vector stores.
MetadataFilter { key, value, operator }
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
value: number | string | Array<string> | 2 more | null
operator?: "==" | ">" | "<" | 11 more
Vector store filter operator.
condition?: "and" | "or" | "not" | null
Vector store filter conditions to combine different filters.
condition?: "and" | "or" | "not" | null
Vector store filter conditions to combine different filters.
search_filters_inference_schema?: Record<string, Record<string, unknown> | Array<unknown> | string | 2 more | null> | null
JSON Schema that will be used to infer search_filters. Omit or leave as null to skip inference.
sparse_similarity_top_k?: number | null
Number of nodes for sparse retrieval.
RetrieverPipeline { description, name, pipeline_id, preset_retrieval_parameters }
description: string | null
A description of the retriever tool.
name: string | null
A name for the retriever tool. Will default to the pipeline name if not provided.
pipeline_id: string
The ID of the pipeline this tool uses.
preset_retrieval_parameters?: PresetRetrievalParams { alpha, class_name, dense_similarity_cutoff, 11 more }
Parameters for retrieval configuration.
alpha?: number | null
Alpha value for hybrid retrieval to determine the weights between dense and sparse retrieval. 0 is sparse retrieval and 1 is dense retrieval.
dense_similarity_cutoff?: number | null
Minimum similarity score wrt query for retrieval
dense_similarity_top_k?: number | null
Number of nodes for dense retrieval.
enable_reranking?: boolean | null
Enable reranking for retrieval
files_top_k?: number | null
Number of files to retrieve (only for retrieval mode files_via_metadata and files_via_content).
rerank_top_n?: number | null
Number of reranked nodes for returning.
The retrieval mode for the query.
Deprecatedretrieve_image_nodes?: boolean
Whether to retrieve image nodes.
retrieve_page_figure_nodes?: boolean
Whether to retrieve page figure nodes.
retrieve_page_screenshot_nodes?: boolean
Whether to retrieve page screenshot nodes.
Metadata filters for vector stores.
MetadataFilter { key, value, operator }
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
value: number | string | Array<string> | 2 more | null
operator?: "==" | ">" | "<" | 11 more
Vector store filter operator.
MetadataFilters { filters, condition }
Metadata filters for vector stores.
MetadataFilter { key, value, operator }
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
value: number | string | Array<string> | 2 more | null
operator?: "==" | ">" | "<" | 11 more
Vector store filter operator.
condition?: "and" | "or" | "not" | null
Vector store filter conditions to combine different filters.
condition?: "and" | "or" | "not" | null
Vector store filter conditions to combine different filters.
search_filters_inference_schema?: Record<string, Record<string, unknown> | Array<unknown> | string | 2 more | null> | null
JSON Schema that will be used to infer search_filters. Omit or leave as null to skip inference.
sparse_similarity_top_k?: number | null
Number of nodes for sparse retrieval.