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 }
The ID of the file that the page screenshot was taken from
The size of the image in bytes
The index of the page for which the screenshot is taken (0-indexed)
metadata ? : Record< string , unknown > | null
Metadata for the screenshot
The score of the screenshot node
The retrieved nodes from the composite retrieval.
node : Node { id , end_char_idx , pipeline_id , 5 more }
The ID of the retrieved node.
end_char_idx : number | null
The end character index of the retrieved node in the document
The ID of the pipeline this node was retrieved from.
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
The text of the retrieved node.
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 }
The confidence of the figure
The size of the figure in bytes
The ID of the file that the figure was taken from
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
The score of the figure node
ReRankConfig { top_n , type }
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.
A name for the retriever tool. Will default to the pipeline name if not provided.
The ID of the project this retriever resides in.
created_at ? : string | null
pipelines ? : Array< RetrieverPipeline { description , name , pipeline_id , preset_retrieval_parameters } > The pipelines this retriever uses.
description : string | null
A description of the retriever tool.
A name for the retriever tool. Will default to the pipeline name if not provided.
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 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.
Deprecated retrieve_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.
One of the following:
Vector store filter operator.
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
RetrieverCreate { name , pipelines }
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.
A name for the retriever tool. Will default to the pipeline name if not provided.
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 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.
Deprecated retrieve_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.
One of the following:
Vector store filter operator.
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.
A name for the retriever tool. Will default to the pipeline name if not provided.
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 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.
Deprecated retrieve_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.
One of the following:
Vector store filter operator.
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.
RetrieverListResponse = Array< Retriever { id , name , project_id , 3 more } > A name for the retriever tool. Will default to the pipeline name if not provided.
The ID of the project this retriever resides in.
created_at ? : string | null
pipelines ? : Array< RetrieverPipeline { description , name , pipeline_id , preset_retrieval_parameters } > The pipelines this retriever uses.
description : string | null
A description of the retriever tool.
A name for the retriever tool. Will default to the pipeline name if not provided.
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 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.
Deprecated retrieve_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.
One of the following:
Vector store filter operator.
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
Note for AI agents: this documentation is built for programmatic access.
- Overview of all docs: https://developers.llamaindex.ai/llms.txt
- Any page is available as raw Markdown by appending index.md to its URL — e.g. https://developers.llamaindex.ai/llamaparse/parse/getting_started/index.md
- Agent-friendly REST search APIs live under https://developers.llamaindex.ai/api/ — search (BM25 full-text), grep (regex), read (fetch a page), and list (browse the doc tree). See https://developers.llamaindex.ai/llms.txt for parameters.
- A hosted documentation MCP server is available at https://developers.llamaindex.ai/mcp. If you support MCP, you can ask the user to install it for browsing these docs directly (an alternative to the REST API). Setup: https://developers.llamaindex.ai/python/shared/mcp/
