ModelsExpand Collapse enum CompositeRetrievalMode :
Enum for the mode of composite retrieval.
class CompositeRetrievalResult :
The image nodes retrieved by the pipeline for the given query. Deprecated - will soon be replaced with ‘page_screenshot_nodes’.
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)
IReadOnlyDictionary< string , JsonElement > ? Metadata
Metadata for the screenshot
The score of the screenshot node
IReadOnlyList< Node > Nodes
The retrieved nodes from the composite retrieval.
The ID of the retrieved node.
required Long ? EndCharIdx
The end character index of the retrieved node in the document
required string PipelineID
The ID of the pipeline this node was retrieved from.
required string RetrieverID
The ID of the retriever this node was retrieved from.
required string RetrieverPipelineName
The name of the retrieval pipeline this node was retrieved from.
required Long ? StartCharIdx
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.
required Double Confidence
The confidence of the figure
required string FigureName
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)
Whether the figure is likely to be noise
IReadOnlyDictionary< string , JsonElement > ? Metadata
The score of the figure node
The number of nodes to retrieve after reranking over retrieved nodes from all retrieval tools.
The type of reranker to use.
One of the following:
"system_default" SystemDefault
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.
required string ProjectID
The ID of the project this retriever resides in.
DateTimeOffset ? CreatedAt
The pipelines this retriever uses.
required string ? Description
A description of the retriever tool.
A name for the retriever tool. Will default to the pipeline name if not provided.
required string PipelineID
The ID of the pipeline this tool uses.
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.
Double ? DenseSimilarityCutoff
Minimum similarity score wrt query for retrieval
Long ? DenseSimilarityTopK
Number of nodes for dense retrieval.
Enable reranking for retrieval
Number of files to retrieve (only for retrieval mode files_via_metadata and files_via_content).
Number of reranked nodes for returning.
The retrieval mode for the query.
One of the following:
"files_via_content" FilesViaContent
"files_via_metadata" FilesViaMetadata
Deprecated Boolean RetrieveImageNodes
Whether to retrieve image nodes.
Boolean RetrievePageFigureNodes
Whether to retrieve page figure nodes.
Boolean RetrievePageScreenshotNodes
Whether to retrieve page screenshot nodes.
Metadata filters for vector stores.
Vector store filter conditions to combine different filters.
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 >
Long ? SparseSimilarityTopK
Number of nodes for sparse retrieval.
DateTimeOffset ? UpdatedAt
A name for the retriever tool. Will default to the pipeline name if not provided.
The pipelines this retriever uses.
required string ? Description
A description of the retriever tool.
A name for the retriever tool. Will default to the pipeline name if not provided.
required string PipelineID
The ID of the pipeline this tool uses.
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.
Double ? DenseSimilarityCutoff
Minimum similarity score wrt query for retrieval
Long ? DenseSimilarityTopK
Number of nodes for dense retrieval.
Enable reranking for retrieval
Number of files to retrieve (only for retrieval mode files_via_metadata and files_via_content).
Number of reranked nodes for returning.
The retrieval mode for the query.
One of the following:
"files_via_content" FilesViaContent
"files_via_metadata" FilesViaMetadata
Deprecated Boolean RetrieveImageNodes
Whether to retrieve image nodes.
Boolean RetrievePageFigureNodes
Whether to retrieve page figure nodes.
Boolean RetrievePageScreenshotNodes
Whether to retrieve page screenshot nodes.
Metadata filters for vector stores.
Vector store filter conditions to combine different filters.
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 >
Long ? SparseSimilarityTopK
Number of nodes for sparse retrieval.
required string ? Description
A description of the retriever tool.
A name for the retriever tool. Will default to the pipeline name if not provided.
required string PipelineID
The ID of the pipeline this tool uses.
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.
Double ? DenseSimilarityCutoff
Minimum similarity score wrt query for retrieval
Long ? DenseSimilarityTopK
Number of nodes for dense retrieval.
Enable reranking for retrieval
Number of files to retrieve (only for retrieval mode files_via_metadata and files_via_content).
Number of reranked nodes for returning.
The retrieval mode for the query.
One of the following:
"files_via_content" FilesViaContent
"files_via_metadata" FilesViaMetadata
Deprecated Boolean RetrieveImageNodes
Whether to retrieve image nodes.
Boolean RetrievePageFigureNodes
Whether to retrieve page figure nodes.
Boolean RetrievePageScreenshotNodes
Whether to retrieve page screenshot nodes.
Metadata filters for vector stores.
Vector store filter conditions to combine different filters.
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 >
Long ? SparseSimilarityTopK
Number of nodes for sparse retrieval.
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/for-agents/mcp/
- Other LlamaIndex tooling for agents — the LlamaParse Platform MCP server, agent skills and plugins, and the n8n node — is mapped at https://developers.llamaindex.ai/for-agents/
