Pipelines

Run Search

Changed on Oct 16, 2026

Run a retrieval query against a managed pipeline.

Searches the pipeline's vector store using the provided query and retrieval parameters. Supports dense, sparse, and hybrid search modes with configurable top-k and reranking.

post/api/v1/pipelines/{pipeline_id}/retrieve

Request

Base URL
https://api.cloud.llamaindex.ai (the document declares no server; this is the origin it was published from)
Auth
HTTP bearer

Path parameters

pipeline_idstring uuid required

Query parameters

project_idstring uuid nullable

organization_idstring uuid nullable

Cookies

sessionstring nullable

Request body

dense_similarity_top_kinteger nullable

Number of nodes for dense retrieval.

dense_similarity_cutoffnumber nullable

Minimum similarity score wrt query for retrieval

sparse_similarity_top_kinteger nullable

Number of nodes for sparse retrieval.

enable_rerankingboolean nullable

Enable reranking for retrieval

rerank_top_ninteger nullable

Number of reranked nodes for returning.

alphanumber nullable

Alpha value for hybrid retrieval to determine the weights between dense and sparse retrieval. 0 is sparse retrieval and 1 is dense retrieval.

search_filters_inference_schemaobject nullable

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

files_top_kinteger nullable

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

retrieval_mode'chunks' | 'files_via_metadata' | 'files_via_content' | 'auto_routed'

retrieve_image_nodesboolean

Whether to retrieve image nodes.

retrieve_page_screenshot_nodesboolean

Whether to retrieve page screenshot nodes.

retrieve_page_figure_nodesboolean

Whether to retrieve page figure nodes.

querystring required

The query to retrieve against.

class_namestring

Response

Successful Response

pipeline_idstring uuid required

The ID of the pipeline that the query was retrieved against.

retrieval_latencyobject

The end-to-end latency for retrieval and reranking.

metadataobject

Metadata associated with the retrieval execution