Sign in

v5

latestOpenAPI 3.1.02026-08-025631,1012.8 MB
Retrievers

Batch Execute Retriever

Execute a retriever against multiple queries in a single request. The retriever is fetched and optimized once, then executed concurrently against each query with bounded parallelism.

Use case: IP safety / copyright clearance — scan 20 media files against face, logo, or audio retrievers in one call instead of 60 sequential SSE requests.

Limits: 1-50 queries per batch, 1-20 concurrency.

Returns results keyed by query index with per-query documents and errors.

post/v1/retrievers/{retriever_id}/execute/batch

Path parameters

retriever_idstring required

Retriever ID or name.

Retriever ID or name.

Query parameters

return_presigned_urlsboolean

Generate presigned URLs for S3-backed blobs and url-shaped fields. Also accepted as a body field — if either source is true, presigning is enabled.

Generate presigned URLs for S3-backed blobs and url-shaped fields. Also accepted as a body field — if either source is true, presigning is enabled.

return_vectorsboolean

Include vector embeddings in result documents. Also accepted as a body field — if either source is true, vectors are returned.

Include vector embeddings in result documents. Also accepted as a body field — if either source is true, vectors are returned.

Request body

settingsobject nullable

Shared settings applied to every query. Supports 'limit' (max results per query, default 10) and 'max_chunks' (for content-mode preprocessing).

concurrencyinteger

Max concurrent executions (1-20). Higher = faster but more resource usage.

return_presigned_urlsboolean

Generate presigned URLs for S3-backed blobs and url-shaped fields. Also accepted as a query param — if either source is true, presigning is enabled.

return_vectorsboolean

Include vector embeddings in result documents. Also accepted as a query param — if either source is true, vectors are returned.

streamboolean

Stream results via Server-Sent Events. Each query result is emitted as it completes, with keepalive pings every 15s to prevent proxy timeouts.

Response

Successful Response

{"stackTrail":"paths:/v1/retrievers/{retriever_id}/execute/batch:post:responses:200:content:application/json:schema","oasType":"schema","type":"unknown"}