v1

latestOpenAPI 3.1.02026-07-1730321418.0 KB

Search

Perform a vector similarity search (VSS) operation on a dataset.

The search operation will return the most relevant matches based on cosine similarity with the input text. The datasets queries should have an embedding column, and the appropriate embedding model loaded.

post/v1/search

Request body

additional_columnsstring[]

Additional columns to return from the dataset. If the column is a primary key, it will be returned within the response under .primary_key, not .data.

datasetsstring[] nullable

The datasets to search for similarity. If None, search across all datasets. For available datasets, use the list_datasets tool and ensure can_search_documents==true.

limitinteger nullable

Number of documents to return for each dataset

textstring required

The text to search documents for similarity

wherestring nullable

An SQL filter predicate to apply. Format: 'WHERE where_cond'.

keywordsstring[] nullable

Response

Search completed successfully

duration_msinteger required

Total time taken to execute the search, in milliseconds