Search a vector store

Performs semantic search within a vector store to find the most relevant document chunks for a query.

POST /api/v1/llm/vector_stores/{vector_store_id}/search

Python (SDK)

Python

from mka1 import SDK


with SDK(
    bearer_auth="<YOUR_BEARER_TOKEN_HERE>",
) as sdk:

    res = sdk.llm.vector_stores.search(vector_store_id="vs_abc123", query="How do I reset my password?", max_num_results=5, rewrite_query=False)

    # Handle response
    print(res)

200

{
  "object": "vector_store.search_results.page",
  "search_query": "How do I reset my password?",
  "data": [
    {
      "file_id": "file-abc123",
      "filename": "user-guide.pdf",
      "score": 0.92,
      "content": [
        {
          "type": "text",
          "text": "To reset your password, navigate to Settings > Security > Reset Password..."
        }
      ]
    }
  ],
  "has_more": false,
  "next_page": null
}

Authorizations

Authorization · string · header · required

Gateway auth: send Authorization: Bearer <mka1-api-key>. For multi-user server-side integrations, you can also send X-On-Behalf-Of: <external-user-id>.

Headers

X-On-Behalf-Of · string

Optional external end-user identifier forwarded by the API gateway.

Path Parameters

vector_store_id · string · required

The ID of the vector store to search.

Body

application/json

Request body for searching a vector store.

query · string string[] · required

A query string for a search, or an array of query strings.

filters · object

A filter to apply based on file attributes.

Option 1

Option 2

Show child attributes

max_num_results · integer · default: 10

The maximum number of results to return. This number should be between 1 and 50 inclusive.

Required range: 1 <= x <= 50

ranking_options · object

Ranking options for search.

Show child attributes

rewrite_query · boolean · default: false

Whether to rewrite the natural language query for vector search.

Response

200 - application/json

OK

A page of search results from the vector store.

object · any · required

The object type, which is always 'vector_store.search_results.page'.

search_query · string · required

The query that was used for the search.

data · object[] · required

Array of search results.

Show child attributes

has_more · boolean · required

Whether there are more results available.

next_page · string | null · required

Cursor for the next page of results, or null if no more results.