Auboz API

Vector Search

Direct vector similarity search without AI synthesis.

The vector search endpoint performs raw semantic search against your knowledge base embeddings. Unlike the Agent endpoint, it returns matching chunks directly without AI synthesis.

POST /v1/kb/query

Scope: kb:read

Request Body
{
  "query": "revenue growth projections",
  "workspace_id": "ws_abc123",
  "top_k": 5
}

Parameters

FieldTypeDescription
querystringRequired. The search query (will be embedded for similarity search)
workspace_idstringRequired. Workspace to search
top_knumberNumber of results to return (default: 5)

Response

Response
{
  "results": [
    {
      "document_id": "doc_abc",
      "filename": "Q4-Report.pdf",
      "chunk_index": 12,
      "content": "Revenue grew 40% year-over-year...",
      "score": 0.92,
      "metadata": {
        "page": 3
      }
    }
  ]
}

Legacy Endpoint

POST /query

Identical to POST /v1/kb/query. Maintained for backward compatibility.

On this page