Retrieve

Retrieve relevant document chunks without generating an answer.

Path Parameters:

• engine_id: Unique identifier of the answer engine

Request Body:

• query: The search query (required, cannot be empty)
• top_k (optional): Number of chunks to return (1-50). Default: 5

Returns:

• answer_engine_id: ID of the engine used
• query: Echo of the submitted query
• documents: List of retrieved document chunks
• metadata: Retrieval metadata

Raises:

• 404: Engine not found
• 422: Invalid request body

Example Request:

POST /api/v3/answer-engine/ae_8c625d9d71/retrieve
Headers: {"Authorization": "Bearer <api_key>"}

{
  "query": "What is Machine Learning?",
  "top_k": 5
}

Example Response:

{
  "answer_engine_id": "ae_8c625d9d71",
  "query": "What is Machine Learning?",
  "documents": [],
  "metadata": {
    "org_id_verify": "org_415",
    "user_id_verify": "user_415",
    "total_chunks_searched": 0,
    "retrieval_time_ms": 0,
    "message": "No documents have been uploaded to this answer engine yet"
  }
}