Query Collection | Captain Docs

1 import requests 2 import uuid 3 4 BASE_URL = "https://api.runcaptain.com" 5 API_KEY = "your_api_key" 6 ORG_ID = "your_organization_id" 7 8 headers = { 9 "Authorization": f"Bearer {API_KEY}", 10 "X-Organization-ID": ORG_ID, 11 "Content-Type": "application/json", 12 "Idempotency-Key": str(uuid.uuid4()) 13 } 14 15 response = requests.post( 16 f"{BASE_URL}/v2/collections/my_documents/query", 17 headers=headers, 18 json={ 19 "query": "What are the key terms in the contract?", 20 "inference": True, 21 "stream": False, 22 "top_k": 80 23 }, 24 timeout=120.0 25 ) 26 27 if response.status_code == 200: 28 result = response.json() 29 print("Response:", result.get("response")) 30 else: 31 print(f"Error: {response.status_code}")

1 { 2 "status": "success", 3 "response": "Based on your Q3 contracts, three documents mention 'termination for convenience' clauses...", 4 "relevant_documents": [ 5 { 6 "document_name": "Acme_Corp_Q3_2024.pdf", 7 "document_id": "doc_abc123", 8 "document_type": "pdf", 9 "relevancy_score": 0.92 10 } 11 ], 12 "query": "Find Q3 contracts mentioning 'termination for convenience'", 13 "collection_name": "contracts_2024" 14 }

Execute a natural language query against a collection using DeepQuery.

Headers:

Authorization: Bearer {api_key} - Captain API key for authentication
X-Organization-ID: Organization UUID
Idempotency-Key: UUID for request deduplication (optional)

Parameters:

query: The natural language query
include_documents: Whether to include relevant documents in the response
inference: Enable AI-powered response generation
stream: Enable real-time streaming
top_k: Number of results to return

Execute a natural language query against a collection using DeepQuery. Headers: - Authorization: Bearer {api_key} - Captain API key for authentication - X-Organization-ID: Organization UUID - Idempotency-Key: UUID for request deduplication (optional) Parameters: - query: The natural language query - include_documents: Whether to include relevant documents in the response - inference: Enable AI-powered response generation - stream: Enable real-time streaming - top_k: Number of results to return

Path parameters

collection_namestringRequired

Name of the collection to query

Request

This endpoint expects an object.

querystringRequired

include_documentsbooleanOptionalDefaults to false

inferencebooleanOptionalDefaults to false

Enable LLM-generated answers based on the relevant sections retrieved

streambooleanOptionalDefaults to false

top_kintegerOptionalDefaults to 80

Response

Successful Response

statusstring or null

responsestring or null

relevant_documentslist of objects or null

querystring or null

collection_namestring or null