Get Attributions for an Answer

Overview

This endpoint returns attribution metadata used by the AI to generate a specific chat reply. Use it to provide transparency and highlight supporting content segments from referenced sources.

Usage Flow

This endpoint is part of a three-step flow:

1. Create a chat session and get conversation IDs
   Call POST /v1/chat to start a conversation and receive threadId and turnId.

2. Get AI chat response
   Call GET /v1/chat/response/{threadId}/{turnId} to retrieve the AI-generated reply.

3. Get attributions
   Call GET /v1/chat/attributions/{threadId}/{turnId} to obtain the list of sources and content segments attributed in the response.

Endpoint

GET https://example.com/v1/chat/attributions/{threadId}/{turnId}

• Authentication Required: Yes
• Rate Limiting: Applies per organization settings
  • X-RateLimit-Limit: Max requests allowed
  • X-RateLimit-Remaining: Remaining requests
  • X-RateLimit-Reset: Reset timestamp (Unix)

Path Parameters

Header Parameters

Example Request

curl --request GET \
     --url https://example.com/v1/v1/chat/attributions/threadId/turnId \
     --header 'accept: application/json'  

import requests

url = "https://example.com/v1/v1/chat/attributions/threadId/turnId"

headers = {"accept": "application/json"}

response = requests.get(url, headers=headers)

print(response.text)

Example Response

{
  "credit_dist": {
    "string": 0
  },
  "domain_credit_dist": {
    "string": 0
  },
  "document_credit_dist": {
    "string": 0
  },
  "publisher_credit_dist": {
    "string": 0
  }
}

Response Codes

What’s Next?

• Display attributions alongside AI responses to build trust and traceability
• Highlight relevant content segments in the user interface
• Link users to source articles for validation and further exploration