OpenAI Assistant

{
    // Required fields for logging
    "language_model_id": "gpt-4",
    "prompt": [
        { "role": "system", "content": "System Instructions for the assistant" },
        { "role": "user", "content": "Individual message level instructions" },
    ],
    "response": "Response message from the assistant (as a string)",
    "session_id": "session-123",
    
    // Required fields for most evaluations
    "user_query": "The message from the user you are responding to",
    "context": "Your retrieved documents as a string or object", // Can be a string or object
    
    // Token usage logs (optional, but recommended). These can be found in the "Run" object from OpenAI Assistants API.
    "prompt_tokens": 123,
    "completion": 100,
    "total_tokens": 223,
    "cost": 0.12314, // if you provide tokens, we will calculate the cost for you automatically.
    
    // Optional fields for better segmentation and analytics (recommended)
    "prompt_slug": "customer-support/v1", // any string
    "environment": "production", // any string
    "customer_id": "disney-usa-2314832", // any string, this is your internal customer identifier
    "customer_user_id": "michaelmouse@gmail.com", // any string, this is the end user identifier,
    "external_reference_id": "239ej92-r24-4838-45663", // any string, this is your internal reference ID for the message,
 
    // Tool calls
    "tool_call": tool_calls, // can be any JSON object
    "tools": tools, // can be any JSON object
 
    // Ground truth data - used for some evaluations
    "expected_response": "If you have a ground truth response, you can send this here",
 
}