Although LLMs are powerful, they are not perfect. They can make mistakes, and sometimes the mistakes are hard to detect. Human review is a way to ensure the quality of the LLM output and the accuracy of the AI evaluators.

​
Pass user feedback to the API

You can pass user feedback to the API as a positive_feedback field in the request.

If you are using the Logging API, you can pass the positive_feedback field in the request to record if the user liked the output.

positive_feedback is a boolean field that indicates if the user liked the output.

payload = {
    "model": "gpt-4o",
    # ...
    "positive_feedback": True, # means the user liked the output
}

After you pass the positive_feedback field, you can see it in the side panel of the Logs.

Previous
Create a dataset from logs
Next