When building LLM applications, it quickly becomes highly useful and important to track user feedback on the result of your LLM workflow.

Doing that with OpenLLMetry is easy. First, make sure you associate your LLM workflow with unique identifiers.

Then, you can simply log a user feedback by calling our Python SDK or Typescript SDK. Feedbacks are always between -1 and 1, where -1 is the worst possible feedback and 1 is the best possible feedback.

For example, if you provide your users with a thumbs-up / thumbs-down feedback, you should log thumbs-up as 1 and thumbs-down as -1.

You can only report feedback for one association property at a time. So this call will throw an exception: traceloop.reportScore({ chat_id: "12345", generation_id: "789", score: 1 });
from traceloop.sdk import Traceloop

Traceloop.report_score("chat_id", "12345", 1)

Was this page helpful?

Associating Entities with TracesManually reporting calls to LLMs and Vector DBs