Feedback - Parea AI

If you collect feedback from your users, such as thumbs up or down, you can record that feedback on your trace logs.

Record feedback

To record feedback you need the trace_id of the trace log you want to record feedback on. You can get the trace_id using the get_current_trace_id() helper function, or from the completion method’s response.

Python
Typescript

from parea.schemas import FeedbackRequest
from parea import Parea, get_current_trace_id, trace

p = Parea(api_key="PAREA_API_KEY")

@trace
def argument_chain(messages: list[dict]) -> tuple[str, str]:
    # get_current_trace_id will return the trace_id of the most recent trace
    trace_id = get_current_trace_id()
    return call_llm(messages), trace_id

result, trace_id = argument_chain([{"role": "user", "content": "Hello"}])
p.record_feedback(
    FeedbackRequest(
        trace_id=trace_id,
        # insert your user score here, score must be float
        score=USER_SCORE,
        # Optionally, you can also provide a ground truth or
        # target answer. This could also be from your user.
        target="ground_truth",
    )
)

Alternatively, if you used p.completion for your LLM request, you can access the inference_id field on the response to get the trace_id.

from parea.schemas import LLMInputs, Message, Role, Completion, CompletionResponse, FeedbackRequest

result: CompletionResponse = p.completion(
    Completion(
        llm_configuration=LLMInputs(
            model="gpt-3.5-turbo",
            messages=[Message(role=Role.user, content="Hello")],
        )
    )
)
p.record_feedback(
    FeedbackRequest(
        trace_id=result.inference_id,
        score=USER_SCORE,
    )
)

import {getCurrentTraceId, trace} from "parea-ai";
const p = new Parea("PAREA_API_KEY");

const argumentChain = trace('argumentChain', async (messages) => {
    // getCurrentTraceId will return the trace_id of current traced function
    const traceId = getCurrentTraceId()
    const result = await call_llm(messages)
    return [result, traceId]
  },
);
const [result, traceId] = await argumentChain([{role: "user", content: "Hello"}]);
await p.recordFeedback({
    trace_id: traceId,
    // insert your user score here, score must be float
    score: USER_SCORE,
});

Alternatively, if you used p.completion for your LLM request, you can access the inference_id field on the response to get the trace_id.

const result = await p.completion({
    llm_configuration: {
        model: 'gpt-3.5-turbo',
        messages: [{role: 'user', content: "Hello"}],
    }
})
await p.recordFeedback({
    trace_id: result.inference_id,
    score: USER_SCORE,
});

​Record feedback

Record feedback