Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.baserun.ai/llms.txt

Use this file to discover all available pages before exploring further.

User feedback is an excellent source for assessing the quality of an LLM application. In Baserun, feedback is collected either as a 0-1 score or custom defined metadata. The feedback is then displayed in the input/output tab inside the trace detail or request detail panel. 
client.feedback(name: str, score: float, metadata: Optional[Dict] = None) -> Tag:

​
Arguments

​
name
string
An optional name that will show up in the Trace/Completion detail view > Feedback section.
​
score
float
required
A score between 0 and 1
​
metadata
object
Extra information about the feedback. For example, a user comment.

​
Instructions

Within a LLM request or a trace, after create an client 
client.feedback (0.9, metadata={"comment": "Great response!"})

​
Adding feedback to a completed trace or completion

Check out the Tags page for more information on how to add feedback to a trace or completion.