Learn how to track user feedback on your traces
enrich_session
function to set on the trace level.To pass to HoneyHive, pass it to the param in the enrich_session
function. This function is used to enrich the session with additional information. Remember that enrich_session
will update, not overwrite, the existing object on the trace.Read more about the enrich_session
function in the Python SDK reference.Here’s an example of how to set on the trace level in Python:HoneyHiveTracer.session_id
HoneyHiveTracer.init(session_id = <session-id>)
with the received sessionIdenrich_session()
or enrich_span()
with your feedback datauser feedback
. This can be of two types:
Copy
, Regenerate
, etc.metrics
field.Return Type | Available Measurements | Notes |
---|---|---|
Boolean | True/False | |
Number | Percentage, Sum, Avg, Median, Min, Max, P95, P98, P99 | |
String | Any string value | Used for filters and group by |
feedback.step1.retry
as a boolean field or feedback.edits.0.value
as a string field.
ground_truth
- The ground truth value for the output of a trace or span. This is used to compare the actual output with the expected output. It is rendered differently in the UI.
enrich_session
function in the Python SDK reference.