Arize AI Community Icon

Home
Events

Arize AX Releases
Arize AX Support
Arize News
Arize Observe
Discussions
Introductions
Phoenix Support

Powered by Tightknit

Phoenix Support

Phoenix Support

Filtering Traces by Specific Feedback Labels in Your System

·Nov 12, 2025 11:37 AM·

Our traces have different feedback labels. We have "thumbs-up", "half-thumbs-up" and "thumbs-down". When I try to filter condition to for example only "thumbs-up" traces nothings shows up.

feedback.label == "thumbs-up"

How can I filter on a specific type of feedback?

4 comments

· Sorted by Oldest

RunLLM
APP
·
·
It seems likely that filtering traces by a specific feedback label (e.g., feedback.label == "thumbs-up") may not work because the correct way to filter by annotation label is to use the evaluation name as an indexer on the special keyword evals, like so: evals['feedback'].label == 'thumbs-up'. The feedback column itself is an aggregation and not directly filterable in this way in the query DSL or UI filter bar.For example, to filter for spans or traces with a "thumbs-up" feedback annotation, use: LBKSquery = SpanQuery().where("evals['feedback'].label == 'thumbs-up'")LBKSThis approach is supported in both the Python API and the Phoenix UI filter bar, as long as the evaluation/annotation is named "feedback" and the label is "thumbs-up" as per your configuration. Would you like more detail or examples for your specific setup?Sources: - How to filter by evaluation results
💡 Hint: Mention RunLLM in the thread for followups.
Sanjana
External
·
·
Hi Daniel N., if you click on the feedback box, you should get an option for filters. This should auto-fill the query box for you. Let us know if that doesn't work
Sanjana
External
·
·
This format should also work: annotations['user feedback'].label == 'thumbs-up'
Daniel N.
·
·
Nice, thank you! This worked for me
annotations['user feedback'].score >2 #thumbs up
❤️1