in the experiment page: is equal supposed to be working for filtering? e.g. reference_output['my_key'] == '0778' doesn't seem to be working for me, I wonder if I'm missing something obvious . in like '0778' in reference_output['external_display_id'] works.
Yes, the equality operator (==) is supported for filtering in the experiment page, including for JSON keys like reference_output['my_key'] == '0778'. This is confirmed by test cases and SQL compilation logic in the codebase, which show that such filters are valid and should work as expected. If in works but == does not, it may be due to data type mismatches or the actual value in the key not matching exactly as a string鈥攅nsure the value and type are correct in your data (test_experiment_run_filters.py, test_experiment_run_filters.ambr).Would you like more detail on debugging why your specific filter might not be working?Sources:
- test_experiment_run_filters.py
- test_experiment_run_filters.ambr
馃挕聽Hint: Mention RunLLM in the thread for followups.
reference_output["my_key"] == "\"my_value\""
works, thank you!
