What's Changed
- add basic evaluators by @aybruhm in #1074
- Evaluation - auto regex test by @aybruhm in #1100
- Evaluation - Auto webhook test by @aybruhm in #1101
- Evaluation - Custom code run by @aybruhm in #1104
- Evaluation - Aggregate evaluator results by @aybruhm in #1107
- [Bug]: Resolve evaluation scenario get endpoint by @aybruhm in #1121
- Improve: Resolve evaluation results router and aggregate evaluation results by @aybruhm in #1125
- [Enhancement]: Integration Tests for Evaluation by @aybruhm in #1122
- Sync evaluation with main by @aybruhm in #1140
- Enhancement: RPM/TPM Rate Limiting for Evaluation by @aybruhm in #1148
- Feat: Migrate Agenta to use Beanie ODM by @devgenix in #1149
- Refactor - Cleanup redundant code in evaluations branch by @aybruhm in #1168
- Cypress tests for new evaluation by @bekossy in #1170
- Refactor evaluations backend by @mmabrouk in #1172
- merge main by @mmabrouk in #1173
- Lm keys by @aakrem in #1181
- Schemas migrations by @aybruhm in #1179
- Main to evaluations in backend by @aakrem in #1187
- Fix issue with dynamic inputs in eval by @mmabrouk in #1188
- Migration - Update odmantic reference to beanie link & migrate old evaluation scenarios to new evaluation scenarios by @aybruhm in #1191
- Refreshing playground and testset results in an alert by @bekossy in #1174
- Export button always activated by @mmabrouk in #1203
- Migration - modify logic to assign evaluations to their respective users by @aybruhm in #1205
- Expected answer and notes not being exported in human eval by @bekossy in #1212
- Enhancement: Migration issues fix by @aybruhm in #1214
- Main to evaluations in backend by @aakrem in #1217
- Evaluations in backend by @mmabrouk in #1137
- Update pyproject.toml by @mmabrouk in #1219
Full Changelog: 0.7.1...0.80