v0.23.0

What's Changed

• Test: modify single model evaluation scores by @ashrafchowdury in #1981
• Test: upload testset as csv by @ashrafchowdury in #1979
• fix(backend): fix json evaluator description by @mmabrouk in #1990
• Test: save single model testset by @ashrafchowdury in #1980
• fix(tool): AGE-612 fix dependencies with langchain_community by @mmabrouk in #1992
• AGE 486 - SDK v3 - Configuration management with Pydantic by @mmabrouk in #1961
• feat(backend): AGE-276 and AGE-471 Improves LLM-as-a-judge reliability by @mmabrouk in #1938
• Bump versions by @github-actions in #1996

Full Changelog: v0.22.0...v0.23.0