v0.25.0

What's Changed

• [Enhancement]: Handle non-string outputs gracefully in auto_contains_json evaluator by @aybruhm in #1987
• [Enhancement] Add LLM API key checks to LLM-based evaluators by @aybruhm in #1989
• [Feature]: expose running evaluators via API to playground by @aybruhm in #1956
• Feat: implemented human evaluations by @ashrafchowdury in #2047
• Doc: fixed broken link style by @ashrafchowdury in #2059
• Update README.md by @mmabrouk in #2060
• docs(app): switched to new auto crawled index in Algolia by @mmabrouk in #2064
• Fix: evaluation related build warnings by @ashrafchowdury in #1951
• Fix: small UI issues in overview page by @ashrafchowdury in #2027
• Dependabot prs sept by @aakrem in #2067
• Bump fastapi from 0.111.1 to 0.114.0 in /agenta-cli by @dependabot in #2066
• Test: automatic evaluation with different correct_answer column by @ashrafchowdury in #1985
• Feat: automatic evaluation functionalities by @ashrafchowdury in #2058
• Evaluation docs Overhaul by @mmabrouk in #2061
• [feature] Evaluators - Debugging by @bekossy in #2071
• Improvement Docs Prompt Management by @mmabrouk in #2083
• [feature] Project - Checkpoint 1 by @aybruhm in #2037
• [Refactor]: Manually Name Database Table Constraints to Resolve sqlalchemy.exc.CompileError by @aybruhm in #2054
• [feature] Projects - Checkpoint 2 by @aybruhm in #2065
• [feature] Projects Structure - Checkpoint 2 by @aybruhm in #2090
• [feature]: new onboarding UI by @ashrafchowdury in #2082
• v0.25.0 by @github-actions in #2091

Full Changelog: v0.24.4...v0.25.0