arabic-teacher / src /evaluation

Commit History

Address comments
b554955

Kelly Diabagate commited on

Agent 3 set up and improvements
6fe612a

Kelly Diabagate commited on

Fix Agent 3 RAG schema mismatch - remove 'correct' field
22c56ed

Kelly Diabagate commited on

Complete Agent 3 evaluation infrastructure and identify RAG schema issue
cae2059

Kelly Diabagate Claude Sonnet 4.5 commited on

Remove old content agent implementation
391dbf9

Kelly Diabagate commited on

Agent 2 implementation + baseline eval and small improvements - clean up
8f908ed

Kelly Diabagate commited on

Agent 2 implementation + baseline eval and small improvements
5c91b05

Kelly Diabagate commited on

Agent 1 + eval - clean up
f7e47b0

Kelly Diabagate commited on

Agent 1 + eval
f4203cb

Kelly Diabagate commited on

Agent 1 + eval
b20998e

Kelly Diabagate commited on

Eval code improvements
13a3adb

Kelly Diabagate commited on

Baseline eval report + small changes
4c193e6

Kelly Diabagate commited on

Fix JSON extraction consistency and update docs
1500657

Kelly Diabagate Claude Sonnet 4.5 commited on

Apply ruff formatting to baseline and metrics
8507cf3

Kelly Diabagate Claude Sonnet 4.5 commited on

Fix baseline feedback template usage and linting
88b8f01

Kelly Diabagate Claude Sonnet 4.5 commited on

Clean up docs and reorganize: Flatten structure, remove outdated files
de0dfe9

Kelly Diabagate Claude Sonnet 4.5 commited on

Address code review feedback: Improve metrics and baseline
b69097e

Kelly Diabagate Claude Sonnet 4.5 commited on

Implement DeepEval evaluation pipeline with comprehensive fixes
01c6524

Kelly Diabagate Claude Sonnet 4.5 commited on