feat: add example questions, tighten grounding instruction, disable markdown tables

fix: strip Gradio metadata from history before passing to Groq API

refactor: switch to Groq, prep app for HF Spaces, clean up comments

Created the front end UI and the README.

Remove outdated result files and enhance filename generation logic in eval.py. Update test cases for improved keyword accuracy. Finalized encoder models

Update answer.py to refine system message for document re-ranking and adjust embedding model comments. Modify JSON result files to reflect updated metrics for average MRR, NDCG, and coverage.

Refactor answer.py and eval.py to integrate OpenAI client, update embedding models, and enhance pipeline debugging. Add einops dependency in pyproject.toml. Created results files to compare

Created answer.py and main.py to run the rag. Created eval and tests to test result accuracy