refactor: extract llm-as-judge logic to reusable module

fix: correct total query count in test_queries.yaml

add script to evaluate rag and evaluation results

add baseline and retrieval eval results

refactor: update eval_baseline.py to integrate Ollama for local LLM calls and improve usage instructions

refactor: update eval_retrieval.py to support chunking strategy argument

add baseline eval script and results

add __init__ files for eval and ablation

Update test_queries.yaml to version 3.0 and retrieval criteria

add script to calibrate test cases.

add test script to evaluate retriaval methodologies. also add script output

add test queries