added rag-only or rag + kg-graph option for LLM response

Add 3-way eval (no-RAG/RAG/RAG+graph) with per-call graph toggle and --sample flag

added knowledge graphs and fix: correct BERTScore unpacking to use recall not precision (bert_score returns P,R,F1); relabel stale precision values in eval_results.json

added new webpage with feature of generating report using LLM + RAG

@

Consolidated all per-(book,model) eval files into one eval_predictions.jsonl and one eval_results.json (tagged internally by model/provider/book), migrated existing data in, and updated the readme

Multi-book RAG support: config.BOOKS registry ingesting multiple PDFs into one Chroma collection with book-aware citations, robust chapter tagging for TOC-less/junk-TOC PDFs, an incremental --add flag to index a new PDF without a full re-embed, and updated README (multi-book docs + Limitations).

improved comments of phase_b_query - 1

added comment for each code files for better understanding

completed evaluation by generating 240 QA pairs

completed phase b and created streamlit UI for anthropic only LLM

added basic plan made by claude