Update docs with actual BM25 index size (866 MB) and deployment timings

Pre-serialize BM25 index for fast startup (~16 min → ~8s)

Add full-text extraction pipeline scripts (Phase 8 WIP)

Update docs: add DEV_README, refresh CLAUDE.md, clean gitignore

Enhance UI: two-section search sources, author lines, interactive dashboard

Add entity list API, author fetching, and search source decoupling

Update chroma_store, vector_retriever, embed_chunks for rebuilt ChromaDB

Prepare for HF Spaces deployment: swap Dockerfile, add README with YAML frontmatter

Fix ChromaDB schema mismatch: auto-migrate missing 'topic' column on startup

Fix search 500 error: add LLM generation error handling and graceful fallback

Pin numpy<2.0 and chromadb==0.4.24, fix ChromaDB reset safety, update docs

Improve web UI: expand venues, add paper filters, fix dashboard chart, add About page

Use pre-built HF dataset for data instead of build-time ingestion

Ingest full ACL Anthology: remove paper cap, widen year range

Fix frontend API paths to match backend route structure

Add build-time data seeding for HF Spaces deployment

Ensure DB schema exists on startup for fresh deployments

Fix emoji in HF staging script to use valid Unicode microscope emoji

Add Hugging Face Spaces deployment ($0/month)

Add Oracle Cloud Always Free deployment ($0/month)

ResearchRadar: RAG-powered NLP research explorer