Update README + mermaid: add NexAGI free-form reasoning chat

Update README: dual LLM providers, 1 worker, JSON analyze, PII skips

fix: swap reranker to BAAI/bge-reranker-base (v2-mini does not exist on HF)

perf: replace reranker v2-m3 (1.1B) with v2-mini (100M) for 10x faster reranking

docs: add HF Spaces YAML frontmatter back

Add project URL to README

Clean up README by removing unnecessary metadata

docs: add shields.io tech stack badges, update model refs to all-MiniLM-L6-v2

docs: update README with all latest features (reranker, mpnet, LRU cache, PII default)

docs: add HF Spaces YAML frontmatter to README

Update README.md

Remove mermaid config from README

Enhance README with mermaid diagram

Update architecture diagram and tech stack in README

Update README.md

comprehensive README with features, architecture, API, deploy docs

merge HF Spaces metadata into README

fix models.py: match Neon schema varchar sizes, add email unique constraint

initial commit