A full-stack RAG demo you can run locally or deploy to a VPS: upload a PDF, build a per-browser vector index (FAISS), chat with an LLM using retrieved context. The UI is a React + TypeScript SPA; the API is FastAPI + LangChain with a multi-agent pipeline, Sentry tunneling, & sensible production defaults (CORS, rate limits, session disk cleanup)
2 files for Codex, OpenCode and Claude Code: RAG-PDF-Chat-Multi-Agent-Pipeline--Python-React-FullStack AGENTS.md, RAG-PDF-Chat-Multi-Agent-Pipeline--Python-React-FullStack CLAUDE.md — 671 tokens loaded in every session.
AGENTS.md A 381 tok CLAUDE.md A 290 tok These files are arnobt78/RAG-PDF-Chat-Multi-Agent-Pipeline--Python-React-FullStack's own configuration — they tell Codex, OpenCode and Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.