#172 · Primary category: Knowledge Base & RAG
chatgpt-your-files
Production-ready MVP for securely chatting with your documents using pgvector
Project last updated:05/12/26
GitHub Stars
516
Forks
195
Contributors
7
License
Other
Why we included this project
This project is a working document-chat app you can take apart and rebuild. It connects a chat front end to OpenAI's GPT models and Supabase's Postgres with pgvector, so uploaded files are embedded into a vector index and retrieved through retrieval-augmented generation. It's also a guided workshop, not just a demo: each feature, from file storage to embeddings to chat, sits at its own git tag, so a developer can follow the progression and see how the whole pipeline fits together. The finished code includes row-level security, third-party login, a REST API, and sample documents, which makes it a reasonable starting point for a real product that answers questions about your own files.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
ragflow
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
Understand-Anything
Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.
crawl4ai
🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN
docling
Get your documents ready for gen AI
anything-llm
Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience