#173 · Primary category： Knowledge Base & RAG
ollama_pdf_rag
A full-stack demo showcasing a local RAG (Retrieval Augmented Generation) pipeline to chat with your PDFs.
Project last updated：04/16/26
GitHub Stars
540
Forks
196
Contributors
2
License
MIT
Why we included this project
Everything here runs on your own hardware. Ollama handles local inference, LangChain builds the retrieval pipeline, and ChromaDB stores the vectors, all exposed through a FastAPI backend with a Next.js app and a Streamlit interface on top. That setup works two ways: as a template you can adapt for a private document Q&A tool, and as a complete example of how a local RAG stack fits together. The multi-query retrieval returns source citations, which helps when you need to verify where an answer came from. If you're weighing a self-hosted document assistant, the notebooks and REST API give you room to experiment before committing to a design.
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