#173 · Primary category: Knowledge Base & RAG
doc-chatbot
Document chatbot — multiple files, topics, chat windows and chat history. Powered by GPT.
Project last updated:07/21/23
GitHub Stars
853
Forks
137
Contributors
1
License
MIT
Why we included this project
This is a working Next.js app that answers questions about your own documents through a chat interface. You can group uploaded PDFs, DOCX files, or text files into topics, open several chat windows per topic, and the conversation history is saved automatically in the browser. Each topic gets its own Pinecone namespace, and you can manage the vectors, including deleting them, without leaving the page. Because it is a small real application rather than a library, it works both as a self-hosted document assistant and as a readable reference for how LangChain, OpenAI, and a vector store fit together. The README covers setup step by step, right down to the QA prompt you will want to rewrite for your own domain. Just note that it requires accounts with OpenAI and Pinecone, and the repo has not been updated since mid-2023.
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