#162 · Primary category： Knowledge Base & RAG
IncarnaMind
Connect and chat with your multiple documents (pdf and txt) through GPT 3.5, GPT-4 Turbo, Claude and Local Open-Source LLMs
Project last updated：02/07/25
GitHub Stars
801
Forks
55
Contributors
3
License
Apache-2.0
Why we included this project
IncarnaMind is a compact, self-contained reference implementation for document Q&A over your own files. It chunks PDFs and text files into a local database and answers questions using a sliding-window chunking scheme plus an ensemble retriever, so you can pull both specific passages and broader context from the same corpus. The model layer is swappable: run it against OpenAI GPT, Anthropic Claude, or a local Llama2 model, which makes it a practical option if you want to keep sensitive material off hosted APIs or compare providers on identical data. The codebase is small enough to read through and adapt, though it currently handles only PDF and TXT input and has no polished frontend. Running a local Llama2 model also needs more than 35GB of GPU RAM.
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