marella/chatdocs
Offline document Q&A tool that runs local LLMs (Transformers, GGUF, GPTQ) with a web UI to chat over PDFs, Word docs, and other file types.
Not currently ranked — collecting fresh signals.
star history
ChatDocs is a local RAG (Retrieval-Augmented Generation) system that embeds documents into a vector store (Chroma) and answers questions by retrieving relevant chunks and feeding them to a local LLM. It supports GGUF/GGML models via CTransformers, Hugging Face Transformers models, and GPTQ quantization. A YAML config controls embedding models, chunk sizes, retrieval parameters, and LLM options. All processing happens on-device with no data leaving the system.
Frequently asked
- What is marella/chatdocs?
- Offline document Q&A tool that runs local LLMs (Transformers, GGUF, GPTQ) with a web UI to chat over PDFs, Word docs, and other file types.
- Is chatdocs open source?
- Yes — marella/chatdocs is open source, released under the MIT license.
- What language is chatdocs written in?
- marella/chatdocs is primarily written in Python.
- How popular is chatdocs?
- marella/chatdocs has 737 stars on GitHub.
- Where can I find chatdocs?
- marella/chatdocs is on GitHub at https://github.com/marella/chatdocs.