jonfairbanks/local-rag
A self-hosted retrieval augmented generation application that ingests local files, GitHub repositories, and websites for use with local Ollama models.
Not currently ranked — collecting fresh signals.
star history
Local RAG provides a browser-based interface for ingesting documents from local files, GitHub repositories, and websites into a vector store. It uses Ollama to serve chat models and HuggingFace or Ollama embedding models locally, keeping all data and model inference on-premises. The pipeline streams responses via LlamaIndex, preserving chat history and source citations without sending sensitive data to third parties.
Frequently asked
- What is jonfairbanks/local-rag?
- A self-hosted retrieval augmented generation application that ingests local files, GitHub repositories, and websites for use with local Ollama models.
- Is local-rag open source?
- Yes — jonfairbanks/local-rag is open source, released under the GPL-3.0 license.
- What language is local-rag written in?
- jonfairbanks/local-rag is primarily written in Python.
- How popular is local-rag?
- jonfairbanks/local-rag has 754 stars on GitHub.
- Where can I find local-rag?
- jonfairbanks/local-rag is on GitHub at https://github.com/jonfairbanks/local-rag.