local-rag

local-rag

Ingest files for retrieval augmented generation (RAG) with open-source Large Language Models (LLMs), all without 3rd parties or sensitive data leaving your network.

Stars: 392

Visit
 screenshot

Local RAG is an offline, open-source tool that allows users to ingest files for retrieval augmented generation (RAG) using large language models (LLMs) without relying on third parties or exposing sensitive data. It supports offline embeddings and LLMs, multiple sources including local files, GitHub repos, and websites, streaming responses, conversational memory, and chat export. Users can set up and deploy the app, learn how to use Local RAG, explore the RAG pipeline, check planned features, known bugs and issues, access additional resources, and contribute to the project.

README:

📚 Local RAG

local-rag-demo

OpenSSF Best Practices GitHub Commit Activity GitHub Last Commit GitHub License

Offline, Open-Source RAG

Ingest files for retrieval augmented generation (RAG) with open-source Large Language Models (LLMs), all without 3rd parties or sensitive data leaving your network.

Features:

  • Offline Embeddings & LLMs Support (No OpenAI!)
  • Support for Multiple Sources
    • Local Files
    • GitHub Repos
    • Websites
  • Streaming Responses
  • Conversational Memory
  • Chat Export

Learn More:

For Tasks:

Click tags to check more tools for each tasks

For Jobs:

Alternative AI tools for local-rag

Similar Open Source Tools

For similar tasks

For similar jobs