R

Retrieval Augmented Generation

A multi-user ChatGPT for any LLMs and vector database. Unlimited documents, messages, and storage in one privacy-focused app. Now available as a desktop application with a built-in LLM!

🔧🔗https://github.com/open-webui/open-webui User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

🕸️🔗https://openwebui.com/

🔧🔗https://github.com/modelscope/modelscope-agent

ModelScope-Agent: An agent framework connecting models in ModelScope with the world

🔧🔗https://github.com/patchy631/ai-engineering-hub In-depth tutorials on LLMs, RAGs and real-world AI agent applications.

🔧🔗https://github.com/gabosgab/ObsidianPrivateAI A plugin for obsidian that makes it easy to interact with a local LLM

🔧🔗https://github.com/maragudk/gai-starter-kit Get started with LLMs, FTS and vector search, RAG, and more, in Go!

🔧🔗https://github.com/brianstm/obsidian-vault-llm-assistant

An obsidian notebook plugin that uses LLM (OpenAI or Gemini) to answer questions and create new n

🔧🔗https://github.com/manimohans/obsidian-local-llm-helper Seamlessly integrate your local LLM with Obsidian. Process large text chunks, transform content with AI, chat with your notes and maintain data privacy — all without leaving your notes.

🔧🔗https://github.com/jjwheatley/mini-rag Local Retrieval Augmented Generation for your Obsidian notes

🔧🔗https://github.com/AkariAsai/OpenScholar This repository includes the official implementation of OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs.

🔧🔗https://github.com/AsyncFuncAI/alphaxiv-open AlphaXIV open-source alternative: Chat with any arXiv paper.

🔧🔗https://github.com/MODSetter/SurfSense Open Source Alternative to NotebookLM / Perplexity / Glean, connected to external sources such as search engines (Tavily, Linkup), Slack, Linear, Notion, YouTube, GitHub and more.

🔧🔗https://github.com/Gurubase/gurubase Gurubase lets you add an "Ask AI" button to your technical docs, turning your content into an AI assistant. It uses web pages, PDFs, YouTube videos, and GitHub repos as sources to generate instant, accurate answers with references. Deploy it via Slack, Discord, GitHub or a web widget.

https://github.com/run-llama/mongodb-demo LlamaIndex retrieval augmented generation with MongoDB, Flask and Next.js