A Curated List of LLM-Aided Tools with Retrieval Augmented Generation (RAG)
This repository offers a comprehensive collection of RAG modules, tools, chatbots, and tutorials. Explore various resources to help you integrate Retrieval-Augmented Generation into your AI projects.
- Dify: Develop LLM apps with features like AI workflows, RAG pipelines, agent capabilities, and more.
- Lobe Chat: A multi-modal AI chat framework supporting various LLM providers and a one-click deployment of private AI chat applications.
- Open WebUI: A user-friendly WebUI for LLMs, formerly known as Ollama WebUI.
- Quivr: Build RAG-based productivity assistants or document/chat-based apps with a shareable interface.
- Anything-LLM: A versatile desktop and Docker AI application with built-in RAG and agent capabilities.
- FastGPT: A platform for building complex question-answering systems with RAG retrieval and visual AI orchestration.
- HayStack: An AI orchestration framework to build customizable LLM applications suited for RAG, question answering, and semantic search.
- DocsGPT: A GPT-powered chatbot to interact with your documentation.
- DB-GPT: A data-centric development framework with agentic workflows.
- Khoj: Use AI as your second brain, available locally or in the cloud, across different platforms like Obsidian, Emacs, or WhatsApp.
- Kotaemon: A tool for chatting with your documents, powered by RAG.
- Vanna: Use RAG to chat with your SQL database for accurate text-to-SQL generation.
- MemGPT: Create LLM agents with long-term memory and custom tools
- Verba: A Weaviate-powered RAG chatbot.
- RagApp: Simplify agentic RAG usage in enterprise applications.
- Rags: Build a ChatGPT-like interface for interacting with your own data.
- RAG with PDF: A specialized RAG tool for PDF document interaction.
- AdaptiveRag: "Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity" (NAACL 2024).
- SelfRag: SELF-RAG: Learning to Retrieve, Generate and Critique through self-reflection (ICLR 2024, Oral top 1%) by Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi.
- GraphRAG: A graph-based approach to Retrieval-Augmented Generation.
- Mem0: A memory layer designed for AI apps, enabling context retention over extended interactions.
- Chunking methods: Text splitter, character splitter, semantic splitters etc.
- Propositional Chunking: trained on wiki.
- RAGFlow: A deep document understanding engine to enhance RAG.
- Flowise: A drag-and-drop UI for building customized LLM workflows.
- FireCrawl: Easily convert entire websites into LLM-ready markdown or structured data with a single API.
- RAG from Scratch: Learn how to implement RAG using LangChain with this step-by-step tutorial.
- RAG Techniques: A curated collection of RAG-related techniques and resources.
Stay updated as this list grows with new and exciting RAG developments!