💼法律AI助手,法律RAG,通过全部200+本法律手册📖、网页搜索内容💻结合LLM回答你的问题,并且给出相应的法规和网站,基于⚡️ langchain,Gradio,ope...
Best RAG Tools
RAG (retrieval-augmented generation) connects your documents and data to LLMs. Browse popular GitHub projects below (ranked by stars), then compare top picks for stack fit.
Popular on GitHub (by stars)
1,168 projects · ranked by GitHub stars, not a quality score
A financial chat application powered by LangChain, OpenBB, and Claude 3 Opus.
An open-source, vector-free long-term memory engine for AI agents, achieving SOTA on LoCoMo and LongMemEval with significantly less context.
pgvector for PostgreSQL Windows (native compiled in Microsoft Windows environment)
参考GraphRag使用 Semantic Kernel 来实现的dotnet版本,可以使用NuGet开箱即用集成到项目中
A native macOS app that turns GitHub Stars into a searchable, organized, AI-powered personal knowledge base.
Implementation of an AI Instructor using LLMs and Langchain
Official code for ACL2025 "🔍 Retrieval Models Aren’t Tool-Savvy: Benchmarking Tool Retrieval for Large Language Models"
AI-powered Moodle plugin for tutoring, quizzes, mind maps, RAG course materials and more.
Open-source RAG evaluation through users' feedback
High-performance KV cache storage for LLM inference — GPU offloading, SSD caching, and cross-node sharing via RDMA. Works with vLLM and SGLa...
Free, open-source Mac utility: start dragging any file, tap a key, and drop it on a wheel to convert, edit, AirDrop or shelve it. Runs fully...
PDF解析(文字,章节,表格,图片,参考),基于大模型(ChatGLM2-6B, RWKV)+langchain+streamlit的PDF问答,摘要,信息抽取
An SVG week calendar for Emacs, backed by Org files. Drag to create, move and resize; a read-only day strip for Org Agenda.
Visualization for a Retrieval-Augmented Generation (RAG) Assistant 🤖❤️📚
Self-hosted academic chatbot, research workspaces and editor (LaTex, Typst, markdown, ...) leveraging local and leading AI models.
Self-hostable multimodal chat with local LLMs (Ollama/OpenAI): PDF RAG, image chat, and Whisper voice, Streamlit + Docker.
CLI application that encourages you to keep up with your projects. "Feed" tux in your terminal by pushing your code to github.
Framework profissional de orquestracao multi-agente em Python: crews, flows orientados a eventos, ReAct, RAG, memoria, MCP/A2A e multi-provi...
Provenance-first extractive RAG: return verbatim source spans with citations using local ModernBERT or optional LLM-assisted extraction.
Serverless AI agent using LangChain.js and Model Context Protocol (MCP) integration to order burgers from a burger restaurant
A custom RAG pipeline for multi-document QA from PDF/DOCX documents, in Android
NuGet package designed to make LLMs, RAG, and Agents first-class citizens in .NET
A pure-Python context management layer for LLM systems — retrieval, re-ranking, memory decay, and token-budget enforcement in one pipeline.