RAG

开源 RAG 框架

检索增强生成（RAG）让大模型根据你自己的文档回答问题：文本先被切成小块、转成向量、存进索引，提问时把最相关的几块加进提示词。这里的项目覆盖整条管线，或其中一环：文档解析、向量检索，或者完整的问答应用。

怎么选

RAG 的回答质量主要取决于检索，而不是模型。比较时看：它怎么处理 PDF、表格、扫描件这类难文档；是否支持关键词加向量的混合检索和重排序；以及能不能显示答案出自哪些来源。

Star 最多的项目

第 25–48 个，共 176 个

simstudioai

sim

★ 29,630

构建、部署和编排 AI 代理。 Sim 是 AI 员工队伍的中央智能层。

TypeScript

NirDiamant

RAG_Techniques

★ 29,490

This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial.

Jupyter Notebook

deepset-ai

haystack

★ 26,514

开源 AI 编排框架，用于构建上下文工程、生产就绪的 LLM 应用程序。通过对检索、路由、内存和生成的显式控制来设计模块化管道和代理工作流程。专为可扩展代理、RAG、多模式应用程序、语义搜索和对话系统而构建。

Python

promptfoo

★ 25,137

测试您的提示、代理和 RAG。 AI 红队/渗透测试/漏洞扫描。比较 GPT、Claude、Gemini、DeepSeek 等的性能。具有命令行和 CI/CD 集成的简单声明性配置。由 OpenAI 和 Anthropic 使用。

TypeScript

NirDiamant

GenAI_Agents

★ 24,294

50+ tutorials and implementations for Generative AI Agent techniques, from basic conversational bots to complex multi-agent systems.

Jupyter Notebook

Tencent

WeKnora

★ 23,952

Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.

AccumulateMore

CV

★ 23,709

✅（已完结）超级全面的深度学习笔记【土堆 Pytorch】【李沐动手学深度学习】【吴恩达深度学习】【大飞大模型Agent】

Jupyter Notebook

1Panel-dev

MaxKB

★ 22,798

MaxKB 是一个用于构建企业级代理的开源平台。。

Python

comet-ml

opik

★ 22,040

Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.

Python

NirDiamant

agents-towards-production

★ 21,459

End-to-end, code-first tutorials for building production-grade GenAI agents. From prototype to enterprise deployment.

Jupyter Notebook

liyupi

程序员鱼皮的 AI 资源大全 + Vibe Coding 零基础教程，分享 OpenClaw 保姆级教程、大模型玩法（DeepSeek / GPT / Gemini / Claude / GLM）、最新 AI 资讯、Prompt 提示词大全、AI 知识百科（Agent Skills / RAG / MCP / A2A）、AI 编程教程（Harness Engineering）、AI 工具用法（Cursor / Claude Code / TRAE / Codex / Copilot）、AI 开发框架教程（Spring AI / LangChain）、AI 产品变现指南，帮你快速掌握 AI 技术，走在时代前沿。本项目为开源文档 aiguide，已升级为鱼皮 AI 导航网站

JavaScript

eosphoros-ai

DB-GPT

★ 19,968

open-source agentic AI data assistant for the next generation of AI + Data products.

Python

elizaOS

eliza

★ 19,341

开源代理操作系统。 elizaOS 上的应用程序 elizaOS 运行应用程序，而不仅仅是代理。

TypeScript

stas00

ml-engineering

★ 18,997

Machine Learning Engineering Open Book

Python

metainternal

llama-cookbook

★ 18,560

Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services

Jupyter Notebook

arc53

DocsGPT

★ 18,263

Private AI platform for agents, assistants and enterprise search. Built-in Agent Builder, Deep research, Document analysis, Multi-model support, and API connectivity for agents.

Python

langbot-app

LangBot

★ 17,831

Production-grade platform for building agentic IM bots - 生产级多平台智能机器人开发平台/ Agent、知识库编排、插件系统 / Bots for Discord / Slack / LINE / Telegram / WeChat(企业微信, 企微智能机器人, 公众号) / 飞书 / 钉钉 / QQ / Matrix e.g. Integrated with ChatGPT(GPT), DeepSeek, Dify, n8n, Langflow, Coze, Claude, Gemini, GLM, Ollama, SiliconFlow, Moonshot, openclaw / hermes agent, deerflow

Python

Canner

WrenAI

★ 17,649

GenBI (Generative BI) for AI agents, an open-source, governed text-to-SQL through an open context layer that turns natural-language questions into trusted dashboards, charts, and SQL across 20+ data sources, such as BigQuery, Snowflake, PostgreSQL, ClickHouse, Amazon Redshift, Databricks and more.

Python

RyanCodrai

turbovec

★ 17,181

基于 TurboQuant 构建的向量索引，使用 Rust 编写并结合 Python 绑定。

Python

MemoriLabs

Memori

★ 16,754

Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems. Built for enterprise, Memori works with the data infrastructure you already run, no rip-and-replace, and deploys across managed cloud, single-tenant cloud, VPC, and on-premises.

Python

memvid

★ 16,542

Memory layer for AI Agents. Replace complex RAG pipelines with a serverless, single-file memory layer. Give your agents instant retrieval and long-term memory.

Rust