经 AI Skill Hub 精选评估,Controllable-RAG-Agent — AI Agent 工作流中文教程 获评「强烈推荐」。已获得 1.6k 颗 GitHub Star,这款AI工具在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 8.2 分,适合有一定技术背景的用户使用。
基于图算法的高级检索增强生成(RAG)解决方案,专为复杂问答任务设计。支持LangChain/LangGraph框架,提供可控的信息检索和生成流程。适合需要构建企业级智能问答系统的开发者和AI研究人员。
Controllable-RAG-Agent — AI Agent 工作流中文教程 是一款基于 Jupyter Notebook 开发的开源工具,专注于 RAG、LLM、LangGraph 等核心功能。作为 GitHub 开源项目,它拥有活跃的社区支持和持续的版本迭代,代码完全透明可审计,支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流,都能提供稳定可靠的解决方案。
基于图算法的高级检索增强生成(RAG)解决方案,专为复杂问答任务设计。支持LangChain/LangGraph框架,提供可控的信息检索和生成流程。适合需要构建企业级智能问答系统的开发者和AI研究人员。
Controllable-RAG-Agent — AI Agent 工作流中文教程 是一款基于 Jupyter Notebook 开发的开源工具,专注于 RAG、LLM、LangGraph 等核心功能。作为 GitHub 开源项目,它拥有活跃的社区支持和持续的版本迭代,代码完全透明可审计,支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流,都能提供稳定可靠的解决方案。
# 克隆仓库 git clone https://github.com/NirDiamant/Controllable-RAG-Agent cd Controllable-RAG-Agent # 查看安装说明 cat README.md # 按 README 完成环境依赖安装后即可使用
# 查看帮助 controllable-rag-agent --help # 基本运行 controllable-rag-agent [options] <input> # 详细使用说明请查阅文档 # https://github.com/NirDiamant/Controllable-RAG-Agent
# controllable-rag-agent 配置说明 # 查看配置选项 controllable-rag-agent --config-example > config.yml # 常见配置项 # output_dir: ./output # log_level: info # workers: 4 # 环境变量(覆盖配置文件) export CONTROLLABLE_RAG_AGENT_CONFIG="/path/to/config.yml"
An advanced Retrieval-Augmented Generation (RAG) solution designed to tackle complex questions that simple semantic similarity-based retrieval cannot solve. This project showcases a sophisticated deterministic graph acting as the "brain" of a highly controllable autonomous agent capable of answering non-trivial questions from your own data.

Ragas metrics for comprehensive quality assessment.1. Clone the repository:
git clone https://github.com/NirDiamant/Controllable-RAG-Agent.git
cd Controllable-RAG-Agent
2. Set up environment variables: Create a .env file in the root directory with your API key: OPENAI_API_KEY=
GROQ_API_KEY=
you can look at the .env.example file for reference.
3. run the following command to build the docker image
docker-compose up --build
3. Install required packages:
pip install -r requirements.txt
The algorithm was tested using the first Harry Potter book, allowing for monitoring of the model's reliance on retrieved information versus pre-trained knowledge. This choice enables us to verify whether the model is using its pre-trained knowledge or strictly relying on the retrieved information from vector stores.
sophisticated_rag_agent_harry_potter.ipynb2. Run real-time agent visualization (no docker):
streamlit run simulate_agent.py
3. Run real-time agent visualization (with docker): open your browser and go to http://localhost:8501/
| 🎬 7-minute video lecture |
🛠️ Hands-on tutorial |
🤖 AI assistant inside Claude Code |
One npm install adds the module's AI assistant to your Claude Code, and it guides you through the tutorial as you build.
<a href="https://europe-west1-rag-techniques-views-tracker.cloudfunctions.net/rag-techniques-tracker?notebook=controllable-rag-agent--readme&click=course-free-module-cta&target=https%3A%2F%2Fwww.diamant-ai.com%2Fcourses%3Futm_source%3Dgithub%26utm_medium%3Dreadme%26utm_campaign%3Dcontrollable-rag-agent&retarget=0&text=course-free-module-cta"><img src="assets/free-module-button.svg" alt="Claim your free module" width="420"></a>
Q: How did the protagonist defeat the villain's assistant?
To solve this question, the following steps are necessary:
The agent's ability to break down and solve such complex queries demonstrates its sophisticated reasoning capabilities.
For questions like "How did the protagonist defeat the villain's assistant?", the agent: 1. Identifies the protagonist 2. Identifies the villain 3. Identifies the villain's assistant 4. Searches for confrontations between protagonist and villain 5. Deduces the reason for defeating the assistant
This demonstrates sophisticated reasoning beyond simple retrieval.
设计理念先进,图算法应用创新。代码质量好,文档完整。1600+星表明社区认可度高,是RAG领域的优质开源项目。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ Apache 2.0 — 宽松开源协议,可商用,需保留版权声明和 NOTICE 文件,含专利授权条款。
AI Skill Hub 点评:Controllable-RAG-Agent — AI Agent 工作流中文教程 的核心功能完整,质量优秀。对于AI爱好者来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。
| 原始名称 | Controllable-RAG-Agent |
| 原始描述 | This repository provides an advanced Retrieval-Augmented Generation (RAG) solution for complex question answering. It uses sophisticated graph based algorithm to handle the tasks. |
| Topics | RAGLLMLangGraph智能体图算法 |
| GitHub | https://github.com/NirDiamant/Controllable-RAG-Agent |
| License | Apache-2.0 |
| 语言 | Jupyter Notebook |
收录时间:2026-05-22 · 更新时间:2026-05-30 · License:Apache-2.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。