Large Language Models have shown impressive capabilities and they are still undergoing steady improvements with each new generation of models released. Applications such as chatbots and summarisation…

Towards Data Science is a community-powered publication that showcases work in data science, machine learning and artificial intelligence. Every day newcomers, seasoned researchers and industry practitioners publish tutorials, research notes and real-world case studies that help the field move forward.

Towards Data Science

The post provides a detailed tutorial on using a small open-source large language model, Qwen2.5–7B-Instruct, to create a local multi-agentic RAG (Retrieval Augmented Generation) system using Hugging Face code agents. It explains the architecture and functionality of multi-agent systems, particularly code agents, and their advantages. Key details include the ReAct framework for LLM agents, the specific roles of manager, Wikipedia search, and page search agents, and security measures for code execution.

Multi-Agentic RAG with Hugging Face Code Agents