Conversational Chatbot with Retrieval-Augmented Generation (RAG)

This repository demonstrates how to build a conversational chatbot with retrieval-augmented generation (RAG) using the Hugging Face ecosystem. We will be employing the chatbot developed in the basic-chatbot repo with the focus being to incorporate RAG.

Getting Started

• This project relies on python=3.12. It was not tested with different versions
• Clone the repository to your local machine
• Once you have, cd into this repo and create the virtual environment (assuming you have conda installed) via

conda env create -f environment.yml

• Enter the virtual environment with conda activate rag-chatbot-env
• Install the packages in the repo root directory using pip install -e . (you only need the -e option if you intend to edit the source code in rag_chatbot/)

Example

See my website for examples on how to use this code.

Citation

If you use this project, please use the citation information provided by GitHub via the “Cite this repository” button or cite it as follows:

@software{Garcia2026RAGChatbot,
  author = {Alberto J. Garcia},
  title = {Conversational Chatbot with Retrieval-Augmented Generation (RAG)},
  year = {2026},
  publisher = {GitHub},
  url = {https://github.com/AJG91/rag-chatbot},
  license = {MIT}
}