This repository contains a Python script which can be used for running a retrieval-augmented generation (RAG) locally using Ollama.
- Install Ollama and pull the model you want (mistral as LLM and nomic-embed-text for embedding were used for this project)
- Clone the repository
- Set up a virtual environment
- Install dependencies using
pip install -r requirements.txt - Start the Ollama server
- Run the script