This project implements a Retrieval-Augmented Generation (RAG) model from scratch using Python. It integrates a retrieval mechanism (such as cosine similarity) with a language generation model to recommend activities based on user input.
The RAG model combines a retrieval component with a generation component to enhance the quality of generated text. This implementation demonstrates how to use Python to build and deploy a recommendation system that responds to user queries with concise activity suggestions.
To set up this project locally, follow these steps:
-
Clone the repository:
git clone https://github.com/KasimVali2207/RAG_Implementation-From-Scratch.git cd RAG_Implementation-From-Scratch -
Install dependencies:
- Ensure you have Python installed (version >= 3.6)
- Install required packages using pip:
pip install -r requirements.txt
-
Download and setup ollama:
- Download ollama from ollama.com/download.
- Open a command prompt or terminal and navigate to the downloaded ollama directory.
- Run the following command to start the llama2 model:
ollama run llama2