Description:
A Retrieval-Augmented Generation (RAG) system that uses Ollama to enable intelligent document understanding. It employs two separate models — one for embedding documents and another for semantic question answering — to provide contextual responses based on the ingested content.

• Document embedding for efficient vector search
• Semantic answering based on document context
• Node.js-based frontend for interaction
• Python backend to orchestrate retrieval and generation

Follow the installation instructions for your operating system:
https://ollama.com/download

Open a terminal and pull the necessary models:

ollama pull nomic-embed-text # For document embedding
ollama pull llama3 # For question answering

cd app
npm install
npm run dev

pip install -r requirements.txt

python3 -m venv .venv 

.venv\Scripts\activate

python main.py