Mental Health Chatbot

Retrieval Augmented Generation (RAG) combines the power of LLMs with external knowledge base.

How to run

1. Install Ollama and Mistral

curl -fsSL https://ollama.com/install.sh | sh
ollama run mistral

2. Run Ollama

make llm

3. Start Milvus (Docker should be running)

make start-milvus

4. Create a virtual env and install requirements

conda create -n llm python==3.9.16
conda activate llm
pip install -r "requirements.txt"

5. Run app

make streamlit-new # For first time
make streamlit # After vector db has been created