This repo uses Ollama, which should be downloaded for your OS. Install the requirements:

pip install -r requirements.txt

run the app:

streamlit run app.py

Using a local LLM of your choice you can perform the usual chat, obtain help with code etc. You can also use the RAG page to generate responses based on the text.

• LLM it made available with Ollama
• LLM indegration uses llama-index
• Vector store for document embeddings with chromadb