yashbonde / cf_demo

🦋 ChainFury Retrieval Augmented Generation (RAG)

Welcome to the ChainFury Retrieval Augmented Generation (RAG) demo! 🎉

• 🔗 Click here to try the demo
• 📚 Access the Blitzscaling PDF

Environment Setup

Before we begin, make sure to set the following environment variables:

For LLM you can use one of the two

• 🔸 CHATNBX_KEY - Your ChatNBX Token ("tune-xxxxx"), see more at ChatNBX
• 🔸 OPENAI_TOKEN - Your OpenAI Token ("sk-xxxxx") also set USE_OPENAI=1

For vector database we use qdrant:

• 🔸 QDRANT_API_KEY - Your QDRANT API Key ("hbl-xxxxxx")
• 🔸 QDRANT_API_URL - The URL for the QDRANT API ("https://xxx")

Step One: Loading the data on qdrant

To load the data on qdrant, follow these steps:

1. Install the necessary requirements by running the following command:

   pip install -r requirements_dev.txt
   python3 load_data.py --help

Step Two: Running the streamlit app

To run the streamlit app, follow these steps:

1. Install the required dependencies (ignore this step if you already have the dev requirements installed) by running:

   pip install -r requirements.txt

2. Run the streamlit app using the following command:

   streamlit run streamlit_app.py

That's it! You're all set to explore the power of ChainFury RAG using the provided demo. 🚀