GDG-RAG-Demo

View the UI of the live app at VaultApp
View the code in Google Colab at GoogleColab

Supported Python versions

Instructions

Recommended system specifications

• GPU: 8 GB VRAM
• RAM: 16 GB RAM

How to run the Streamlit application

• Make sure you have Python and Git installed on your system

• Clone the repository on to your local machine using Git

  git clone https://github.com/jonathanjthomas/GDG-RAG-Demo.git

• Navigate to the repository directory

• Set up a virtual environment using the below command

  python -m venv venv

• Activate your virtual environment using

  • Windows

    venv\Scripts\Activate

  • Linux and MacOS

    source venv/bin/activate

• Install all the required libraries and dependencies

  pip install -r requirements.txt

• Download and install Ollama

• Pull the required Ollama models (gemma2:2b and nomic-embed-text)

  ollama pull gemma2:2b
  ollama pull nomic-embed-text

• Run vault.py with streamlit

  streamlit run code\vault.py or python -m streamlit run code\vault.py

Debugging

• If you face any conflicts with existing dependencies, make sure you have activated your virtual environment

• If you run into an error showing:

  httpx.ConnectError: [WinError 10061] No connection could be made because the target machine actively refused it

  Then try running the following to resolve the issue

  ollama serve

• If you run into any other issues which have not been listed above, please feel free to reach out to us

Additional Resources

Source code on Google Colab
Gemma 2 - Local RAG with Ollama and LangChain
How to Build a Local RAG Knowledge Base with Google Gemma 2 2B

Reach Out

Have any doubts? Feel free to reach out to us at:

• Aditya S ([email protected])
• Jonathan John Thomas ([email protected])