Visual QnA is an innovative project that combines image recognition and natural language processing to provide users with a comprehensive question-answering system using Gemini Pro Api. Leveraging the power of AI, this platform allows users to ask queries about images or pose general questions, making it amazing for education, research, and everydayUse.
- Step 1: Clone this repo
- Create Virtual Enviornment if required using (conda create -p ./venv python=3.11 -y)
- Activate the environment using (conda activate ./venv)
- Step 2: Go to Terminal and run the command ( pip install -r requirements.txt )
- Now all required libraries and frameworks will be installed
- Step 3: Create Gemini Pro API key from this link
- Save this API key into .env file and run the app.py file
- Step 4: Now run the code into Terminal (streamlit run streamlit_app.py )