Add VLM model and UI support to Virtual AI Assistant Demo

[riacheruvu]

Description

Add a Vision-Language Model (VLM) and update the user interface (UI) to accommodate this new feature for the Virtual AI Assistant demo. This enhancement will allow the assistant to process and understand visual inputs in addition to text, making it more versatile and interactive.

This project will involve Python programming; basic experience with AI models from frameworks like PyTorch, TensorFlow, OpenVINO, or ONNX is beneficial. To learn more about the OpenVINO toolkit, visit the documentation here.

Steps:

1. Add optional VLM Model Support:

   • Integrate a Vision-Language Model (VLM) into the Virtual AI Assistant demo, via a command line parameter. A great place to start is looking at the OpenVINO Notebooks repository for different VLM models that are supported, and exploring how to port it to the OpenVINO Build Deploy repository's demo format.
   • Ensure the model can process and understand visual inputs, such as images, and generate appropriate responses.

2. Update User Interface:

   • Modify the UI to support visual inputs, allowing users to upload images or use a webcam.
   • Ensure the UI is intuitive and user-friendly, providing clear instructions for interacting with the assistant.

3. Enhance User Experience:

   • Use optimizations to ensure the VLM model operates efficiently, maintaining results within a reasonable time frame (without significantly slowing down the current demo).
   • Add real-time data visualization to display the assistant's understanding of visual inputs.

4. Documentation:

   • Provide clear and detailed documentation for setting up and running the enhanced demo.
   • Include comments in the code to explain key sections and logic.

How to Get Started:

1. Fork the OpenVINO Build Deploy repository.
2. Follow these installation instructions to setup your environment and install the required dependencies for this project.
3. Read Demo Contribution Guide.
4. Build your feature and ensure it meets the requirements specified in the contribution guide.
5. Submit a pull request.