benderscript/netvision

Network Topology Image Analsysis

NetVision - A GenAI Application for Networking Topology Image Analysis

This application leverages Streamlit and OpenAI's GPT-4V model to analyze networking topology images. It provides a user-friendly interface that allows users to upload images of network topologies and receive insights and analyses generated by the GPT-4V model.

Features

• Upload interface for network topology images.
• Real-time analysis of images using OpenAI's GPT-4V.
• Interactive chat interface to discuss and query network topology features.
• Session state management to maintain interaction history.

Application Demo

See the application in action:

Prerequisites

• Python 3.12+
• Poetry for dependency management
• An OpenAI API key or Azure OpenAI deployment with vision support

Installation

Setting Up the Environment

1. Clone the repository:

   git clone https://your-repository-url
   cd your-project-directory

2. Install dependencies using Poetry:

   poetry install

Configuring the OpenAI API Key

1. Create a .env file in the root directory of the project and add your OpenAI API key:

   OPENAI_API_KEY=your_openai_api_key
   

2. Alternatively create a .env.azure and add your information such as:

   AZURE_OPENAI_API_KEY=<key>
   AZURE_OPENAI_ENDPOINT=<Azure endpoint URL>
   AZURE_OPENAI_API_VERSION=2024-02-15-preview
   AZURE_OPENAI_DEPLOYMENT=<your deployment name>

Running the Application

To run the Streamlit application, use Poetry to handle the environment:

poetry run streamlit run main.py

Navigate to http://localhost:8501 in your web browser to interact with the application. Upload your network topology images to receive detailed analyses and insights.

Contributing

Contributions are welcome! Please read CONTRIBUTING.md for how to contribute to this project.

License

This project is licensed under the Apache-2.0 - see the LICENSE file for details.

Acknowledgments

• Streamlit for providing an excellent platform to build interactive apps.

Support

For support, open an issue in the GitHub repository or contact the project maintainers.