PPMExplorer

PPMExplorer is a project aimed to drawing new insights from images and captions in the Pompei: Pitture e Mosaic (PPM) encyclopedia set. The project uses Svelte for building the web application, Microsoft Azure AI Vision API for generating image and caption feature vectors, and Microsoft Azure Cosmos DB for storing and indexing the data.

Background

Dr. Cindy Roulette, a former Ph.D. student at the University of Arkansas, developed a similar application using Unity in 2020. Our objective for this project is to recreate the application in a web-based format and modernize its features to incorporate advancements in computer vision, natural language processing, and artificial intelligence.

What are feature vectors?

Feature vectors are numerical representations of data that can be used to compare and analyze the similarity between different data points. In the context of this project, we query vectorized user input against a database of vectorized images and captions to find the most similar matches.

Source

Local Development

To set up the project locally, follow these steps:

1. Install Node.js:

If you don't have Node.js installed, download and install the latest version from the official website.

2. Clone the repository:

git clone https://github.com/cadedupont/ppmexplorer.git
cd ppmexplorer

3. Install dependencies:

npm install

4. Obtain necessary API keys:

Contact the project owners to obtain the required API keys and add them to a .env file in the root directory of the project.

5. Run the development server:

npm run dev

or

npm run dev -- --open

to open the application in your default browser.

Contact

For any inquiries, please contact the project owners: