Going Multi-Modal: Integrating Voice, Text and Images in Azure AI RAG Applications

Zahhar Kirillov (EPAM Systems)
Lingua: Inglese
Orario: 16:30  -  17:15

Multimedia processing is a very exciting and forward-looking area in Generative AI. As an engineer, I was keen to understand how to build more sophisticated, feature-rich and user-friendly applications by integrating different data types - images, audio and text. We will take a look into business use-cases that require multimedia processing in RAG applications and how they could be supported by Azure AI toolset.