Multimodal Conversational Interfaces with GPT and Vision AI

Discover the groundbreaking GPT-4 Visual model from OpenAI, introducing multimodal input and output capabilities in this 41-minute conference talk. Explore the integration of GPT-4 Visual into Azure Cognitive Search and its enhancement with vision embeddings, revolutionizing AI-driven information retrieval. Learn how images and videos can now prompt or supplement prompts to large language models like GPT-4. Gain insights into new multimodal models for Azure AI Content Safety, part of Microsoft's Responsible AI product suite. Presented by a panel of experts including Fisayo Feyisetan, Theodoros Lappas, and Thomas Soemo, this session from Microsoft Ignite 2023 offers valuable resources and information on transforming conversational interfaces with cutting-edge AI technology.