Operationalizing Generative AI on Vertex AI

Explore the challenges and opportunities of operationalizing generative AI on Vertex AI in this 47-minute conference talk from Google Cloud Next 2024. Dive into the fundamental principles of MLOps and learn how they must be adapted for generative AI workflows. Discover the capabilities of Vertex AI that support this new paradigm, including model selection, data curation, prompt engineering, task-specific fine-tuning, grounding model outputs in real-world data, and hardware optimization. Join speakers Chase Lyall, Mikhail Chrestkha, Matt Ferrari, and Debasish Das as they guide you through the complexities of working with foundation models and large language models in production environments.