How to scale Gen AI to billions of rows in BigQuery at a fraction of the cost

Documentation for Optimized Mode → https://goo.gle/optimize-ai-functions Generative AI in BigQuery overview → https://goo.gle/bq-genai-overview For many, running generative AI over massive datasets has felt out of reach due to costs and slow processing times. Others settle for traditional ML techniques that require specialized skill sets and often deliver lower-quality results. With optimized mode for BigQuery AI functions, you can now get LLM-quality results at a fraction of the cost and at BigQuery speeds. In this video, we’ll show you how BigQuery uses model distillation and embeddings to process massive datasets, reducing query latency and token consumption. Chapters: 0:00 - Challenge of scaling Gen AI 1:07 - Introducing optimized mode for BigQuery AI 1:22 - How It Works: Model distillation and embeddings 1:57 - Automatic optimization with AI.IF and AI.CLASSIFY 2:16 - Demo: Analyzing images and text with optimized mode 4:23 - Conclusion & next steps 🔔 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech #BigQuery #GoogleCloud #Gemini #GenAI #SQL #DataAnalytics Speaker: Rushabh Desai Products Mentioned: BigQuery