Prepare to master common generative AI use cases with ease
summary
Snowflake demonstrates a concrete GenAI stack: Cortex for built-in functions, the open LLM Arctic available in the Azure model catalog, and Snowpark External Access to call Azure OpenAI. The demo builds a wardrobe recommender (image + URL table → Azure OpenAI) as a Streamlit app that runs from two scripts — about 41 lines of code for the UI — and claims full setup in 30–40 minutes; sentiment and embedding/vector types live inside Snowflake.
AI-written summary · about
chapters (10)
- 0:00Introduction
- 1:12Generative AI use cases
- 3:18Snowflake Cortex platform
- 5:24Snowflake LLM Arctic
- 6:48Architecture demo
- 8:10Wardrobe recommender demo
- 10:58Sentiment analysis with Cortex
- 13:22Search and embeddings
- 14:44Self-service data access
- 15:05Resources and next steps
related talks
29mBuilding End to End Gen AI Powered Analytics: From Data to Production
01h 13mBuilding a Semantic AI Layer in Snowflake: From Metrics to AI Insights
23mAcceleratinag Data Science and Machine Learning with Snowflake DataTech
15mEnterprise AI Runs on Trusted Data
49mLLM inference and fine-tuning on secure enterprise data
15mFrom Air Quality to Aircraft and Automobiles, Data Is Everywhere
01h 10mPractical Applications of Generative AI: How to Sprinkle a Little AI in Your App
31mAI-driven DataOps: Building data products with a taste of the future