Snowflake Notebooks on Container Runtime are a powerful IDE option for building ML workloads at scale. Container Runtime (Public Preview) gives you a flexible container infrastructure that supports building and operationalizing a wide variety of resource-intensive ML workflows entirely within Snowflake.
This notebook demonstrates how you can load an open source embedding model, generate embeddings using a GPU, evaluate a dataset for a RAG solution, deploy the embedding model, perform large scale batch inference, and save results to a Snowflake table without a lot of complex infrastructure setup and management.
For prerequisites, setup, step-by-step guide and instructions, please refer to the QuickStart Guide.