April 14, 2025 — Snowflake Cortex AI COMPLETE multimodal support — Preview

Snowflake announces the preview of Cortex AI COMPLETE multimodal support, enabling the processing and analysis of images alongside text using powerful vision AI models, all through simple SQL. This feature allows image processing from Snowflake or external stages without complex integrations or external APIs.

Snowflake’s new multimodal capabilities include:

  • Advanced vision models, including Claude 3.5 Sonnet and Pixtral Large

  • Comprehensive visual analysis with image comparison, captioning, classification, entity extraction, and visual question answering

  • Flexible image analysis using intuitive SQL syntax, for single or multiple images

  • Support for common image formats (.jpg, .jpeg, .png, .webp, .gif)

  • Efficient batch image processing integrated with existing data workflows through table-based approaches

For more information, see Cortex COMPLETE Multimodal and COMPLETE (SNOWFLAKE.CORTEX) (multimodal).

Language: English