Apr 30, 2026: AI_PARSE_DOCUMENT image extraction (General availability)

High-fidelity image extraction with the Snowflake Cortex AI_PARSE_DOCUMENT function using LAYOUT mode is now generally available, enabling organizations to unlock visual data from documents and build richer, multimodal document processing workflows. By extracting images alongside text and layout, teams can incorporate visual context from documents such as healthcare records, financial reports, and regulatory filings, without additional tooling or pipelines.

Key capabilities include:

  • Multimodal data enrichment: Extract images to complement text data, enabling deeper insights and more context-aware analytics.

  • Enhanced RAG workflows: Combine extracted images and text to improve retrieval-augmented generation (RAG) quality and relevance.

  • Image understanding and classification: Use extracted images with Cortex AI functions to automatically describe, tag, and analyze visual content.

  • Richer knowledge bases: Build document repositories that include both text and images for improved search, reasoning, and downstream AI applications.

  • Streamlined compliance workflows: Extract and analyze visual elements such as charts, signatures, and embedded graphics for audit and regulatory use cases.

For more information, see Parsing documents with AI_PARSE_DOCUMENT.