AI_PARSE_DOCUMENT

Jul 27, 2026: AI_EXTRACT and AI_PARSE_DOCUMENT now available in GCP Middle East Central2 (Dammam)

AI_EXTRACT and AI_PARSE_DOCUMENT are now available in the Google Cloud Platform Middle East Central2 (Dammam) region, expanding regional support for customers with in-region requirements for document processing workloads.

This addition enables customers in the Dammam region to use these Cortex AI Functions for document extraction and parsing capabilities without requiring cross-region inference.

Read from the provider's text; the quote is the provider's exact lines.

May 04, 2026: AI_PARSE_DOCUMENT OCR quality improvements

The Snowflake Cortex AI_PARSE_DOCUMENT function has launched significant quality improvements for OCR mode, building on the strong OCR performance already available in AI_PARSE_DOCUMENT and delivering even higher accuracy and faster processing for enterprise-scale document workflows that require efficient, high-quality text extraction.

Read from the provider's text; the quote is the provider's exact lines.

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

Read from the provider's text; the quote is the provider's exact lines.

Apr 30, 2026: AI_PARSE_DOCUMENT increased page limit to 2,000 pages

The Snowflake Cortex AI_PARSE_DOCUMENT function now supports processing documents of up to 2,000 pages in both LAYOUT and OCR modes, enabling organizations to efficiently handle large, multi-page documents such as healthcare records, insurance claims, regulatory filings, and technical manuals in a single request with reduced pre-processing and orchestration.

Key improvements include:

• Expanded document size support: Process documents up to 2,000 pages, a significant increase from previous limits, reducing the need to split large files before processing.
• Improved workflow efficiency: Minimize pre-processing steps by handling large documents in a single call, simplifying pipelines and reducing operational overhead.
• Consistent performance across modes: Both LAYOUT and OCR modes now support large-scale documents, enabling flexibility across a wider range of use cases.

Read from the provider's text; the quote is the provider's exact lines.

Apr 02, 2026: AI_PARSE_DOCUMENT now available in AWS Europe West 2 (London)

AI_PARSE_DOCUMENT is now available in the AWS Europe West 2 (London) region, expanding regional support for customers with in-region requirements for document processing workloads.

This addition enables customers in the London region to use AI_PARSE_DOCUMENT for text extraction, layout analysis, and document parsing without requiring cross-region inference.

Read from the provider's text; the quote is the provider's exact lines.

Jan 26, 2026: Extract images from documents using AI_PARSE_DOCUMENT (Preview)

The AI_PARSE_DOCUMENT AI Function can now extract images embedded in PDF and Word documents, alongside text, data, and layout elements. Extracted images can be written to stages or passed directly to other Cortex AI Functions for further analysis.

Read from the provider's text; the quote is the provider's exact lines.