Source
December 12, 2024 — Document AI release notes
Doubling the length limit of the answers provided by the model. The model can now return answers that are up to 512 tokens long (about 320 words) per question.
AI_CLASSIFY
AI_CLASSIFY is the updated version of CLASSIFY_TEXT (SNOWFLAKE.CORTEX). For the latest functionality, use AI_CLASSIFY. Classifies text or images into categories that you specify.
AI_COMPLETE
Generates a response (completion) from text or an image using a supported language model. You can provide: A text prompt, to generate a response from the model.
Prepare your documents for Document AI
The documents must be 50 MB or less in size. Document pages must have dimensions of 1200 x 1200 mm or less. The images must be between 50 x 50 and 10,000 x 10,000 pixels.
Known limitations to Document AI
The Document AI model returns answers that are up to 512 tokens long (about 320 words) per question. The model for table extraction returns answers that are up to 2048 tokens long. For internal stages, Document AI supports using…
Extract information with Document AI
This topic describes extracting information from documents using Document AI. If you previously published or trained the Document AI model build, you can now extract information from documents by running the extracting query in…
Question optimization for extracting information with Document AI
Question optimization for extracting information with Document AI Feature — Generally Available Available to accounts in AWS, Microsoft Azure, and Google Cloud commercial regions, with some exceptions.
AI_FILTER
Classifies free - form prompt inputs into a boolean. Currently supports both text and image filtering.
AI_EMBED
Creates an embedding vector from text or an image. Embeddings are abstract numerical representations of the features of a piece of text or an image that can be used to determine the degree of similarity between pieces of text or…
Working with Document AI
Document AI consists of model builds, which include the model, the documents uploaded to test the model, and the data values to be extracted. To prepare a Document AI model build: Upload the documents that will be used to test the…