Source
Extract information with Document AI
Feature — Generally Available Available to accounts in AWS, Microsoft Azure, and Google Cloud commercial regions, with some exceptions.
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.
SnowConvert AI - Contact Us
SnowConvert AI - Contact Us SnowConvert AI is now a part of Snowflake.
AI_AGG
Reduces a column of text data using a natural language instruction. For example, AI_AGG(reviews, 'Describe the most common complaints mentioned in the book reviews') will return a summary of user feedback.
AI_SUMMARIZE_AGG
Summarizes a column of text data. For example, AI_SUMMARIZE_AGG(churn_reason) will return a summary of the churn_reason column. Unlike AI_COMPLETE and SUMMARIZE (SNOWFLAKE.CORTEX), this function supports datasets larger than the maximum…
AI_SIMILARITY
Computes a similarity score based on the vector cosine similarity value of the inputs’ embedding vectors. Currently supports both text and image similarity computation.
Question optimization for extracting information with Document AI
When you work with Document AI, use natural language to ask the model questions about your documents. To ask a question that returns an accurate answer, follow these guidelines: Use plain English. For each question, know what answers you…
SnowConvert AI - Considerations
SnowConvert AI - Considerations "myst_slugs": { "snowconvert - ai - - - considerations": [ 1, "snowconvert - ai - considerations", "SnowConvert AI - Considerations" "wordcount": { "words":…
AI_SENTIMENT
AI_SENTIMENT is the updated version of ENTITY_SENTIMENT (SNOWFLAKE.CORTEX). For the latest functionality, use AI_SENTIMENT. Returns overall and category sentiment in the given input text.
AI_COMPLETE structured outputs
AI_COMPLETE lets you supply a JSON schema or type literal that completion responses must follow, producing structured output. Structured output reduces the need for post - processing in your AI data pipelines and enables seamless integration…