Source
Overview of Snowflake Intelligence
Snowflake Intelligence uses agents, which are AI models that are connected to one or more semantic views, semantic models, Cortex search services, and tools. Agents can answer questions, provide insights, and show visualizations.
AI_COMPLETE (Single image)
Generates a response (completion) for a text prompt using a supported language model. Syntax The function has two required arguments and four optional arguments. The function can be used with either positional or named argument syntax.
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…
AI_COMPLETE (Single string)
Generates a response (completion) for a text prompt using a supported language model. Syntax The function contains two required arguments and four optional arguments. The function can be used with either positional or named argument…
AI_COMPLETE (Prompt object)
Generates a response (completion) for a prompt object. The prompt object references one or more columns containing text or image data. Syntax The function can be used with either positional or named argument syntax.
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 Observability in Snowflake Cortex
Use AI Observability in Snowflake Cortex to evaluate and trace your generative AI applications. With AI Observability, you can make your applications more trustworthy and transparent. Use it to measure the performance of your AI…
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…
Snowflake AI Observability Reference
Groundedness determines if the generated response is supported by and grounded in the retrieved context from the retriever or the search service. Given the generated response and retrieved context, an LLM judge is used to determine…
SnowConvert AI - IBM DB2 - CREATE TABLE
Specifies that the columns of the new table have the same name, data type, and optionally same data, as the resulting from the fullselect. Warning AS RESULT TABLE is partially supported in Snowflake. The Copy options do not apply in…