SnowPro Specialty Gen AI GES-C01

By Snowflake · Question Mode

QuestionQ55

VerifiedSnowflake Gen AI & LLM Functions

Which strategy should be used to reduce latency when using the SNOWFLAKE.CORTEX.COMPLETE function?

Explanation

The Cortex REST API is designed for direct model-inference requests, avoiding the additional SQL query-execution path that is used when invoking the function through SQL or a Snowpark session. Temperature changes output randomness, while response_format constrains the output to a JSON schema; neither is a latency optimization.

Learn more

Community Discussion

No comments yet. Be the first to start the discussion!