SnowPro Advanced Data Scientist

By Snowflake · Question Mode

QuestionQ67

VerifiedUse GenAI and LLM capabilities in Snowflake

A Data Scientist must build a chat-based Retrieval Augmented Generation (RAG) application using company manuals.

Which task-specific models or general functions should be used when Snowflake Cortex Search is not used?

Choose three
Explanation

A RAG workflow embeds the manual content and user query, retrieves relevant manual chunks by comparing their vectors, and supplies those chunks to a language model to generate the response. SNOWFLAKE.CORTEX.EMBED_TEXT_768() creates the embeddings, VECTOR_COSINE_SIMILARITY() identifies semantically similar vectors, and SNOWFLAKE.CORTEX.COMPLETE() generates the chat completion from the retrieved context.

Learn more

Community Discussion

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