A Gen AI Specialist is responsible for maintaining a Cortex Analyst-powered application. They have defined a semantic model that includes a Verified Query Repository (VQR) to guide user interactions. The application front-end uses the Suggested Questions feature to help users get started. The specialist wants to ensure that a specific set of critical, verified business questions are always displayed to users, regardless of their prior input or the semantic similarity to their current query. Which of the following configuration steps in the semantic model YAML will achieve this requirement?

• A.
  
• B.
  
• C.
  
• D.
  
• E.
  

A data engineering team aims to automatically classify incoming customer support requests into predefined categories ('Technical Issue', 'Billing Inquiry', 'General Question') as part of their Snowflake data ingestion pipeline. The goal is to achieve high classification accuracy while managing LLM inference costs efficiently. Which of the following strategies, when applied within a Snowflake data pipeline using Streams and Tasks, would best contribute to meeting these objectives?

• A. Option A
• B. Option D
• C. Option B
• D. Option C
• E. Option E

A data science team is implementing a large-scale Retrieval Augmented Generation (RAG) application on Snowflake, using 'SNOWFLAKE.CORTEX.EMBED TEXT 1024' to process millions of customer support tickets for semantic search. The goal is to achieve high retrieval quality and manage costs effectively. Which of the following are recommended practices and accurate cost/performance considerations when leveraging 'EMBED TEXT 1024' in this scenario? (Select all that apply)

• A. Models for such as 'snowflake-arctic-embed-l-v2.0' and 'multilingual-e5-large' , are billed at 0.05 Credits per one million input tokens processed.
• B. Even with models like 'snowflake-arctic-embed-l-v2.0-8k' which have a large context window (8192 tokens), splitting customer support tickets into chunks of no more than 512 tokens is recommended for optimal RAG retrieval quality.
• C. The function should be called using 'TRY_COMPLETE instead of directly to handle potential errors gracefully and avoid incurring costs for failed operations.
• D. For 'EMBED_TEXT 1024' , billing is based on both input and output tokens, encouraging brevity in generated embeddings to control costs.
• E. To minimize compute costs, the team should use a Snowpark-optimized warehouse for operations, as it is specifically designed for ML workloads.

A data scientist is leveraging various Snowflake Cortex LLM functions to process extensive text data for an application. To effectively manage their budget, they need a clear understanding of how costs are incurred for each specific function. Which of the following statements accurately describe how costs are calculated for Snowflake Cortex LLM functions, with a particular focus on token usage?

• A. Option A
• B. Option D
• C. Option B
• D. Option C
• E. Option E

A Snowflake administrator is tasked with monitoring the efficiency and cost-effectiveness of their Cortex Analyst deployments. They need to identify if certain semantic models are generating a high volume of failed or expensive queries. Which of the following approaches or statements are crucial for effectively monitoring and identifying issues with Cortex Analyst usage and associated costs?

• A. Option A
• B. Option D
• C. Option B
• D. Option C
• E. Option E