Snowflake GES-C01 : SnowPro® Specialty: Gen AI Certification Exam

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. To minimize compute costs, the team should use a Snowpark-optimized warehouse for operations, as it is specifically designed for ML workloads.
• B. 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.
• 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. 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.

A financial institution wants to leverage Snowflake Cortex Agents to build an AI application for complex financial analysis, requiring interaction with both their structured transaction databases and unstructured legal documents, while also ensuring intelligent decision- making throughout the process. Which of the following accurately describe the foundational capabilities of Snowflake Cortex Agents?

• A. Allows integration of custom logic and external services through user-defined functions (UDFs) and stored procedures as custom tools.
• B. Cortex Agents enable direct fine-tuning of base LLMs using private customer data, with the resulting models managed within the Snowflake Model Registry.
• C. Agents are designed to orchestrate tasks by planning execution steps, and utilizing tools such as Cortex Analyst for structured data and Cortex Search for unstructured data.
• D. Cortex Agents primarily focus on providing a low-latency, hybrid (vector and keyword) search engine over text data.
• E. They incorporate a 'Reflection' component, allowing the agent to evaluate results after each tool use and determine the next logical steps, including iterating or clarifying.

A data engineer is building an AI data pipeline to automatically extract specific sentiment categories from customer reviews using 'AI_COMPLETE. They want the output to be a structured JSON object containing 'food_quality', 'food_taste', 'wait_time', and 'food cost' with their respective sentiments (e.g., 'positive', 'negative', 'neutral'). The engineer aims for high accuracy and ensures that all these fields are present in the output. Which of the following statements correctly describe the approach to achieve this?

• A. When using OpenAl (GPT) models for structured output, the 'additionalPropertieS field must be set to 'true' in every node of the schema to allow for flexibility in the generated JSON.
• B. To improve accuracy, the JSON schema should include detailed descriptions for each field (e.g., 'food_quality', 'food_taste') to guide the model more precisely in identifying and extracting the sentiments.
• C. For optimal accuracy in structured output, it is always best to explicitly instruct the LLM within the prompt to 'Respond in JSON' and provide a detailed description of the schema, regardless of task complexity.
• D. The 'temperature' option should be set to a high value (e.g., 0.9) in the 'CompleteOptionS to encourage the model to strictly adhere to the specified JSON schema and reduce non-deterministic responses.
• E. The 'response_format' argument in 'AI COMPLETE should specify a JSON schema, and to ensure all fields are present, the 'required' field must be explicitly set for all desired properties in the schema.

A data engineering team is designing a Snowflake data pipeline to automatically enrich a 'customer issues' table with product names extracted from raw text-based 'issue_description' columns. They want to use a Snowflake Cortex function for this extraction and integrate it into a stream and task-based pipeline. Given the 'customer_issues' table with an 'issue_id' and (VARCHAR), which of the following SQL snippets correctly demonstrates the use of a Snowflake Cortex function for this data enrichment within a task, assuming is a stream on the 'customer issues' table?

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

A data analyst is working with a table containing customer feedback text and needs to perform various text analysis tasks efficiently within Snowflake. They want to summarize the reviews, determine their sentiment, and extract specific pieces of information. Which of the following Snowflake Cortex LLM functions, when applied to a text column, will achieve the desired outcome and return the specified output type?

• A. To get a concise overview of each review, the analyst should use
  
• B. To determine the overall sentiment of each review, the analyst should use
  
• C. To extract a specific answer to a question from each review, the analyst can use
  
• D. To categorize reviews into predefined labels, the analyst should use
  
• E. The