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

A data engineer has successfully experimented with a prompt and various model settings in the Snowflake Cortex Playground for a text classification task using the mistral-large2 model and Cortex Guard. They now want to operationalize this solution within their Snowflake environment. Which of the following statements correctly describe capabilities or considerations when moving from the Cortex Playground to a production pipeline?

• A. If the mistral-large2 model is not natively available in the target production region, cross-region inference must be enabled by setting the CORTEX_ENABLED_CROSS REGION parameter.
• B. To filter unsafe LLM responses in production, the Cortex Guard option, which is built with Meta's Llama Guard 3, must be explicitly enabled in the COMPLETE function's options argument.
• C. The Playground allows exporting the exact SQL query with all defined model settings, including temperature and Cortex Guard enablement, for direct use in a Snowflake worksheet or task.
• D. For continuous processing of new data, the exported SQL query can be automated using
• E. The exported SQL query, when used with dynamic tables, supports incremental refresh for efficient processing of new data without recomputing the entire table.

A business analyst is using a Cortex Analyst-powered conversational application to query structured data in Snowflake. They initially ask, 'What was the total profit from California last quarter?' and then follow up with, 'What about New York?' The application successfully provides accurate answers to both questions. Which of the following statements explain how Cortex Analyst supports this multi-turn conversational experience and maintains accuracy? (Select all that apply)

• A. To handle follow-up questions, Cortex Analyst leverages an internal LLM summarization agent (e.g., Llama 3.1 70B) to reframe the current-turn question by retrieving context from the conversation history, rather than simply passing the entire history.
• B. For multi-turn conversations, Cortex Analyst primarily relies on semantic search over sample values defined in the semantic model to infer context and generate SQL, making explicit conversation history management unnecessary.
• C. Cortex Analyst stores the full, verbatim history of all previous user prompts and LLM responses, which are then passed to every subsequent LLM call to ensure complete context retention without any summarization.
• D. The accuracy of the SQL queries generated by Cortex Analyst for follow-up questions is significantly enhanced by its integration with a Verified Query Repository (VQR), which stores pre-verified natural language questions and their corresponding SQL queries.
• E. The semantic model YAML file, which defines logical tables, dimensions, and measures, is crucial for Cortex Analyst to bridge the gap between business terminology and underlying technical schema, thereby improving text-to-SQL conversion accuracy for both initial and follow-up queries.

A Data Engineer is responsible for deploying machine learning models using Snowpark Container Services. They need to ensure that a specific role, model_deployer_role, has the appropriate permissions to create a Snowpark Container Service that uses an image from an existing image repository named my_inferenc_ images. Which of the following SQL commands grant the necessary privileges 'on the image repository' for this purpose?

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

A machine learning team is leveraging the Snowflake Model Registry to manage diverse models, including a custom Python utility for data preprocessing that they wish to make available as a model method. Which of the following statements accurately describe capabilities or considerations when logging models and their associated artifacts and methods in the Model Registry?

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

A data engineer is developing an AI-infused data pipeline in Snowflake Notebooks to analyze Federal Reserve Meeting Minutes and official Statements, which are initially in PDF format. The goal is to determine the FED's stance on interest rates (hawkish, dovish, or neutral) and the reasoning for each ingested PDF using an LLM. The pipeline needs to automate data ingestion, text extraction, LLM inference, and store the results in a Snowflake table. Which sequence of operations and Snowflake features is most appropriate for building this pipeline within Snowflake?

• A. Scrape data from an external website directly into a Snowflake table using an 'EXTERNAL FUNCTION'. Then, apply 'SNOWFLAKE.CORTEX.EXTRACT ANSWER with a question like 'What is the FED's stance?' and 'SNOWFLAKE.CORTEX.SUMMARIZE' for reasoning to enrich the table. Automate this using 'STREAMS' and 'TASKS.
• B. Ingest PDF documents into a directory table. Use 'Document AI' C!PREDICT') to extract specific entities and tables from the PDFs into structured JSON. Then, create a 'STREAM' on the stage and a 'TASK' to continuously process new documents, extracting information and potentially performing additional sentiment analysis with another LLM.
• C. Scrape PDF data from an external website, load unstructured PDF files to an internal stage, then use a 'UDE to parse raw text from PDFs and a separate UDF' ('GENERATE_PROMPT) to encapsulate a custom prompt. Finally, use a 'TASK' to automate the process, calling Snowflake's function with the custom prompt at the point of ingestion to generate the sentiment signal and reasoning.
• D. Directly ingest PDF documents into a 'VARIANT column in a Snowflake table. Then, use the SQL function in 'OCR mode to extract text and layout. The extracted text is then passed to 'SNOWFLAKE.CORTEX.CLASSIFY TEXT to determine the sentiment, and the results are stored in a new table.
• E. Load unstructured PDF files into an internal stage. Use a stored procedure to download new PDFs from the FOMC website. Leverage Snowpark Container Services to deploy a fine-tuned open-source LLM (e.g., Llama 2) for text extraction and sentiment analysis, and orchestrate the pipeline with ' Dynamic TableS for continuous updates.