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

An enterprise is deploying a new RAG application using Snowflake Cortex Search on a large dataset of customer support tickets. The operations team is concerned about managing compute costs and ensuring efficient index refreshes for the Cortex Search Service, which needs to be updated hourly. Which of the following considerations and configurations are relevant for optimizing cost and performance of the Cortex Search Service in this scenario?

• A. The
• B. CHANGE_TRACKING
• C. For embedding text, selecting a model like
  
• D. For optimal performance and cost efficiency, Snowflake recommends using a dedicated warehouse of size no larger than MEDIUM for each Cortex Search Service.
• E. The primary cost driver for Cortex Search is the number of search queries executed against the service, with the volume of indexed data (GBImonth) having a minimal impact on overall billing.

A data engineer is designing an automated data pipeline in Snowflake to process incoming customer feedback documents. The pipeline needs to perform the following steps: 1. Extract the overall sentiment from the feedback text. 2. Generate a concise summary of each feedback document. 3. Extract key entities (e.g., product, issue, customer name) into a structured JSON format using a powerful LLM, ensuring adherence to a predefined schema and graceful error handling. Which of the following Snowflake Cortex features and best practices should the data engineer leverage to build this robust AI-infused pipeline?

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

A Gen AI engineer is tasked with selecting the most suitable Large Language Model (LLM) from Snowflake Cortex AI for a new customer service chatbot. They need to rapidly prototype and compare different LLMs with varying parameters on a sample dataset before committing to a production deployment. Which of the following statements accurately describe how the Cortex Playground (Public Preview) can assist in this scenario?

• A. It allows connection to a Snowflake table with textual data, processing up to 100 rows, to experiment with prompts directly on actual data.
• B. It allows direct fine-tuning of selected LLMs with custom datasets within the playground interface to improve model performance for specific tasks.
• C. It enables side-by-side comparison of model outputs for different LLMs and model settings, facilitating an informed decision on model selection.
• D. It supports exporting the tested prompts and model configurations as Python code, ready for integration into a Snowpark ML pipeline.
• E. It provides a mechanism to deploy the chosen LLM directly into Snowpark Container Services (SPCS) compute pools from within the playground for immediate production use.

A data engineering team is tasked with improving the accuracy of a Cortex Analyst solution for a large e-commerce product catalog. Users frequently ask natural language questions involving specific product names, brands, and categories. The team observes that Cortex Analyst sometimes struggles to identify and correctly filter by these literal values in the generated SQL. Which of the following configurations or approaches, within the semantic model, can effectively enhance Cortex Analyst's ability to precisely identify and use literal values for filtering, based on Snowflake's best practices?

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

A data engineer is configuring a Document AI pipeline to process scanned PDF invoices stored in an internal stage named 'invoice_docs_stage'. After uploading the PDF files, they execute an extracting query using '!PREDICT. The query consistently returns the error:

Which of the following is the most likely cause of this error?

• A. The documents contain non-English text, which is not fully supported by Document AI for optimal results.
• B. The internal stage was not created with 'SNOWFLAKE_SSE' encryption enabled.
• C. The 'GET_PRESIGNED_URL' function used in the '!PREDICT query has an expired URL.
• D. The Document AI model build is attempting to process more than 1000 documents in a single query.
• E. The PDF documents exceed the maximum allowed file size of 50 MB.