A Gen AI developer is implementing a Document AI solution to extract key fields from thousands of diverse PDF reports, which vary significantly in length and complexity. They use the '!PREDICT method with 'GET_PRESIGNED_URL' to process documents from an external stage. After initial testing, they observe two distinct types of errors in the query results:

for other, lengthy PDF files. Which two of the following actions should the developer take to resolve these issues?

• A. Redesign the input documents to ensure they do not exceed 125 pages per file, or preprocess by splitting overly long documents into multiple smaller files.
• B. Increase the virtual warehouse size to a Large or X-Large to speed up processing and prevent URL expiration.
• C. Implement a mechanism to process documents in smaller batches or extend the expiration time for the presigned URLs to ensure timely access by Document
• D. Grant the
  
• E. Reconfigure the external stage to use

Explanation: Only visible for ValidVCE members. You can sign-up / login (it's free).

A Gen AI specialist is tasked with creating a Snowflake Cortex Search Service to power a Retrieval Augmented Generation (RAG) application for customer support transcripts. The goal is to allow semantic search over the 'transcript_text' column, filter results by 'region' and , and leverage a multilingual embedding model for high-quality results. The service should be created in the 'cortex_search_db.serviceS schema and use as the warehouse. Which of the following SQL commands correctly creates such a Cortex Search Service, assuming 'support_transcripts' is the source table and change tracking is enabled?

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

Explanation: Only visible for ValidVCE members. You can sign-up / login (it's free).

A development team is implementing a suite of generative AI applications on Snowflake, utilizing both SQL functions and the Cortex REST API. They prioritize content safety and plan to integrate Cortex Guard wherever possible. Considering the various interfaces for interacting with Snowflake Cortex LLMs, which of the following interfaces and functions support the direct use of Cortex Guard via the guardrails' argument or equivalent configuration?

• A. The 'SNOWFLAKE.CORTEX.CLASSIFY_TEXT SQL function for text classification tasks.
• B. The Snowflake Cortex LLM REST API when invoking the '/api/v2/cortex/inference:complete' endpoint.
• C. The 'SNOWFLAKE.CORTEX.COMPLETE SQL function for generative AI tasks.
• D. The 'Cortex Playground' (Public Preview) when testing prompts and model settings.
• E. The 'SNOWFLAKCORTEX.TRY_COMPLETE SQL function, which is the error-tolerant version of 'COMPLETE.

Explanation: Only visible for ValidVCE members. You can sign-up / login (it's free).

A data analytics team aims to enhance their understanding of customer feedback stored in a Snowflake table called CUSTOMER_FEEDBACK. This table has a REVIEW_TEXT column containing raw customer comments and a CUSTOMER_SEGMENT column. The team wants to classify each review into predefined categories and then generate a concise summary of all reviews for each customer segment. Which of the following Snowflake Cortex AI functions and approaches should they use?

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

Explanation: Only visible for ValidVCE members. You can sign-up / login (it's free).

A security architect is configuring access controls for a new custom role, 'document_processor_role' , which will manage Document AI operations within a designated database 'doc_processing_db' and schema 'doc_workflow_schema'. The goal is to grant only the minimum essential database-level role required to begin working with Document AI features.

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

Explanation: Only visible for ValidVCE members. You can sign-up / login (it's free).