最新のGES-C01問題集で試験を準備する

A Gen AI Specialist needs to extract the 'invoice number' and 'total_amount' from a specific invoice PDF, 'invoice_001 .pdf, located in an internal stage named They want to use the default (latest) model build version for a model named 'invoice_processor'. Which SQL query correctly uses the '!PREDICT method to extract the required information, and what key fields would be present in the JSON output for a successful extraction of 'invoice_number' and 'total_amount'?

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

A data engineer is designing a new feature for a Retrieval Augmented Generation (RAG)-based application in Snowflake. They plan to store document embeddings and perform semantic similarity searches to retrieve relevant context for an LLM. Which of the following statements about using the VECTOR data type and related functions in Snowflake are true? (Select all that apply.)

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

A Data Engineer has successfully deployed a Document AI model build named 'expense reports' to extract 'total amount' and approver signature' from digital expense reports. They observe that sometimes the 'approver signature' is not present in a document, or certain table cells are intentionally left blank in other document types processed by Document AI. They also want to automate the ingestion and processing of new expense reports. Regarding the '!PREDICT' method's JSON output when 'approver signature' is missing or a table cell is empty, and the recommended Snowflake features for continuously processing new documents, which statements are true?

• A. If the 'approver_signature' is not found, the JSON output for 'approver_signature' will contain Tvalue" : null, "score" : 0.0}'.
• B. To automate continuous processing, the Data Engineer should create a stream on the internal stage where documents are uploaded, and a task that calls the ' !PREDICT method when new data arrives.
• C. When a table cell is empty, the Document AI model will return a 'score' key but no 'value' key for that cell.
• D. If the model does not find an answer, it returns an empty string for 'value' and a score indicating its confidence that no answer was found.
• E. Dynamic Tables are the primary recommended feature for continuous document processing with Document AI, replacing the need for streams and tasks.

A data science team is deploying a custom real-time inference service for a fine-tuned LLM using Snowpark Container Services (SPCS). They have a Docker image in their Snowflake image repository. They need to define the service using a YAML specification file. Which of the following are ''essential'' components or configurations that must be included in the 'spec.yaml' file for a long- running service that uses this image, custom environment variables, and requires external access?

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

A Snowflake administrator is designing a new role, 'doc_ai_pipeline_creator' , intended to configure and deploy Document AI extraction pipelines. This role needs the ability to ensure that the designated virtual warehouse, 'analytics_wh', can be reliably started and stopped as needed for Document AI tasks. Which of the following SQL statements grants the privilege that directly enables the 'doc ai_pipeline_creator' role to control the operational state of 'analytics_wh'?

• A.
  
• B.
  
• C.
  
• D.
  
• E.