GES-C01最も有効な質問と解答で勉強

A Data Scientist has a pre-trained PyCaret model and wants to log it into the Snowflake Model Registry for inference. The model requires specific versions of and 'scipy' , and a configuration file 'my_config.json' needs to be packaged with the model for use during inference. Assuming 'sp_session' is an active Snowpark Session, is an instance of 'PyCaretModel' , and 'train_features' is a Pandas DataFrame for which of the following code snippets correctly logs this custom PyCaret model into the Snowflake Model Registry?

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

A global enterprise has Snowflake accounts in various regions, including a US East (Ohio) account where a critical application is deployed. They need to use AI_COMPLETE with the claude-3-5-sonnet model for real-time customer support, but this model is not natively available in US East (Ohio) for direct AI_COMPLETE usage. The Snowflake administrator considers enabling cross-region inference. Which statements accurately reflect the considerations and characteristics of cross-region inference in Snowflake Cortex?

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

A data scientist has fine-tuned a Hugging Face sentence transformer model for semantic search and intends to deploy it to Snowpark Container Services (SPCS) via the Snowflake Model Registry. The model requires GPU acceleration and specific Python packages ('sentence-transformerS, 'torch', 'transformers'). A GPU compute pool named 'my_gpu_pool' is available. Which of the following code snippets correctly logs the model and deploys it as a service to SPCS, ensuring it utilizes the GPU compute pool and has the necessary Python dependencies for the Hugging Face model and PyTorch?

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

A company is planning to process a large volume of legal documents to generate summaries using SNOWFLAKE. CORTEX. SUMMARIZE. Given the scale, they are acutely focused on managing costs and optimizing performance. Which of the following statements are true regarding the cost and performance characteristics of using SNOWFLAKE. CORTEX. SUMMARIZE? (Select all that apply)

• A. The SUWARIZE function is billed primarily based on the number of output tokens generated in the response, not input tokens.
• B. The fixed billing rate for the SUMMARIZE function is 0.10 Credits per one million Tokens processed.
• C. For SUWARIZE, Snowflake adds an internal prompt to the user's input text, which increases the total input token count for billing purposes beyond the raw text length.
• D. The context window for the SWIMARIZE function is 4,096 tokens, ensuring efficiency for short documents only.
• E. Snowflake recommends using a larger warehouse (e.g., L or XL) for SUMMARIZE function calls to significantly improve processing performance for high-volume tasks.

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.