Snowflake SnowPro® Specialty: Gen AI Certification 問題集 : GES-C01

A data application developer is building a Streamlit chat application within Snowflake. This application uses a RAG pattern to answer user questions about a knowledge base, leveraging a Cortex Search Service for retrieval and an LLM for generating responses. The developer wants to ensure responses are relevant, concise, and structured. Which of the following practices are crucial when integrating Cortex Search with Snowflake Cortex LLM functions like AI_COMPLETE for this RAG chatbot?

• A. To maintain conversational context in a multi-turn chat, the developer should pass all previous user prompts and model responses in the
  
• B. The retrieved context from Cortex Search should be directly concatenated with the user's prompt as input to the
• C. For performance and cost optimization, it is always recommended to query Cortex Search and the LLM function within a single
• D. The
  
• E. Using the
  

A new ML Engineer, 'data_scientist_role' , has been assigned to a project involving custom machine learning models in Snowflake. They need to gain the necessary permissions to perform the following actions related to Snowflake Model Registry and Snowpark Container Services: 1. Log a custom model into a specified schem a. 2. Deploy that model to an existing Snowpark Container Service compute pool. 3. Call the deployed model for inference using SQL. Which of the following SQL commands grant the 'minimal' required privileges to the for these actions, assuming the compute pool and image repository already exist and are appropriately configured?

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

A developer is building an interactive chat application in Snowflake leveraging the COMPLETE (SNOWFLAKE. CORTEX) LLM function to power multi-turn conversations. To ensure the LLM maintains conversational context and generates coherent responses based on prior interactions, which of the following methods correctly implements the passing of conversation history to the COMPLETE function?

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

An operations team at a company is implementing a robust governance framework to monitor and optimize the costs associated with their Snowflake Cortex LLM function usage. They need to identify which functions are driving the highest token consumption and overall credit usage to pinpoint areas for cost reduction. Which of the following monitoring tools or methods are appropriate for gaining these insights into Cortex LLM function costs and token consumption?

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

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.