Snowflake SnowPro® Specialty: Gen AI Certification Sample Questions:

1. 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)

2. data scientist is designing a Retrieval Augmented Generation (RAG) system in Snowflake for querying a large knowledge base of internal documents. They plan to store document embeddings and use vector similarity for retrieval. Which statement accurately describes the use of vector functions and associated costs in this RAG architecture?

A) The

B) Snowpark Python fully supports all Snowflake vector similarity functions, including

C) Storing vector embeddings, created using functions like

D) When using

E)

3. A data analytics team is building a Retrieval Augmented Generation (RAG) application to provide contextual answers from a vast repository of internal documents stored in Snowflake. They are evaluating different strategies for generating and retrieving text embeddings to optimize the overall RAG pipeline's performance and relevance. Which of the following statements accurately describe performance considerations related to embedding generation and retrieval in this RAG context? (Select all that apply)

A) Option A
B) Option E
C) Option B
D) Option D
E) Option C

4. A data engineering manager needs to audit Cortex LLM function costs to identify specific SQL queries that are unexpectedly high in token consumption for the 'llama3.1-8b' model. They require granular analysis of prompt, completion, and guardrail token usage for these queries. Which of the following Snowflake methods or views would provide the necessary insights?

A) Option A
B) Option E
C) Option B
D) Option D
E) Option C

5. A data scientist is working on a new feature that involves querying a Cortex Search Service and integrating the results into various downstream processes. They are concerned about potential data type compatibility issues and limitations within the Snowflake environment. Which of the following statements accurately describe how to query a Cortex Search Service or the limitations of the 'VECTOR data type and Cortex Search itself? (Select all that apply)

A) Cortex Search Services can be configured as a source for Snowflake dynamic tables, enabling continuous and automated synchronization of the search index with base data.
B) Cortex Search Services can only be queried using the 'SNOWFLAKE.CORTEX.SEARCH_PREVIEW' SQL function and do not offer a programmatic interface for applications.
C) The "VECTOR data type, used to store embeddings generated for Cortex Search, is fully supported as a primary key in Snowflake's hybrid tables to accelerate similarity searches.
D) The 'VECTOR data type, which stores the output of embedding models like those used by Cortex Search, is explicitly not supported in 'VARIANT columns.
E) To retrieve the support ticket most relevant to a query about 'internet issues', filtered to return results only in the 'North America' region, one can use the 'filter' parameter in the 'SEARCH PREVIEW function's JSON argument like so:

Solutions: