Snowflake SnowPro® Specialty: Gen AI Certification Sample Questions:

1. A developer is building a client application that interacts with a Snowflake Cortex Agent using its REST API. They are implementing multi- turn conversation support. Which of the following is the most critical aspect for maintaining conversational context over multiple API calls?

A) The REST API automatically identifies and reuses context from previous requests based on the Authorization token, eliminating the need to pass full history.
B) The client application must include all prior user prompts and assistant/analyst responses in a messages array in each new API request.
C) Only the last user prompt and the immediately preceding agent response should be sent to conserve token usage.
D) The agent internally summarizes long conversations, and the client receives only a condensed summary_token to pass for subsequent turns.
E) A specific session_id parameter, generated at the start of the conversation, must be sent with each request to link turns.

2. A data engineer is tasked with defining a semantic model for Cortex Analyst to enable natural language queries over sales dat a. They are creating a YAML file to describe the logical structure. Which of the following statements correctly describe the configuration of this semantic model? (Select all that apply)

A) Dimensions such as 'product_category' can include a configuration, which can specify an optional 'literal_column' that, if omitted, defaults to the search index column.
B) A 'metric' like 'total_revenue' can be defined using an 'expr' that references other logical columns, such as 'sum(profity from a logical 'sales_data' table, within the semantic model.
C) To ensure high accuracy for specific common questions, 'verified_querieS can be included, where the 'sqr field must reference the underlying physical table and column names (ee.g., not the logical names defined in the semantic model.
D) The 'VARIANT data type is a supported data type for columns defined as 'dimensions' or 'facts' within the semantic model, allowing flexible storage of complex attributes.
E) The 'tables' section must define logical tables that directly map to Snowflake physical tables or views, with 'base_table' specifying the fully qualified name (database, schema, table).

3. A data engineer is tasked with establishing a robust MLOps pipeline using the Snowflake Model Registry. They have trained a scikit-learn model and need to log it. Which of the following statements correctly describes a 'required' step or privilege for successfully logging a model using the 'Registry.log_model' method?

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

4. An ML engineer is working on a Snowflake project that requires storing and comparing high-dimensional feature vectors extracted from customer interaction logs. They need to ensure the vector data type is correctly defined and then perform an inner product calculation.
Which of the following statements about defining and using the
VECTOR
data type and
VECTOR_INNER_PRODUCT
function in Snowflake SQL are correct? (Select all that apply)

A) The
B) The

C) To store a vector with 512 floating-point dimensions in a table, the correct SQL syntax for adding a column would be:

D) When calling

E) Direct comparison operators like

5. A data scientist is tasked with improving the accuracy of an LLM-powered chatbot that answers user questions based on internal company documents stored in Snowflake. They decide to implement a Retrieval Augmented Generation (RAG) architecture using Snowflake Cortex Search. Which of the following statements correctly describe the features and considerations when leveraging Snowflake Cortex Search for this RAG application?

A) Enabling change tracking on the source table for the Cortex Search Service is optional; the service will still refresh automatically even if change tracking is disabled.
B) For optimal search results with Cortex Search, source text should be pre-split into chunks of no more than 512 tokens, even when using models with larger context windows like

C) The

D) Cortex Search automatically handles text chunking and embedding generation for the source data, eliminating the need for manual ETL processes for these steps.
E) To create a Cortex Search Service, one must explicitly specify an embedding model and manually manage its underlying infrastructure, similar to deploying a custom model via Snowpark Container Services.

Solutions: