Snowflake GES-C01 real exam prep : SnowPro® Specialty: Gen AI Certification Exam

A Gen AI Specialist is setting up Snowpark Container Services (SPCS) to host a custom open-source LLM. They need to understand the fundamental nature and constraints of image repositories within Snowflake. Which of the following statements accurately describe image repositories in Snowflake's Snowpark Container Services?

• A. Dropping individual images from a repository is supported, allowing for granular management of stored container images.
• B. The maximum compressed layer size for an image registry is consistent across all cloud providers and regions, typically 160 GiB.
• C. Image repositories are storage units within an image registry service, and they are used to store OCI-compliant container images.
• D. An image repository in Snowflake is an OCIv2 compliant service used exclusively for storing Docker images, not other OCI-compliant container images.
• E. Image repositories are primarily used for storing pre-trained Snowflake ML models and do not support custom third-party container images.

A security administrator is implementing strict model access controls for Snowflake Cortex LLM functions, including those accessed via the Cortex REST API. By default, the 'SNOWFLAKE.CORTEX USER' database role is granted to the 'PUBLIC' role, allowing all users to call Cortex AI functions. To enforce a more restrictive access policy, the administrator revokes 'SNOWFLAKE.CORTEX USER from 'PUBLIC'. Which of the following actions must the administrator take to ensure specific roles can 'still' make Cortex REST API requests, and what are the implications?

• A. Only the role can make cortex REST API calls after revoking 'SNOWFLAKE.CORTEX_USER from 'PUBLIC', as this role inherently bypasses all other access controls.
• B. The 'SNOWFLAKE.CORTEX USER database role must be granted to the specific account roles, and then these account roles must be granted to users. Additionally, the account parameter can be used to restrict which models are accessible.
• C. The from 'SNOWFLAKCORTEX USER database role is only required for SQL functions, not for the Cortex REST API, so no further action is needed after revoking 'PUBLIC for REST API access.
• D. Access for Cortex REST API is managed independently of database roles; a separate REST API key must be provisioned for each user or application.
• E. The 'SNOWFLAKE.CORTEX USER database role must be granted directly to individual users who need access, as it cannot be granted to other account roles.

A development team is implementing a document retrieval system in Snowflake. They plan to store document embeddings and use VECTOR_L2_DISTANCE to find the most relevant documents for a given query embedding. Considering Snowflake's capabilities, which of the following statements are true regarding the use of vector types and VECTOR_L2_DISTANCE
? (Select all that apply)

• A. To prevent issues with direct vector comparisons, explicitly using
• B. VECTOR
• C. O When defining a table column for 1024-dimensional float embeddings, the SQL type specification
• D. Using the Snowpark Python library, developers can directly invoke
  
• E. Document embeddings, which are typically float arrays, can be stored in a

A financial institution is deploying a sentiment analysis application that uses Snowflake Cortex 'SENTIMENT' and 'COMPLETE' functions, with different LLMs, for processing customer feedback. They are using AI Observability (Public Preview) to compare the cost- efficiency of using 'mistral-7b' versus 'claude-3-5-sonnet' as LLM judges for evaluation metrics, and also tracking the overall cost of their AI Observability usage. Which statements accurately reflect the cost implications and monitoring tools for this scenario?

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

A data team has implemented a Snowflake data pipeline using SQL tasks that process customer call transcripts daily. This pipeline relies heavily on SNOWFLAKE. CORTEX. COMPLETE() (or its updated alias) for various text analysis tasks, such as sentiment analysis and summary generation. Over time, they observe that the pipeline occasionally fails due to LLM-related errors, and the compute costs are higher than anticipated. What actions should the team take to improve the robustness and cost-efficiency of this data pipeline? (Select all that apply.)

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