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

A development team is constructing a Gen AI application using Snowflake Cortex LLM functions, particularly for conversational and text generation tasks. They are concerned about potential high costs due to token consumption. Which of the following strategies would most effectively help minimize token usage and optimize costs when working with these Cortex LLM functions?

• A. To encourage more succinct LLM responses and reduce completion_tokens, configure the temperature option to a higher value (e.g., 0.7) in COMPLETE function calls.
• B. Utilize the COUNT_TOKENS (SNOWFLAKE .CORTEX) helper function to pre-validate the prompt length against the model's context window, thereby preventing truncation errors and subsequent re-runs.
• C. When employing AI_COMPLETE for structured output tasks, providing concise and highly descriptive explanations for each field within the JSON schema will reduce the input tokens required for the LLM to understand and adhere to the schema accurately.
• D. In multi-turn conversations within Cortex Analyst, integrate a dedicated LLM summarization agent to rephrase follow-up questions, which reduces the total conversational history passed as context to the main LLM.
• E. For multi-turn conversational experiences using SNOWFLAKE .CORTEX.COMPLETE, only send the most recent user prompt in each API call, as the model automatically retains previous context.

Explanation: Only visible for TorrentVCE members. You can sign-up / login (it's free).

An AI engineer is building an automated pipeline in Snowflake that processes various types of textual data using Cortex AI functions. To ensure the pipeline's stability and avoid failures due to exceeding LLM context windows, they integrate SNOWFLAKE.CORTEX.COUNT_TOKENS and TRY_COMPLETE
. Consider the following code snippets and statements about context window management in Snowflake Cortex.

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

Explanation: Only visible for TorrentVCE members. You can sign-up / login (it's free).

A data engineering team is tasked with creating vector embeddings for a collection of diverse, multilingual research papers for a semantic search application. They need to use 'SNOWFLAKE.CORTEX.EMBED TEXT 1024' and are considering two models: 'snowflake-arctic-embed-l-v2.0' and 'voyage-multilingual-2'. They also need to ensure the resulting embeddings are stored correctly and understand potential text truncation. Which of the following statements correctly describes the application of the 'EMBED TEXT 1024' function for these models and the characteristics of the generated embeddings?

• A. The 'snowflake-arctic-embed-I-v2.0' model has a larger context window than 'voyage-multilingual-2 , making it more suitable for longer research papers without truncation.
• B. Using either 'snowflake-arctic-embed-l-v2.0' or 'voyage-multilingual-2' with will result in a 'VECTOR(FLOAT, 1024)' data type, which is compatible with 'VARIANT columns.
• C. The function call
  
• D. The query
  
• E. Both 'snowflake-arctic-embed-l-v2.0' and 'nv-embed-qa-4' are multilingual models with a 1024-dimension output, making them interchangeable for this use case.

Explanation: Only visible for TorrentVCE members. You can sign-up / login (it's free).

• A. Users with 'ds_team_role' will still be able to successfully call
  
• B. Enabling Cortex Guard for 'AI_COMPLETE through the 'guardrails' option automatically bypasses the 'CORTEX_MODELS_ALLOWLIST to ensure all LLMs can be used for content safety filtering.
• C. If a user attempts to call an LLM not explicitly listed in the via the Cortex LLM Playground, Snowflake will automatically fall back to the 'snowflake-arctic' model for that request.
• D. The 'ACCOUNTADMIN' must execute the SQL command:
  
• E. The parameter provides granular control at the database or schema level, allowing administrators to define different sets of approved models for different data contexts.

Explanation: Only visible for TorrentVCE members. You can sign-up / login (it's free).

A data architect is designing a workflow to programmatically extract highly structured data from various text inputs using Snowflake Cortex AI's AI_COPIPLETE function through its REST API. They require the output to strictly adhere to a complex JSON schema for downstream processing and need to manage associated costs. Which of the following statements accurately describe aspects of this approach?

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

Explanation: Only visible for TorrentVCE members. You can sign-up / login (it's free).