最新のGES-C01問題集で試験を準備する

A developer is building a prototype Gen AI application using the Snowflake Cortex LLM REST API. During testing, they frequently encounter HTTP 429 'Too Many Requests' errors, particularly when rapidly invoking the 'COMPLETE endpoint. Which of the following statements accurately describes the usage quotas and troubleshooting steps for such rate limit events in the Cortex REST API?

• A. The HTTP 429 response indicates that the daily credit consumption for Snowflake Cortex AISQL usage has exceeded the 10-credit limit for on-demand accounts without a valid payment method, requiring conversion to a paid account.
• B. Rate limits are model-specific, and exceeding either the Tokens Processed per Minute (TPM) or Requests per Minute (RPM) limits will result in an HTTP 429 response code.
• C. Cortex REST API rate limits are primarily based on Requests per Minute (RPM) and do not consider the total Tokens Processed per Minute (TPM).
• D. If the usage is below the RPM limit but still triggers a 429, the developer should review the token usage rate as TPM limits might be exceeded.
• E. To resolve rate limiting, the developer should increase the virtual warehouse size for their API requests, as larger warehouses automatically increase API quotas.

A data science team is developing an internal LLM to classify legal documents. They previously used a general-purpose LLM, but found its performance for their specific legal domain to be inconsistent, leading to high error rates and increased manual review. They decide to fine-tune a model using Snowflake Cortex Fine-tuning to improve accuracy and reduce latency for real-time document classification. Which base model, among those available for fine-tuning via SNOWFLAKE .CORTEX.FINETUNE
, is explicitly noted for its low latency and high throughput processing, making it a strong candidate for this use case, especially for multi-page text classification?

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

A company is developing a Streamlit application leveraging Snowflake Cortex Analyst for natural language querying over sales data.
They want to implement a robust multi-turn conversational experience where users can ask follow-up questions. Which of the following statements accurately describe the design and cost implications of supporting multi-turn conversations in Cortex Analyst? (Select all that apply)

• A. An internal LLM summarization agent is automatically employed by Cortex Analyst before its original workflow to reframe follow-up questions based on conversation history, optimising LLM processing for each agent.
• B. When an LLM judge is used to evaluate the summarization quality for multi-turn conversations, a smaller model like Llama 3.1 8B is generally preferred over Llama 3.1 70B to minimise latency, even if it leads to a slightly higher error rate in rewritten questions.
• C. Developers can manually implement multi-turn conversations in their applications by using the
• D. The cost for Cortex Analyst's multi-turn conversational support is primarily based on the number of messages processed, and the number of tokens within each message does not directly affect the per-message cost.
• E. Cortex Analyst supports multi-turn conversations by simply passing the entire conversation history directly to every LLM call within its agentic workflow, which is the most efficient method for maintaining context.

A data scientist is designing a real-time similarity search feature in Snowflake using product embeddings. They plan to use VECTOR_L2_DISTANCE to find similar products. Which statement correctly identifies a cost or data type characteristic relevant to this implementation?

• A. The
• B. Storing product embeddings generated by
• C. The
• D. The maximum dimension supported for a
• E. Both the

A data science team is using SNOWFLAKE. CORTEX. CLASSIFY_TEXT to categorize product reviews into detailed segments like 'Bug Report - Critical', 'Feature Request - UI/UX', 'General Praise', or 'Query - Billing Issue'. For highly nuanced reviews, they find the initial classifications lack precision, and they are also concerned about the associated compute costs for processing large volumes of dat a. Which strategies should they employ to optimize classification accuracy and manage costs effectively with this function?

• A. To improve accuracy for ambiguous classifications, they should augment the list_of_categories with explicit description and examples for each category, understanding that these additions will increase input token costs for each record processed.
  
• B. If classifying thousands of reviews, they can significantly reduce overall compute costs by setting the temperature option to 0.0 within CLASSIFY_TEXT to ensure deterministic and cheaper inference.
• C. To reduce input token costs for classifications, the input text should be pre-processed to remove common stop words and punctuation, as these characters are counted as billable tokens without contributing to classification accuracy.
• D. CLASSIFY_TEXT labels, descriptions, and examples are counted as input tokens only once per function call, regardless of the number of records processed in a batch, to optimize cost efficiency.
• E. For complex scenarios where the relationship between review text and categories is not straightforward, including a concise task_description (e.g., 'Classify the product review focusing on technical support relevance') in the options argument is recommended to guide the model.