A data engineering team needs to establish an automated pipeline in Snowflake to continuously extract 'contract_id' and effective_date' from new PDF contract documents uploaded to an internal stage named They have a pre-trained Document AI model named 'contract_processor'. Which of the following sets of SQL commands correctly configures the necessary Snowflake objects for this automated processing pipeline, including handling file access and initial data loading?

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

A company is building a chatbot for internal support, powered by Snowflake Cortex LLMs. The primary goals are to provide answers that are accurate, grounded in proprietary documentation, and to minimize factual 'hallucinations'. They are considering various strategies to achieve this. Which of the following statements correctly describe effective methods or tools within Snowflake for addressing these concerns?

• A. For tasks requiring LLMs to generate SQL queries from natural language, using the can improve accuracy by Cortex Analyst Verified Query Repository (VQR) leveraging pre-verified SQL queries for similar questions.
• B. Enabling Cortex Guard with guardrails: true directly addresses model hallucinations by ensuring responses are always factually correct and aligned with the provided context.
• C. AI Observability can be leveraged to systematically evaluate applications, measuring metrics like 'factual correctnesS and 'groundedness' to detect and mitigate hallucinations, especially in summarization.
• D. Deploying a custom fine-tuned model using SNOWFLAKE. CORTEX. FINETUNE on proprietary documentation is the most effective approach to ensure factual accuracy for any LLM task.
• E. Using Cortex Search as a Retrieval Augmented Generation (RAG) engine can enhance LLM responses by providing relevant context from proprietary documentation, thereby reducing hallucinations.

A data platform architect is integrating 'SNOWFLAKE.CORTEX.EMBED TEXT 768' into a complex data pipeline for a new search application. The pipeline involves extracting text from various sources, generating embeddings, storing them in Snowflake, and performing semantic searches. Which of the following statements accurately describes a compatibility aspect or limitation when working with 'EMBED TEXT 768' and the resulting 'VECTOR' data type within Snowflake?

• A. The 'VECTOR' data type, which stores the output of is fully compatible with all Snowflake features, including being used as a primary key in hybrid tables for fast lookups.
• B. To support diverse embedding dimensions from different models, the 'VECTOR data type can be stored efficiently within a 'VARIANT column, which automatically handles schema variations.
• C. If the function is not natively available in the account's primary Snowflake region, cross-region inference cannot be enabled, thus preventing its use.
• D. The function can be directly integrated into a dynamic table's 'SELECT statement to provide continuous, automated embedding updates for new data.
• E. When is invoked within a Snowpark Python User-Defined Function (UDF) on Snowflake data, the data remains within Snowflake's network boundary during the embedding generation process.

A security audit is being conducted for a financial institution using Snowflake Cortex. Which of the following statements accurately describe Snowflake's data safety and security guarantees concerning whether customer data, metadata, or prompts leave Snowflake's governance boundary to a third-party when using Cortex features, under the default Snowflake configurations for Cortex functions unless otherwise specified?

• A. For Cortex Analyst, if the legacy ENABLE_CORTEX_ANALYST_MODEL_AZURE_OPENAI account parameter is set to TRUE, customer metadata and prompts are transmitted to Azure OpenAI, but the underlying customer data is not.
• B. When CORTEX_ENABLED_CROSS_REGION is active for Cortex LLM functions, user inputs and outputs are always cached in the intermediate region to reduce latency, thereby leaving the primary region's immediate governance.
• C. When using SNOWFLAKE .CORTEX. COMPLETE with Snowflake-hosted LLMs like all prompts and generated responses remain within Snowflake's mistral-large2, governance boundary by default.
• D. Customer Data and inputs to Snowflake AI Features are never used by Snowflake to train or fine-tune models made available to other customers.
• E. Models brought into Snowflake via Snowpark Container Services (BYOM) are treated as Snowflake's proprietary models, meaning Snowflake assumes responsibility for their data handling policies.

A Snowflake Gen AI Specialist is defining a semantic model for Cortex Analyst to improve text-to-SQL accuracy. They are adding entries to the verified _ queries section of their YAML file. Consider the following semantic model snippet and a proposed verified_query entry. Which of the following statements correctly identifies an issue or a best practice not followed in the sql field of the proposed verified_query entry, based on Cortex Analyst VQR guidelines? Semantic Model Snippet:

Proposed verified _ query entry:

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