A financial analyst is concerned about the rising costs of their Document AI pipeline, which uses 'invoice_model!PREDlCT' to extract data from daily financial reports. They observe that their assigned 'LARGE virtual warehouse is running continuously, even during periods of low document ingestion, contributing significantly to their bill. They want to investigate how to reduce costs effectively for their existing Document AI setup.

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

A Gen AI Specialist is leveraging Snowflake Document AI to extract specific entities and table data from a large and varied collection of documents. They are aware of potential limitations and want to understand the expected outcomes when processing different types of files. Considering a scenario where a Document AI model build is used with the '!PREDICT' method, which of the following statements accurately describe the expected behavior or potential issues based on Document AI's conditions and limitations?

• A. Processing a legal contract document that is 130 pages long will likely result in a '_processingErrors' message indicating that the document has too many pages.
• B. If a question for an entity, like 'total_invoice_amount', does not find a corresponding value in a document, the JSON output for will contain a 'value' key with a 'null' string and a 'score' key indicating the model's confidence in the absence of the answer.
• C. In a table extraction task, if a specific cell (e.g., 'tablellitem') is empty, the resulting JSON will omit the 'value' key for that cell, but will still provide a 'score' indicating the model's confidence that the cell is empty.
• D. A document written entirely in Ukrainian will be processed by Document AI, and the extracted information will be of satisfactory quality due to extensive multilingual support.
• E. If the extracted answer to a question for a single entity (e.g., is very long, it will be automatically truncated to a maximum of 2048 tokens.

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 function can be directly integrated into a dynamic table's 'SELECT statement to provide continuous, automated embedding updates for new data.
• B. 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.
• C. 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.
• D. If the function is not natively available in the account's primary Snowflake region, cross-region inference cannot be enabled, thus preventing its use.
• 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.

An ML engineer has developed a custom PyCaret classification model and wants to deploy it to Snowpark Container Services (SPCS) for inference using the Snowflake Model Registry. The model requires specific versions of pycaret' , 'scipy', and 'joblib'. The engineer also wants to make the service accessible via an HTTP endpoint. Which of the following Model Registry and service creation steps are 'most appropriate' for the ML engineer? (Select all that apply.)

• A.
  
• B. Opt for warehouse deployment instead of SPCS, as PyCaret is not natively supported by Snowflake and managing its dependencies in SPCS would be overly complex compared to a warehouse.
• C.
  
• D.
  
• E.