An ML engineering team is preparing to log a custom Python model to the Snowflake Model Registry. This model has several Python package dependencies. The team wants to ensure the model can be deployed optimally, either in a Snowflake warehouse or to Snowpark Container Services (SPCS), depending on future needs. They are particularly concerned with how dependency specification impacts deployment eligibility. Which statements accurately describe how Snowflake handles model dependencies and determines deployment eligibility for custom Python models logged in the Model Registry, particularly when considering both Snowflake warehouse and Snowpark Container Services (SPCS) environments? (Select all that apply.)

• A. If all of a model's 'conda_dependencieS are available in the Snowflake conda channel, the model is automatically deemed eligible to run in a warehouse.
• B. The function will fail if 'WAREHOUSE is specified in 'target_platforms' but the model's size or GPU requirements make it ineligible for warehouse deployment.
• C. Specifying both 'conda_dependencies' and 'pip_requirements' for a model is recommended to cover all possible deployment scenarios, and Snowflake's build process ensures compatibility between them.
• D. For models intended for SPCS, 'pip_requirements' are always preferred over 'conda_dependencies' because SPCS strictly prohibits the use of any conda packages from 'conda-forge'
• E. When 'conda_dependencies' are specified for a model to be deployed to SPCS, these dependencies are by default obtained from 'conda-forge' rather than the Snowflake conda channel.

A development team is building a RAG application in Snowflake Cortex that needs to extract high-fidelity text and layout from a collection of technical documentation PDFs stored in an internal stage to power semantic search and LLM responses. They want to ensure proper context retrieval for complex user queries. Given this scenario, which of the following actions or statements are crucial for effectively leveraging AI_PARSE_DOCUMENT to optimize the RAG pipeline?

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

A developer is refining a Document AI extraction process using the '!PREDICT' method and is meticulously examining the JSON output for invoices, which include 'invoice number', 'invoice items', 'tax amount', and 'vendor name'. They also have a detailed internal table of 'product details' to be extracted. To ensure optimal data quality and accurate interpretation of the extracted information, which of the following best practices or characteristics of Document AI's output should the developer consider?

• A. To maximize accuracy when defining data values, questions should be broadly generic (e.g., 'What is the amount?) to allow the Document AI model to infer the most relevant context, especially for fields like 'tax_amount' where multiple numbers might be present.
• B. When extracting lists of values, such as 'invoice_items', the Document AI model returns them as an array in the JSON output, preserving the original order of items as they appear in the document.
• C. For table extraction, such as the extracted values for each column (e.g., 'tablel litem', 'tablel Igross) are ordered consistently with the rows of the original table, facilitating direct joining of columns.
• D. The 'ocrScore' provided in the '_documentMetadata' object for each document indicates the model's confidence in the content of specific extracted values, rather than the overall quality of the optical character recognition process.
• E. If the 'vendor_name' field cannot be confidently identified in a document, the model will include '"vendor_name": [ { "score": O.X, "value": "NOT FOUND" } l' in the JSON output.

A data engineering team has developed a Python-based generative AI application and instrumented its key functions using the TruLens SDK. Their next step is to register this application with Snowflake AI Observability to initiate evaluation runs and capture application traces within Snowflake.

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

An ML engineer is deploying a custom PyTorch-based image classification model, obtained from Hugging Face, to Snowpark Container Services (SPCS). The deployment requires GPU acceleration on a compute pool named 'my_gpu_pool' and specific Python packages ('torch' , 'transformers' , 'opencv-python'). The scenario dictates that 'opencv-python' is only available via PyPl, while 'torch' and 'transformers' can be sourced from either conda-forge or PyPl. The engineer uses the Snowflake Model Registry to log the model. Which of the following and configurations correctly specify the necessary Python dependencies and GPU utilization for this inference service, adhering to Snowflake's recommendations?

• A.
  
• B.
  
• C.
  
• D.
  
• E.