Databricks-Generative-AI-Engineer-Associate 無料問題集「Databricks Certified Generative AI Engineer Associate」

（A）Ingest PDF documents about the monster truck team into a vector store and query it in a RAG architecture.

（B）Instruct the LLM to respond with "RAG", "API", or "TABLE" depending on the query, then use text parsing and conditional statements to resolve the query.

（C）Build a system prompt with all possible event dates and table information in the system prompt. Use a RAG architecture to lookup generic text questions and otherwise leverage the information in the system prompt.

（D）Write a system prompt for the agent listing available tools and bundle it into an agent system that runs a number of calls to solve a query.

（A）Curate upstream data properly that includes manual review before it is fed into the RAG system

（B）Restrict access to the data sources to a limited number of users

（C）Increase the frequency of upstream data updates

（D）Inform the user of the expected RAG behavior

（A）Reach out to the data curators directly after you have started using the trained model to let them know.

（B）Reach out to the data curators directly before you have started using the trained model to let them know.

（C）Only use data explicitly labeled with an open license and ensure the license terms are followed.

（D）Use any available data you personally created which is completely original and you can decide what license to use.

（A）Rather than preprocessing prompts, it's more effective to postprocess the LLM outputs to align the outputs to desired outcomes

（B）It is better not to introduce custom code to preprocess prompts as the LLM has not been trained with examples of the preprocessed prompts

（C）Directly modify the LLM's internal architecture to include preprocessing steps

（D）Write a MLflow PyFunc model that has a separate function to process the prompts

（A）Wrap the LLM's prediction function into a Flask application and serve using Gunicorn

（B）Log the model using MLflow during training, directly register the model to Unity Catalog using the MLflow API, and start a serving endpoint

（C）Save the model along with its dependencies in a local directory, build the Docker image, and run the Docker container

（D）Log the model as a pickle object, upload the object to Unity Catalog Volume, register it to Unity Catalog using MLflow, and start a serving endpoint

（A）TensorFlow

（B）Pandas

（C）LangChain

（D）PySpark