A Generative Al Engineer is setting up a Databricks Vector Search that will lookup news articles by topic within 10 days of the date specified An example query might be " Tell me about monster truck news around January 5th 1992 " . They want to do this with the least amount of effort.
How can they set up their Vector Search index to support this use case?

• A. pass the query directly to the vector search index and return the best articles.
• B. Create separate indexes by topic and add a classifier model to appropriately pick the best index.
• C. Split articles by 10 day blocks and return the block closest to the query.
• D. Include metadata columns for article date and topic to support metadata filtering.

A Generative AI Engineer has set up an endpoint with AI Guardrails turned on to block any incoming requests that divulge PII. They also have inference tables enabled for this endpoint. If an end user sends their phone number in their prompt, what will appear in the inference table for that record?

• A. The record will not appear in inference tables because it contains PII.
• B. The full answer that would have been sent without the PII block will appear in inference tables.
• C. The request will appear, but the response column will be blank.
• D. The request will appear, but the response will be the error indicating that the request was blocked due to PII.

A Generative Al Engineer has created a RAG application to look up answers to questions about a series of fantasy novels that are being asked on the author's web forum. The fantasy novel texts are chunked and embedded into a vector store with metadata (page number, chapter number, book title), retrieved with the user' s query, and provided to an LLM for response generation. The Generative AI Engineer used their intuition to pick the chunking strategy and associated configurations but now wants to more methodically choose the best values.
Which TWO strategies should the Generative AI Engineer take to optimize their chunking strategy and parameters? (Choose two.)

• A. Add a classifier for user queries that predicts which book will best contain the answer. Use this to filter retrieval.
• B. Pass known questions and best answers to an LLM and instruct the LLM to provide the best token count. Use a summary statistic (mean, median, etc.) of the best token counts to choose chunk size.
• C. Create an LLM-as-a-judge metric to evaluate how well previous questions are answered by the most appropriate chunk. Optimize the chunking parameters based upon the values of the metric.
• D. Change embedding models and compare performance.
• E. Choose an appropriate evaluation metric (such as recall or NDCG) and experiment with changes in the chunking strategy, such as splitting chunks by paragraphs or chapters.
  Choose the strategy that gives the best performance metric.

A Generative Al Engineer is developing a RAG application and would like to experiment with different embedding models to improve the application performance.
Which strategy for picking an embedding model should they choose?

• A. Pick an embedding model with multilingual support to support potential multilingual user questions
• B. Pick an embedding model trained on related domain knowledge
• C. Pick the most recent and most performant open LLM released at the time
• D. pick the embedding model ranked highest on the Massive Text Embedding Benchmark (MTEB) leaderboard hosted by HuggingFace

A Generative AI Engineer is integrating Mosaic AI Vector Search into a Retrieval-Augmented Generation (RAG) system. The source data, comprising simple text entries, is stored in a Delta table. To simplify the workflow, the engineer plans to use an embedding model served via a Mosaic AI Model Serving endpoint to automatically compute embeddings during data synchronization from the Delta table to the vector search index.
Which method should the engineer use to achieve this integration?

• A. Hybrid embedding computing.
• B. Delta Sync index with managed embeddings.
• C. Direct Vector Access index.
• D. Delta Sync index with self-managed embeddings.