Databricks Databricks-Generative-AI-Engineer-Associate : Databricks Certified Generative AI Engineer Associate

A Generative AI Engineer is building an LLM to generate article summaries in the form of a type of poem, such as a haiku, given the article content. However, the initial output from the LLM does not match the desired tone or style.
Which approach will NOT improve the LLM's response to achieve the desired response?

• A. Include few-shot examples in the prompt to the LLM
• B. Use a neutralizer to normalize the tone and style of the underlying documents
• C. Provide the LLM with a prompt that explicitly instructs it to generate text in the desired tone and style
• D. Fine-tune the LLM on a dataset of desired tone and style

A Generative Al Engineer is building a RAG application that answers questions about internal documents for the company SnoPen AI.
The source documents may contain a significant amount of irrelevant content, such as advertisements, sports news, or entertainment news, or content about other companies.
Which approach is advisable when building a RAG application to achieve this goal of filtering irrelevant information?

• A. Keep all articles because the RAG application needs to understand non-company content to avoid answering questions about them.
• B. Consolidate all SnoPen AI related documents into a single chunk in the vector database.
• C. Include in the system prompt that any information it sees will be about SnoPenAI, even if no data filtering is performed.
• D. Include in the system prompt that the application is not supposed to answer any questions unrelated to SnoPen Al.

A Generative Al Engineer is deciding between using LSH (Locality Sensitive Hashing) and HNSW (Hierarchical Navigable Small World) for indexing their vector database Their top priority is semantic accuracy Which approach should the Generative Al Engineer use to evaluate these two techniques?

• A. Compare the Bilingual Evaluation Understudy (BLEU) scores of returned results for a representative sample of test inputs
• B. Compare the Recall-Onented-Understudy for Gistmg Evaluation (ROUGE) scores of returned results for a representative sample of test inputs
• C. Compare the cosine similarities of the embeddings of returned results against those of a representative sample of test inputs
• D. Compare the Levenshtein distances of returned results against a representative sample of test inputs

A Generative AI Engineer is implementing a supervisor agent and two specialist agents in Databricks: a Sales Analyst for revenue questions and an HR Analyst for staff questions. Each specialist must retrieve data only from its own governed domain, and the engineer wants to preserve that separation using Databricks-native data access for each agent rather than building custom retrieval logic.
What should the engineer implement?

• A. Create a shared Genie Space over both domains, but use distinct service principals and Unity Catalog grants for each specialist agent's API access.
• B. Create a single Genie Space over both domains and rely on the supervisor agent to route only sales questions to the Sales Analyst and HR questions to the HR Analyst.
• C. Create two separate Genie Spaces for Sales and HR, each scoped to its own governed datasets, and have each specialist agent call the appropriate Space through the API.
• D. Create separate Knowledge Assistants for Sales and HR and have each specialist retrieve from the corresponding assistant.

A Generative Al Engineer would like an LLM to generate formatted JSON from emails. This will require parsing and extracting the following information: order ID, date, and sender email. Here's a sample email:

They will need to write a prompt that will extract the relevant information in JSON format with the highest level of output accuracy.
Which prompt will do that?

• A. You will receive customer emails and need to extract date, sender email, and order ID. Return the extracted information in a human-readable format.
• B. You will receive customer emails and need to extract date, sender email, and order ID. Return the extracted information in JSON format.
  Here's an example: {"date": "April 16, 2024", "sender_email": "[email protected]", "order_id":
  "RE987D"}
• C. You will receive customer emails and need to extract date, sender email, and order ID. Return the extracted information in JSON format.
• D. You will receive customer emails and need to extract date, sender email, and order ID. You should return the date, sender email, and order ID information in JSON format.