Databricks-GenAI-Assoc Practice Test 21 — 15 Questions

Question 1

A data engineer wants to track who accessed a specific table in Unity Catalog. Which tool should they use?

Accepted Answer

Unity Catalog system tables. The System Tables (specifically the access_logs table) in Unity Catalog provide detailed audit logs of all interactions with data objects. By querying these tables using SQL, administrators can monitor data access patterns, identify unauthorized attempts to view sensitive data, and fulfill audit requirements. This centralized logging is a cornerstone of the governance transparency provided by Unity Catalog.

Answer

Databricks cluster logs

Answer

Cloud provider logs

Answer

Workspace activity console

Question 2

When monitoring a RAG application, you notice a high discrepancy between the retrieved context and the generated answer. Which metric would specifically help identify if the model is ignoring the provided context?

Accepted Answer

Faithfulness. Faithfulness measures whether the generated answer is derived exclusively from the retrieved context. If a model generates information not supported by the source text, it is 'hallucinating' or ignoring the context. Monitoring faithfulness is crucial for RAG systems because it directly detects when the model drifts away from the ground truth provided by the internal knowledge base, which is the primary value proposition of a RAG architecture.

Answer

Context Precision

Answer

Retrieval Recall

Answer

Semantic Similarity

Question 3

An organization wants to implement 'Guardrails' on their model outputs. Which deployment strategy best facilitates this?

Accepted Answer

Deploy a wrapper model that processes the output for safety.. The best way to implement guardrails is to build a secondary validation model or use an API-based gatekeeper that intercepts and inspects model outputs before they are returned to the user. Integrating this logic into the inference pipeline within the Databricks environment ensures that all content is screened. This pattern is essential for enterprise deployments where safety, compliance, and preventing hallucinations are top priorities for generative AI applications.

Answer

Hardcode guardrails inside the base model training script.

Answer

Instruct users to manually check the output for safety.

Answer

Disable all logging to prevent guardrails from slowing down.

Question 4

An engineer is troubleshooting a Vector Search index that fails to update. The index relies on a Delta table that is frequently updated. What is the most likely cause for the index failing to reflect new data?

Accepted Answer

The synchronization process was not triggered after the table update.. Vector Search indexes are managed assets that require periodic synchronization with the source Delta table. If the synchronization process is not triggered automatically or via an API call, the index will remain stale. Understanding the lifecycle and sync mechanisms of Vector Search is essential for developers to ensure that RAG systems retrieve the most current information, as static indexes quickly lose relevance in dynamic data environments.

Answer

The Delta table must be converted to a Parquet format.

Answer

The embedding model version changed in the middle of a sync.

Answer

Unity Catalog permissions do not allow read access to the source table.

Question 5

Which workflow best describes the recommended CI/CD process for updating a Databricks Asset Bundle?

Accepted Answer

Update the local YAML, run 'bundle validate', and deploy to the target environment.. A robust CI/CD workflow for Databricks Asset Bundles involves validating the configuration, testing in a development workspace, and then deploying to production via an automated process. By validating the bundle before deployment, you catch syntax errors early. This pipeline-driven approach ensures that all changes are tracked in version control, reviewed through pull requests, and deployed consistently, minimizing the risks associated with manual workspace configuration changes.

Answer

Make changes directly in the production workspace and export the updated YAML.

Answer

Use the Databricks UI to update the Job definition and update the YAML manually later.

Answer

Deploy the bundle to production without validation to speed up the delivery time.

Question 6

What is the primary benefit of using Unity Catalog when designing generative AI applications in Databricks?

Accepted Answer

It provides centralized governance, lineage, and access control for data assets.. Unity Catalog provides a unified governance and security layer, ensuring that data used for training, fine-tuning, or RAG is access-controlled and lineage-tracked. This is crucial for compliance and reproducibility in AI projects. By centralizing permissions and audit logs, teams can securely manage access to sensitive data across their entire generative AI pipeline, which is a fundamental requirement for enterprise AI adoption.

Answer

It automatically generates Python code for model training.

Answer

It converts unstructured text into vectors automatically.

Answer

It eliminates the need for data preprocessing before RAG.

Question 7

A team is preparing a pretraining corpus and must filter out near-duplicate documents before tokenization. The corpus contains 500 million short text records in a Delta table. They want a scalable, deterministic deduplication signal that can be computed per record and compared across the dataset. Which approach best fits this requirement?

Accepted Answer

Compute a MinHash signature per document with a fixed number of hash permutations and compare signatures with a locality-sensitive hashing banding scheme.. Near-duplicate detection at scale needs a compact per-record signature plus a candidate-generation strategy, which MinHash with locality-sensitive hashing banding provides. Exact hashing misses near-duplicates, embedding clustering is costly and nondeterministic, and length-based filtering has no content signal, so none of those satisfy the deterministic, scalable requirement.

Answer

Sort the corpus by document length and drop every record whose length falls within one standard deviation of another record.

Answer

Compute an MD5 hash of each full document and drop rows sharing the same hash value.

Answer

Train a sentence embedding model and cluster documents with k-means, then drop all but one document per cluster.

Question 8

Which of the following describes the 'Gold' layer in a Medallion architecture, and why is it important for GenAI data preparation?

Accepted Answer

It is the final, curated state of data, optimized for consumption by ML models.. The Gold layer represents highly refined, business-level aggregates or prepared datasets ready for consumption. In GenAI, this is where the final, cleaned, and curated training sets (or vector-ready documents) reside. Having a Gold layer ensures that models are trained on validated, high-quality data, which is fundamental to building reliable, production-grade Generative AI applications that meet organizational standards for accuracy and data governance.

Answer

It contains raw, unprocessed data for initial exploration.

Answer

It stores transient data used only for debugging intermediate steps.

Answer

It is a temporary cache for speeding up cluster startup times.

Question 9

A machine learning engineer needs to deploy a custom Mosaic AI Model Serving endpoint that requires access to a private internal database. Which mechanism should be used to securely manage the database credentials?

Accepted Answer

Reference the credentials using the Databricks Secrets API within the model loading script.. Databricks Secrets provide a centralized, secure way to store and reference sensitive information like database credentials. By using the secret scope, the engineer avoids hardcoding sensitive data into the model code or configuration files. This practice is essential for maintaining a secure MLOps lifecycle, as it prevents credential exposure and allows for granular access control via Databricks access control lists (ACLs) on the secret scope itself.

Answer

Hardcode the credentials as environment variables in the model serving endpoint deployment configuration.

Answer

Inject the credentials via a public GitHub repository linked to the Databricks Git folder.

Answer

Store the credentials in a plain-text file on the Unity Catalog volume attached to the serving endpoint.

Question 10

A data engineering team is deploying a RAG application using Mosaic AI Model Serving. They need to monitor the quality of the model's responses in production. Which Databricks feature should they use to capture and analyze inference data, such as requests, responses, and latency metrics?

Accepted Answer

Mosaic AI Inference Tables. Mosaic AI Model Serving provides built-in inference tables to automatically capture request and response logs. By enabling these tables, engineers can export data to a Unity Catalog table for analysis. This is critical for monitoring performance, data drift, and model quality over time. Without this feature, teams lack the visibility required for production-grade LLM governance and continuous improvement cycles within the Databricks ecosystem.

Answer

Databricks SQL Alerts

Answer

Delta Live Tables Audit Logs

Answer

MLflow Experiment Tracking

Question 11

A Generative AI engineer is configuring a Mosaic AI Model Serving endpoint for a production-grade LLM. Which TWO of the following tasks are necessary to ensure effective monitoring and evaluation of the endpoint? (Choose two)

Accepted Answer

Enable Inference Tables on the serving endpoint.. Effective monitoring requires both capturing data and evaluating that data against ground truth or automated metrics. Enabling inference tables provides the necessary raw data, while integrating with evaluation tools allows for systematic scoring of output quality. Together, these steps form the backbone of a robust monitoring strategy, ensuring that production drift is detected and quality is maintained according to business standards.

Answer

Set up an automatic retraining job on the endpoint.

Answer

Increase the GPU count to maximize inference throughput.

Answer

Delete all request logs after 24 hours to save storage.

Question 12

When designing an agentic workflow in Databricks, which TWO practices are essential to ensure the application remains observable and maintainable?

Accepted Answer

Enable MLflow tracing for all agent execution steps.. Observability and maintainability are critical for enterprise-grade AI agents. Using MLflow to log trace data provides visibility into the agent's decision-making process, which is necessary for debugging multi-step reasoning. Simultaneously, implementing robust evaluation suites ensures that agent updates do not introduce regressions in task performance. These two practices form the foundation of a reliable AI operations strategy, enabling teams to confidently deploy and iterate on agentic workflows in production environments.

Answer

Avoid unit testing to speed up the development process.

Answer

Store all agent logic in a single, massive notebook file.

Answer

Disable logging to minimize storage consumption costs.

Question 13

Which THREE conditions must be met for a user to successfully create a new table in a Unity Catalog schema?

Accepted Answer

The user must have the USAGE privilege on the catalog.. Creating a table in Unity Catalog involves a specific permission chain. The user must have USAGE on the catalog, USAGE on the schema, and the CREATE TABLE privilege on the schema. These requirements ensure that governance is maintained at every level of the hierarchy, preventing unauthorized data creation in sensitive or restricted namespaces within the organization's data architecture.

Answer

The user must have the MODIFY privilege on the catalog.

Answer

The user must have the OWNER role for the entire metastore.

Question 14

Which TWO of the following are primary components of the Unity Catalog identity model?

Accepted Answer

Account-level users. The Unity Catalog identity model is unified at the account level, meaning that identities are managed consistently across all workspaces. The core components are Users and Groups. By centralizing these identities in the account console, Databricks ensures that permissions are applied uniformly, regardless of which workspace a user is accessing, which is critical for large-scale enterprise governance and audit compliance.

Answer

Workspace-local users

Answer

Cloud-provider-specific identities

Answer

Data asset aliases

Question 15

An AI engineer is deploying a RAG application using Databricks Model Serving. They need to ensure the endpoint can handle high traffic with low latency and automatically scale based on demand. Which configuration should they use?

Accepted Answer

Configure autoscaling with a minimum of 1 and maximum of 10 replicas, and set appropriate concurrency per replica.. Autoscaling with a minimum and maximum replica count allows the endpoint to scale out during high traffic and scale in during low traffic, optimizing both latency and cost. Setting appropriate concurrency per replica ensures efficient utilization. This configuration provides the elasticity required for high traffic with low latency, while avoiding the pitfalls of fixed provisioning or overly restrictive concurrency limits.

Answer

Enable scale-to-zero and set a maximum concurrency of 1.

Answer

Disable autoscaling and manually provision 20 replicas to handle peak load.

Answer

Use a single large replica with maximum concurrency set to 100.