Databricks-GenAI-Assoc Practice Test 13 — 15 Questions

Question 1

You are preparing a large text corpus for fine-tuning a generative AI model. The corpus is stored in a Delta table with columns: doc_id, raw_text, and metadata. You need to create a cleaned dataset that removes personally identifiable information (PII) and normalizes whitespace, while preserving document boundaries for training. Which two actions should you perform to achieve this in a scalable and maintainable way? (Choose two.)

Choose an answer to begin — your selection is scored in the full session.

Accepted Answer

Apply a regular expression to replace all whitespace sequences with a single space in the raw_text column.. ai_mask redacts PII in place, and regexp_replace normalizes whitespace, together achieving the cleaning goals at scale. Both are declarative, repeatable, and preserve document boundaries. Sentiment filtering, manual inspection, and classification are either irrelevant or destructive to the dataset, and they do not address PII removal and whitespace normalization.

Answer

Convert the Delta table to Parquet files and manually inspect each file for PII.

Answer

Use the ai_classify function to label each document as 'clean' or 'dirty' and drop dirty ones.

Answer

Use the ai_analyze_sentiment function to filter out negative documents before training.

Question 2

A team is deploying a GenAI application using Mosaic AI Model Serving. They want to ensure that the endpoint can handle sudden spikes in traffic without dropping requests. Which feature should they configure?

Accepted Answer

Autoscaling. Autoscaling is designed to automatically adjust the serving endpoint's capacity based on incoming traffic. It ensures that the endpoint can handle sudden spikes by adding more resources and scales down when traffic decreases. This maintains availability and performance without manual intervention, making it the correct choice for handling variable loads.

Answer

Request batching

Answer

Model versioning

Answer

Provisioned throughput

Question 3

A Generative AI engineer is preparing a Delta table of support tickets for embedding generation. The pipeline computes embeddings with ai_query and stores them in a separate embeddings table keyed by ticket_id. Tickets are frequently updated by agents, and the engineer wants the embeddings table to reflect the latest ticket text without recomputing embeddings for tickets whose text has not changed. Which design best achieves this?

Accepted Answer

Use change data capture with APPLY CHANGES to merge ticket updates into the embeddings table, recomputing embeddings only for changed rows.. To update embeddings only for changed tickets, the pipeline must consume a change feed and apply changes to the embeddings table. APPLY CHANGES merges inserts, updates, and deletes while allowing embedding derivation to run only on changed rows. Full refreshes recompute everything, and file-level or query-level filters cannot persist decisions across updates.

Answer

Add a hash column of the ticket text and use a QUALIFY clause to filter unchanged rows within the same query.

Answer

Enable Auto Optimize on the embeddings table so only modified files are rewritten during updates.

Answer

Run a full refresh of the embeddings table on every pipeline update so all ticket embeddings stay current.

Question 4

An AI engineer is building a RAG application and wants to log the retrieval context and generated response for each request to MLflow for evaluation. They are using the `mlflow.langchain` flavor. Which method should they use to log the model so that MLflow automatically captures the necessary artifacts?

Accepted Answer

mlflow.langchain.log_model. For LangChain models, `mlflow.langchain.log_model` is the specialized logging function that captures the chain's configuration and enables MLflow to track inputs and outputs. This allows the engineer to later evaluate retrieval context and responses using MLflow's evaluation capabilities. Other logging methods do not provide this automatic integration.

Answer

mlflow.sklearn.log_model

Answer

mlflow.tensorflow.log_model

Answer

mlflow.pyfunc.log_model

Question 5

A GenAI engineer must build a fine-tuning dataset from 40 TB of raw JSONL conversation logs stored in cloud object storage. The logs are immutable and only ever read once, in full, during preprocessing. Which storage and access configuration should be used to minimize cost while keeping the data readable by Spark on Databricks?

Accepted Answer

Register the cloud path as an external location in Unity Catalog and read the JSONL files directly with Spark.. Because the logs are immutable and read once in full, the lowest-cost approach is to leave them where they are and read them in place under Unity Catalog governance. Copying or converting the data creates a redundant full-size copy and extra compute for no reuse benefit, while legacy mounts sacrifice governance without reducing storage or access cost.

Answer

Convert the JSONL to Parquet with an external tool, upload the Parquet back, then read it from the bucket.

Answer

Run COPY INTO to ingest the JSONL into a managed Delta table, then read the Delta table for preprocessing.

Answer

Mount the object storage bucket to DBFS with a legacy mount and read files through the /mnt path.

Question 6

A data engineer needs to persist a prepared instruction-tuning dataset so that downstream fine-tuning jobs can read it with ACID guarantees, time travel, and schema enforcement, and so that Unity Catalog can track column-level lineage. Which storage format and registration should be used?

Accepted Answer

Write the dataset as a Delta table registered in Unity Catalog.. Delta Lake on Unity Catalog is the only option that simultaneously delivers ACID transactions, time travel, schema enforcement, and column-level lineage for the prepared dataset. Parquet, CSV, and ORC files lack transactional table semantics, and the Hive metastore does not provide the Unity Catalog lineage the team needs.

Answer

Write the dataset as an ORC table in the Hive metastore.

Answer

Write the dataset as CSV files to an external location registered in Unity Catalog.

Answer

Write the dataset as Parquet files in a Unity Catalog volume.

Question 7

An engineer is cleaning a Delta table of customer support transcripts stored in Unity Catalog. The table has a nested array column named messages, where each element has role and content fields. They need to keep only rows where at least one message has role equal to 'user' and content longer than 20 characters. Which transformation correctly expresses this filter?

Accepted Answer

Use the higher-order function exists on the messages array with a lambda testing role = 'user' AND length(content) > 20.. Filtering rows based on whether any nested element meets a predicate is exactly what the exists higher-order function provides, and its lambda can test both role and content length in one pass. Exploding reshapes and shuffles data, string matching is ambiguous, and transform preserves array length so it cannot signal absence of a match.

Answer

Cast the messages array to a string and apply a LIKE pattern matching the literal text 'user' followed by any content.

Answer

Use the transform higher-order function on messages and then check whether the resulting array is non-empty.

Answer

Explode the messages array, filter on role and content length, then group by the row identifier to rebuild the rows.

Question 8

A data engineer is preparing a large corpus of customer support transcripts stored as Parquet in a Unity Catalog volume. Before generating embeddings, each transcript must be tokenized and truncated to a maximum token length. The engineer wants to use a Databricks-native approach that runs distributed across the cluster and avoids pulling the full corpus into a single node. Which approach best satisfies these requirements?

Accepted Answer

Use spark.read.parquet to load the corpus and apply a pandas_udf that tokenizes and truncates each transcript.. Distributed tokenization of a large corpus requires the work to run inside Spark executors, which a pandas UDF provides by operating vectorized on each partition. Reading with pandas on the driver or looping over files locally centralizes the workload and breaks at scale. A pandas UDF keeps the corpus distributed while applying the tokenizer and truncation per row.

Answer

Use dbutils.fs.cp to copy the Parquet files to a local path, then run a Python tokenizer loop over each file.

Answer

Create a Delta table from the Parquet files and query it with a SQL UDF that calls a tokenizer from a Python library.

Answer

Read the Parquet files with pandas.read_parquet on the driver, tokenize, then write the truncated text back to the volume.

Question 9

A GenAI engineer is building an agent with LangChain on Databricks. The agent must call a Unity Catalog function `catalog.schema.get_weather` to fetch current weather. They want the LLM to decide when to invoke this function. Which LangChain component should they use to expose the Unity Catalog function to the LLM?

Accepted Answer

Databricks Unity Catalog function as a LangChain tool. To let an LLM decide when to call a Unity Catalog function, the function must be presented as a LangChain tool. The `UCFunctionToolkit` from Databricks integrates with LangChain, automatically generating tool definitions from Unity Catalog functions. This enables the agent to invoke the function dynamically based on the conversation, which is essential for building responsive GenAI applications.

Answer

Databricks Vector Search retriever

Answer

MLflow pyfunc model wrapper

Answer

Databricks SQL Connector

Question 10

A developer is using MLflow to track experiments for a generative AI application. They want to log a prompt template and its associated parameters so that they can reproduce the exact input to the model later. Which MLflow function should they use to log the prompt template as an artifact?

Accepted Answer

mlflow.log_artifact. Prompt templates are best stored as artifacts because they are files that may be reused, versioned, and referenced independently of the run. mlflow.log_artifact provides a robust way to persist such files, ensuring reproducibility and easy access later.

Answer

mlflow.set_tag

Answer

mlflow.log_metric

Answer

mlflow.log_param

Question 11

A GenAI engineer is developing an agent using Databricks Mosaic AI Agent Framework. The agent must call an external API to fetch real-time stock prices. The engineer wants to ensure the agent can be evaluated and deployed with minimal changes between development and production. Which approach should the engineer take to define the tool-calling logic?

Accepted Answer

Implement the API call as a Python function and register it as a tool in the agent's LangChain or similar framework, then log the agent with MLflow.. The Mosaic AI Agent Framework supports defining tools as Python functions that the agent can invoke. By registering the function as a tool and logging the agent with MLflow, the same code is used for evaluation and deployment, ensuring consistency. Other approaches either do not execute the call, introduce delay, or add architectural complexity that hinders portability.

Answer

Create a separate Databricks job that periodically fetches stock prices and writes them to a Delta table, then have the agent query that table.

Answer

Use a Databricks SQL function to call the external API via a UDF, and invoke it from the agent.

Answer

Hardcode the API call directly in the agent's prompt as a description of the endpoint.

Question 12

A GenAI engineer is preparing a large text corpus for fine-tuning an LLM. The corpus contains many near-duplicate documents and documents in multiple languages. They need to reduce redundancy and ensure language consistency. Which two steps should be performed during data preparation? (Choose two.)

Accepted Answer

Use the language detection function from the spark-nlp library to filter documents to a single target language.. To reduce redundancy and ensure language consistency, the engineer should use MinHash with LSH to remove near-duplicate documents and apply language detection to filter to the target language. These steps directly address the stated goals and are scalable for large corpora.

Answer

Train a custom tokenizer on the entire corpus to better handle multilingual text.

Answer

Use Delta Lake time travel to revert to a previous version of the dataset if duplicates are found.

Answer

Apply a fixed-size chunking strategy to split all documents into 512-token segments before deduplication.

Question 13

A Generative AI engineer is preparing a Delta table of product reviews for a retrieval-augmented generation application. The reviews contain HTML tags, inconsistent casing, and occasional very long paragraphs that exceed the embedding model's context window. The engineer wants to clean and normalize the text before chunking and embedding. Which two actions should the engineer take to directly address the stated quality issues? (Choose two.)

Accepted Answer

Split long paragraphs into overlapping chunks sized to the embedding model's token limit.. The reviews need markup removed and length controlled before embedding. Stripping HTML and normalizing whitespace cleans the text, while chunking with overlap sized to the model token limit prevents truncation of long paragraphs. Uppercasing, dropping short reviews, and archiving raw HTML do not resolve the stated noise and overflow problems.

Answer

Drop every review shorter than 100 characters to reduce noise in the corpus.

Answer

Store the raw HTML in a separate column so it remains available for future parsing needs.

Answer

Convert all review text to uppercase to standardize casing across the corpus.

Question 14

A GenAI engineer has registered a RAG chain in Unity Catalog as a model and now needs to deploy it for real-time inference with per-request token usage and latency captured automatically. Which Databricks capability should they enable on the serving endpoint?

Accepted Answer

Enable inference tables on the Mosaic AI Model Serving endpoint.. Inference tables are the native Mosaic AI Model Serving feature that persists request and response payloads plus metadata to a Delta table, giving automatic capture of token usage and latency for real-time endpoints. Autoscaling, MLflow experiments, and Unity Catalog lineage address capacity, development tracking, and governance respectively, but none record per-request serving telemetry.

Answer

Attach an MLflow experiment to the endpoint and rely on the run history for telemetry.

Answer

Enable Unity Catalog lineage on the registered model version.

Answer

Configure the endpoint with autoscaling enabled to log per-request metrics.

Question 15

A GenAI engineer has built a retrieval-augmented generation (RAG) application using Databricks Vector Search and a Databricks-hosted LLM served via Mosaic AI Model Serving. Users report that responses are sometimes irrelevant or cite incorrect document passages. The engineer wants to systematically improve answer quality by identifying which retrieved chunks are actually being used by the LLM. Which approach should the engineer take to capture the relationship between retrieved context and the generated response for later evaluation?

Accepted Answer

Enable MLflow Tracing on the RAG chain to log each retrieval and generation step with inputs and outputs.. MLflow Tracing instruments each stage of a RAG pipeline, recording retrieved chunks and the LLM's output as linked spans. This gives the engineer the data needed to see which context was passed and potentially used, enabling targeted improvements and evaluation. Other options either change retrieval behavior or log only endpoint-level data, lacking the granular linkage required.

Answer

Configure the Model Serving endpoint to log all requests and responses to a Delta table for offline analysis.

Answer

Increase the Vector Search index's embedding dimension to improve semantic matching.

Answer

Add a reranker model after Vector Search to reorder retrieved chunks by relevance score.