A.  

Add the section header as a prefix to chunks

B.  

Increase the document chunk size

C.  

Split the document by sentence

D.  

Use a larger embedding model

E.  

Fine tune the response generation model

A.  

Create a tool for finding available team members given project dates. Embed all project scopes into a vector store, perform a retrieval using team member profiles to find the best team member.

B.  

Create a tool for finding team member availability given project dates, and another tool that uses an LLM to extract keywords from project scopes. Iterate through available team members’ profiles and perform keyword matching to find the best available team member.

C.  

Create a tool to find available team members given project dates. Create a second tool that can calculate a similarity score for a combination of team member profile and the project scope. Iterate through the team members and rank by best score to select a team member.

D.  

Create a tool for finding available team members given project dates. Embed team profiles into a vector store and use the project scope and filtering to perform retrieval to find the available best matched team members.

A.  

Use a reranker to order the documents based on the relevance scores.

B.  

Modify the prompt to instruct the LLM to order the documents based on the relevance scores.

C.  

Use a different embedding model for computing document embeddings.

D.  

Increase the number of documents added to the prompt to improve context relevance.

A.  

Llama2-70b

B.  

BGE-large

C.  

MPT-7b

D.  

CodeLlama-34B

A.  

Split the data into train and test set, create a unique identifier for each document, then save to a Delta table

B.  

Flatten the dataframe to one chunk per row, create a unique identifier for each row, and save to a Delta table

C.  

First create a unique identifier for each document, then save to a Delta table

D.  

Store each chunk as an independent JSON file in Unity Catalog Volume. For each JSON file, the key is the document section name and the value is the array of text chunks for that section

A.  

Limit the number of relevant documents available for the RAG application to retrieve from

B.  

Pick a smaller LLM that is domain-specific

C.  

Limit the number of queries a customer can send per day

D.  

Use the largest LLM possible because that gives the best performance for any general queries

A.  

Enable MLflow tracing to gain visibility into each agent's behavior and execution step.

B.  

Run MLflow.evaluate to determine root cause of failed step.

C.  

Implement structured logging within the agent's code to capture detailed execution information.

D.  

Deconstruct the agent into independent steps to simplify debugging.

A.  

Big Code Models Leaderboard

B.  

Number of model parameters

C.  

MTEB Leaderboard

D.  

Chatbot Arena Leaderboard

E.  

Number of model downloads last month

A.  

Use few snot prompting to instruct the model on expected output format

B.  

Use zero shot prompting to instruct the model on expected output format

C.  

Use zero shot chain-of-thought prompting to prevent a verbose output format

D.  

Use a system prompt to instruct the model to be succinct in its answer

A.  

It allows you to break down complex tasks into multiple independent subtasks. This enables the assistant to generate more comprehensive and accurate responses.

B.  

It allows you to reduce the latency of your applications. By having multiple chains participating in the response as a chain, you increase the rate at which the response is generated.

C.  

It allows you to decrease the effort involved in crafting a prompt. Chains make it possible to reuse prompt text across multiple different use cases.

D.  

It reduces the average cost of a typical request. Chains make more efficient use of the tokens produced to generate higher quality responses with fewer tokens.

A.  

Use an access token belonging to service principals

B.  

Use a frequently rotated access token belonging to either a workspace user or a service principal

C.  

Use OAuth machine-to-machine authentication

D.  

Use an access token belonging to any workspace user

A.  

The chatbot should only look at previous event information

B.  

There should be two different chatbots handling different types of user queries.

C.  

The chatbot should be implemented as a multi-step LLM workflow. First, identify the type of question asked, then route the question to the appropriate model. If it’s an upcoming event question, send the query to a text-to-SQL model. If it’s about ticket purchasing, the customer should be redirected to a payment platform.

D.  

The chatbot should only process payments

A.  

Safety Guardrail

B.  

Security Guardrail

C.  

Contextual Guardrail

D.  

Compliance Guardrail

A.  

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.

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”: “sarah.lee925@gmail.com”, “order_id”: “RE987D”}

C.  

You will receive customer emails and need to extract date, sender email, and order ID. Return the extracted information in a human-readable format.

D.  

You will receive customer emails and need to extract date, sender email, and order I

D.  

A.  

Assess the quality of the retrieved context

B.  

Implement caching for frequently asked questions

C.  

Use a different LLM to improve the generated response

D.  

Use a different semantic similarity search algorithm

A.  

Use spark.conf.set ()

B.  

Pass variables using the Databricks Feature Store API

C.  

Add credentials using environment variables

D.  

Pass the secrets in plain text

A.  

Respond with “In Stock” if the customer asks for a product.

B.  

You will be given a customer call transcript where the customer asks about product availability. The outputs are either “In Stock” or “Out of Stock”. Format the output in JSON, for example: {“call_id”: “123”, “label”: “In Stock”}.

C.  

Respond with “Out of Stock” if the customer asks for a product.

D.  

You will be given a customer call transcript where the customer inquires about product availability. Respond with “In Stock” if the product is available or “Out of Stock” if not.

A.  

Directly modify the LLM’s internal architecture to include preprocessing steps

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.  

Rather than preprocessing prompts, it’s more effective to postprocess the LLM outputs to align the outputs to desired outcomes

D.  

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

A.  

Tram the LLM to generate a single, comprehensive response without interacting with any external tools, relying solely on its pre-trained knowledge.

B.  

Implement a framework like ReAct which allows the LLM to generate reasoning traces and perform task-specific actions that leverage external tools if necessary.

C.  

Encourage the LLM to make multiple API calls in sequence without planning or structuring the calls, allowing the LLM to decide when and how to use external tools spontaneously.

D.  

Use a Chain-of-Thought (CoT) prompting technique to guide the LLM through a series of reasoning steps, then manually input the results from external tools for the final answer.

A.  

Operational metrics like request volume, latency, and errors

B.  

Quality metrics like correctness and guideline adherence

C.  

Both operational and quality metrics

D.  

No metrics are automatically captured

A.  

(Incorrect structure)

B.  

(Incorrect structure)

C.  

prompt_template = "Tell me a {adjective} joke"

prompt = PromptTemplate(input_variables=["adjective"], template=prompt_template)

llm = OpenAI()

llm_chain = LLMChain(prompt=prompt, llm=llm)

llm_chain.generate([{"adjective": "funny"}])

D.  

(Incorrect structure)