Databricks Certified Generative AI Engineer Associate Exam - Topic 5 Question 4 Discussion

Actual exam question for Databricks's Databricks Certified Generative AI Engineer Associate exam

Question #: 4
Topic #: 5

[All Databricks Certified Generative AI Engineer Associate Questions]

A Generative AI Engineer developed an LLM application using the provisioned throughput Foundation Model API. Now that the application is ready to be deployed, they realize their volume of requests are not sufficiently high enough to create their own provisioned throughput endpoint. They want to choose a strategy that ensures the best cost-effectiveness for their application.

What strategy should the Generative AI Engineer use?

ASwitch to using External Models instead

BDeploy the model using pay-per-token throughput as it comes with cost guarantees

CChange to a model with a fewer number of parameters in order to reduce hardware constraint issues

DThrottle the incoming batch of requests manually to avoid rate limiting issues

Show Suggested Answer

Suggested Answer: B

Problem Context: The engineer needs a cost-effective deployment strategy for an LLM application with relatively low request volume.

Explanation of Options:

Option A: Switching to external models may not provide the required control or integration necessary for specific application needs.

Option B: Using a pay-per-token model is cost-effective, especially for applications with variable or low request volumes, as it aligns costs directly with usage.

Option C: Changing to a model with fewer parameters could reduce costs, but might also impact the performance and capabilities of the application.

Option D: Manually throttling requests is a less efficient and potentially error-prone strategy for managing costs.

Option B is ideal, offering flexibility and cost control, aligning expenses directly with the application's usage patterns.

by Izetta at Oct 23, 2024, 02:14 AM

Limited Time Offer

25%

Off

Get Premium Databricks Certified Generative AI Engineer Associate Questions as Interactive Web-Based Practice Test or PDF

Contribute your Thoughts:

Submit Cancel

Karan

3 months ago

Wow, I didn't know throttling could be a strategy!

upvoted 0 times

...

Tonette

3 months ago

C could help with performance, but is it really necessary?

upvoted 0 times

...

Jacqueline

3 months ago

Not sure about B, what if the usage spikes later?

upvoted 0 times

...

Rory

4 months ago

I agree, pay-per-token is a smart move!

upvoted 0 times

...

Teri

4 months ago

B seems like the best option for cost-effectiveness.

upvoted 0 times

...

Nobuko

4 months ago

Changing to a model with fewer parameters sounds like it could help, but I’m not convinced it directly addresses the cost issue.

upvoted 0 times

...

Leana

4 months ago

I feel like we practiced a similar question where throttling requests was mentioned, but I don't think that's the best strategy for cost-effectiveness.

upvoted 0 times

...

Joseph

4 months ago

I'm not entirely sure, but switching to external models seems like it could save costs too. I need to think about the trade-offs.

upvoted 0 times

...

Hoa

5 months ago

I remember we discussed the cost implications of different throughput options in class. I think pay-per-token might be the best choice here.

upvoted 0 times

...

Nichelle

5 months ago

I'm not sure about Option A. Switching to external models might not be the best solution if the current model is working well.

upvoted 0 times

...

Colene

5 months ago

I'm leaning towards Option B. The pay-per-token throughput seems like it would provide the most cost guarantees, which is important for this application.

upvoted 0 times

...

Sina

5 months ago

I think the key here is to find a way to reduce the hardware constraints and still maintain the performance of the model. Option C seems like the best approach to me.

upvoted 0 times

...

Han

5 months ago

Hmm, I'm a bit confused by the question. I'm not sure which strategy would be the most cost-effective.

upvoted 0 times

...

Eric

5 months ago

This seems like a tricky question. I'll need to think through the different options carefully.

upvoted 0 times

...

Fernanda

1 year ago

Ah, the joys of scaling AI applications. I'd say option B is the way to go, but maybe they should also consider a backup plan just in case. You know, like a Plan B.

upvoted 0 times

...