Exam AWS Certified AI Practitioner AIF-C01 topic 1 question 140 discussion

Exam question from Amazon's AWS Certified AI Practitioner AIF-C01

Question #: 140
Topic #: 1

[All AWS Certified AI Practitioner AIF-C01 Questions]

A company is using a large language model (LLM) on Amazon Bedrock to build a chatbot. The chatbot processes customer support requests. To resolve a request, the customer and the chatbot must interact a few times.

Which solution gives the LLM the ability to use content from previous customer messages?

A. Turn on model invocation logging to collect messages.
B. Add messages to the model prompt.
C. Use Amazon Personalize to save conversation history.
D. Use Provisioned Throughput for the LLM.

Show Suggested Answer

Suggested Answer: B 🗳️

by chris_spencer at Feb. 4, 2025, 10:13 a.m.

Disclaimers:

- ExamTopics website is not related to, affiliated with, endorsed or authorized by Amazon.
- Trademarks, certification & product names are used for reference only and belong to Amazon.

Comments

Submit Cancel

65703c1

2 weeks, 5 days ago

Selected Answer: B

B is the correct answer

upvoted 1 times

...

kopper2019

6 months ago

Selected Answer: B

B. Add previous messages to the model prompt.

upvoted 2 times

...

kopper2019

6 months, 1 week ago

Selected Answer: B

B is the correct answer. Here's why: Adding previous messages to the prompt allows the LLM to maintain context across multiple interactions.

upvoted 2 times

...

Jessiii

6 months, 1 week ago

Selected Answer: B

Add messages to the model prompt. By including the conversation history in the model's prompt, the LLM can maintain context and reference previous interactions to provide coherent and relevant responses. This approach ensures that the chatbot can understand and respond to the customer's requests based on the entire conversation history.

upvoted 2 times

...

jerry00218

6 months, 2 weeks ago

Selected Answer: B

Answer: B. Add messages to the model prompt Large language models (LLMs) typically rely on the context that is provided directly in the input prompt when generating a response. To give the model the ability to use content from previous customer messages, you need to include those past messages in the prompt for each new inference call. This approach ensures that the model has the necessary context to respond accurately based on prior interactions.

upvoted 3 times

...