Q: 9
HOTSPOT
An ML engineer is building a generative AI application on Amazon Bedrock by using large language
models (LLMs).
Select the correct generative AI term from the following list for each description. Each term should
be selected one time or not at all. (Select three.)
• Embedding
• Retrieval Augmented Generation (RAG)
• Temperature
• Token
?
?Your Answer
Discussion
Nah, I don't think Token fits here. Embedding, Retrieval Augmented Generation (RAG), Temperature.
Embedding, Retrieval Augmented Generation (RAG), Temperature
These match the AWS generative AI patterns in official docs and labs. Used similar terms in practice tests too. I think this is what they're after, but open to other takes if someone disagrees!
Embedding, Retrieval Augmented Generation (RAG), Temperature
Embedding, Retrieval Augmented Generation (RAG), Temperature. Saw similar in exam reports, seems like the best fit.
Embedding, Retrieval Augmented Generation (RAG), Temperature. Had something like this in a mock-Token's not really about retrieval or output control, it's more basic. These three match the key generative AI concepts AWS highlights.
Not Token, it's Embedding, Retrieval Augmented Generation (RAG), and Temperature. Token is a common trap in these kinds of questions.
Makes sense, those are embedding, retrieval augmented generation, temperature.
Embedding, Retrieval Augmented Generation (RAG), Temperature-Token would only fit if the prompt described LLM input units specifically.
Did anyone else run into this on a practice test? The official AWS docs and exam guide cover Embedding, RAG, and Temperature often but I’m wondering if any lab exercises helped clarify these for folks.
Yeah, I'd pick Embedding, Retrieval Augmented Generation (RAG), and Temperature. Embedding is about turning text into vectors, RAG mixes in fresh external data, and Temperature tweaks the randomness in generated responses. Pretty sure that's what AWS expects here, but let me know if you see it differently.
Be respectful. No spam.
