Q8ML Model Development
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
← → navigate · a answer
Discussion · 4
5
Tokens are the smallest units an LLM processes.
Embeddings convert text into high-dimensional vectors that capture semantic meaning.
RAG combines generated content with retrieved external information to enrich the output.
3
Token : Represents a unit of text used when the model processes and generates responses.
Temperature : Controls how random and creative the generated output is, allowing adjustments to the model's response style.
Embedding : Converts text into vector representations to capture semantic meaning, improving the model's ability to understand and generate coherent content.
1
Token
Embedding
RAG
1
Tokens
Embeddings
Retrieval Augmented Generation(RAG)