Explain model input processing and RAG document search.
The same word embedding can have different roles.
Choose two correct statements.
Token embeddings represent input units inside a model, while document embeddings represent chunks for semantic retrieval; neither is authorization.
Detailed explanation
A semantic vector is not guaranteed to be reversible.
RAG can compare questions and chunks by similarity.
Representation and authorization are separate.
They make words or subwords numerical for neural processing.
Check official documentation
Compare the following points with the official documentation.
AWS公式AIF-C01 Domain 2.1・3.2とAmazon Bedrock埋め込みの説明を確認する。
Official references
What to confirm
内部トークン表現とRAG用文書ベクトルの役割を区別できる。
Key points
- Token
- Document
- Authorization
Notes
- Environment: AWS公式AIF-C01試験ガイドとAWS公式ドキュメントの確認
- Compare the definition with the AIF-C01 objective and the service documentation before applying it.
- Keep the concept separate from a particular answer choice or implementation step.
Foundation review
Token embedding
A numeric representation assigned to an individual token for model processing.
Document embedding
A vector representing the meaning of a document or chunk for search or comparison.