Send chat history and retrieved documents to a model.
Control quality, cost, and the risk of exceeding the limit.
Choose two appropriate designs.
Summarize history and retrieve relevant documents, then define token limits and fallback behavior before the limit is exceeded.
Detailed explanation
This increases cost, leakage, and limit risk.
Reducing input controls context size and cost.
The application can truncate, retry, summarize, or notify the user safely.
The user needs a clear state and a safe alternative.
Check official documentation
Compare the following points with the official documentation.
AWS公式AIF-C01ガイドDomain 2.2とAmazon Bedrockモデル仕様のコンテキスト上限を確認する。
Official references
What to confirm
入力の最小化と上限超過時の動作を設計できる。
Key points
- Input minimization
- Limits
- Fallback
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
Context competition
Long history and irrelevant documents consume capacity that could be used for the current answer.
Graceful degradation
A defined fallback is safer than hiding an overflow error or returning an unexplained empty result.