Pass conversation history and retrieved documents to a model.
Stay within context and cost limits.
Choose two designs.
Measure input, output, and reserved tokens, limit retrieval and history, and evaluate splitting or summarization for lost constraints and evidence.
Detailed explanation
Assumptions and constraints can disappear.
Overflow and cost are controlled.
Tokenization and model limits differ.
Shortening quality is checked.
Check official documentation
Compare the following points with the official documentation.
AWS公式AIF-C01 Domain 2.3のコンテキスト上限、トークン、プロンプト設計を確認する。
Official references
What to confirm
文脈上限と費用を守りつつ、重要な前提を失わない短縮方法を選べる。
Key points
- Token budget
- Summary
- Splitting
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 budget
A planned limit for input, output, or reserved tokens in a request.
Context limit
The maximum input and output token range a model supports in one request.