Internal policies change frequently.
Use current documents without retraining a model after every update.
Which method best matches the requirement?
RAG retrieves current documents at answer time; fine-tuning is better suited to adapting behavior or format and requires a training cycle.
Detailed explanation
This is unnecessarily expensive and slow for routine document changes.
Fine-tuning does not automatically ingest future document updates.
This ignores length, permissions, and conflicting documents.
Frequently changing knowledge can be retrieved at answer time.
Check official documentation
Compare the following points with the official documentation.
Amazon Bedrock Knowledge BasesとCustom model fine-tuningの公式説明を比較する。
Official references
What to confirm
知識の鮮度にはRAG、モデルの振る舞いや形式の適応には微調整を検討することを説明できる。
Key points
- Knowledge freshness
- RAG
- Fine-tuning
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
Knowledge versus behavior
Retrieval changes the context supplied to a model, while fine-tuning changes parameters and requires retraining.
Update path
A source update can refresh an index; a parameter change requires evaluation and a controlled model release.