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
Frequently changing knowledge can be retrieved at answer time.
Frequently changing knowledge can be retrieved at answer time.
This is unnecessarily expensive and slow for routine document changes.
This is unnecessarily expensive and slow for routine document changes.
This ignores length, permissions, and conflicting documents.
This ignores length, permissions, and conflicting documents.
Fine-tuning does not automatically ingest future document updates.
Fine-tuning does not automatically ingest future document updates.
Try it yourself
An example you can run in a temporary verification environment.
Amazon Bedrock Knowledge BasesとCustom model fine-tuningの公式説明を比較する。Expected result
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
- Command output formatting can vary slightly by distribution or tool version.
- Run the example in a temporary directory or process when possible.
Foundation review
Read the scope first
Check whether the command acts on the current shell, a new process, an existing process, or a file.
Verify the observable result
Use the supplied command and compare the output with the expected result.