3.2Standard
Ingest a PDF procedure containing tables and footnotes.
Keep column and annotation meaning.
Choose two appropriate ingestion practices.
× Incorrect
Preserve headings, table labels and units, footnotes, and page locations, then sample against the source before indexing.
Detailed explanation
IncorrectFlatten the PDF and discard units
Values can lose their relationships.
CorrectCompare extracted samples with the source and representative queries
OCR and column errors can be found early.
CorrectPreserve headings, table columns and units, footnotes, and page positions
Numbers remain traceable to their meaning.
IncorrectIndex every page without extraction checks
Bad chunks can become evidence at scale.
Check official documentation
Compare the following points with the official documentation.
AWS公式AIF-C01 Domain 3.2のデータ取り込み・文書解析・RAG品質を確認する。
Official references
What to confirm
PDF・表・脚注の意味を保持する取り込みと検証を説明できる。
Key points
- Layout
- Tables
- OCR validation
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
Document parsing
Extracting text, tables, images, layout, and metadata from source documents.
Layout preservation
Keeping structural relationships such as headings, columns, units, and reading order.
Question IDAWS-AIF-183
EnvironmentAWS公式AIF-C01試験ガイドとAWS公式ドキュメントの確認
Last technical review2026-08-20
Report an error or rights issue