Test files › RAG test corpus › service-manual.docx

Sample DOCX file (service manual)

Name: Sample DOCX file (service manual): service-manual.docx
Creator: HEXAQA
License: https://creativecommons.org/publicdomain/zero/1.0/

A Word document whose numbers and part codes are split across text runs, as Word does after editing.

↓ Download service-manual.docx

Filename	`service-manual.docx`
Format	DOCX
Size	1.2 KB (1,199 bytes)
MIME type	`application/vnd.openxmlformats-officedocument.wordprocessingml.document`
SHA-256	`8f195ed4250601a75a7cf7016fc94262a04bbaa942e26ea3ebb49c73421c6a60`

What this file catchesConcatenating runs gives "every 12 months" and "QM-CAL-KIT". Any extractor that puts a space or newline between runs gives "every 1 2 months" and "QM- CAL- KIT".

Download & verify

curl -fsSL -o "service-manual.docx" "https://files.hexaqa.com/rag/corpus/service-manual.docx"

curl -fsSL "https://files.hexaqa.com/rag/corpus/service-manual.docx" | sha256sum # expect: 8f195ed4250601a75a7cf7016fc94262a04bbaa942e26ea3ebb49c73421c6a60

More rag test corpus test files

firmware-3.1-notes-v2.md k2-specification.pdf price-list.xlsx product-sheet-two-column.pdf staff-handbook.pdf support-faq.html support-thread.eml answers.jsonl

← All RAG test corpus files