Skip to content

Commit 35f545b

Browse files
bundoleeclaude
andcommitted
docs: add OCR configuration examples to CLAUDE.md
Add --ocr-lang and --force-ocr usage examples for hybrid server with supported language codes reference. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
1 parent b7cd0da commit 35f545b

1 file changed

Lines changed: 9 additions & 0 deletions

File tree

CLAUDE.md

Lines changed: 9 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -47,8 +47,17 @@ opendataloader-pdf-hybrid --port 5003
4747

4848
# With debug logging
4949
opendataloader-pdf-hybrid --log-level debug
50+
51+
# With OCR language configuration (for scanned PDFs)
52+
opendataloader-pdf-hybrid --ocr-lang "ch_sim,en" # Chinese + English
53+
opendataloader-pdf-hybrid --ocr-lang "ko" # Korean
54+
opendataloader-pdf-hybrid --ocr-lang "ja" --force-ocr # Japanese with forced OCR
5055
```
5156

57+
**OCR Options:**
58+
- `--ocr-lang`: Comma-separated [EasyOCR language codes](https://www.jaided.ai/easyocr/) (default: EasyOCR default languages)
59+
- `--force-ocr`: Force full-page OCR on all pages regardless of embedded text
60+
5261
## Architecture
5362

5463
```

0 commit comments

Comments
 (0)