mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-08 20:58:11 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs: support running examples from root or subfolder (#1816)

Browse Source 
support running examples from root or subfolder

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
This commit is contained in:
Michele Dolfi
2025-06-19 04:10:40 -05:00
committed by GitHub
parent dd7f64ff28
commit 64ac043786
13 changed files with 33 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
docs/examples/tesseract_lang_detection.py vendored
View File

@@ -9,7 +9,8 @@ from docling.document_converter import DocumentConverter, PdfFormatOption
def main():
input_doc = Path("./tests/data/pdf/2206.01062.pdf")
data_folder = Path(__file__).parent / "../../tests/data"
input_doc_path = data_folder / "pdf/2206.01062.pdf"
# Set lang=["auto"] with a tesseract OCR engine: TesseractOcrOptions, TesseractCliOcrOptions
# ocr_options = TesseractOcrOptions(lang=["auto"])
@@ -27,7 +28,7 @@ def main():
}
)
doc = converter.convert(input_doc).document
doc = converter.convert(input_doc_path).document
md = doc.export_to_markdown()
print(md)