mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-08-01 23:12:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix example filepaths

Browse Source 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
This commit is contained in:
Michele Dolfi 2025-02-06 16:12:52 +01:00
parent 6d801eff55
commit 23e82a5f49
11 changed files with 11 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docs/examples/custom_convert.py
View File

@ -21,7 +21,7 @@ _log = logging.getLogger(__name__)
def main():
logging.basicConfig(level=logging.INFO)
input_doc_path = Path("./tests/data/2206.01062.pdf")
input_doc_path = Path("./tests/data/pdf/2206.01062.pdf")
###########################################################################

2
docs/examples/develop_formula_understanding.py
View File

@ -68,7 +68,7 @@ class ExampleFormulaUnderstandingPipeline(StandardPdfPipeline):
def main():
logging.basicConfig(level=logging.INFO)
input_doc_path = Path("./tests/data/2203.01017v2.pdf")
input_doc_path = Path("./tests/data/pdf/2203.01017v2.pdf")
pipeline_options = ExampleFormulaUnderstandingPipelineOptions()
pipeline_options.do_formula_understanding = True

2
docs/examples/develop_picture_enrichment.py
View File

@ -71,7 +71,7 @@ class ExamplePictureClassifierPipeline(StandardPdfPipeline):
def main():
logging.basicConfig(level=logging.INFO)
input_doc_path = Path("./tests/data/2206.01062.pdf")
input_doc_path = Path("./tests/data/pdf/2206.01062.pdf")
pipeline_options = ExamplePictureClassifierPipelineOptions()
pipeline_options.images_scale = 2.0

2
docs/examples/export_figures.py
View File

@ -16,7 +16,7 @@ IMAGE_RESOLUTION_SCALE = 2.0
def main():
logging.basicConfig(level=logging.INFO)
input_doc_path = Path("./tests/data/2206.01062.pdf")
input_doc_path = Path("./tests/data/pdf/2206.01062.pdf")
output_dir = Path("scratch")
# Important: For operating with page images, we must keep them, otherwise the DocumentConverter

2
docs/examples/export_multimodal.py
View File

@ -19,7 +19,7 @@ IMAGE_RESOLUTION_SCALE = 2.0
def main():
logging.basicConfig(level=logging.INFO)
input_doc_path = Path("./tests/data/2206.01062.pdf")
input_doc_path = Path("./tests/data/pdf/2206.01062.pdf")
output_dir = Path("scratch")
# Important: For operating with page images, we must keep them, otherwise the DocumentConverter

2
docs/examples/export_tables.py
View File

@ -12,7 +12,7 @@ _log = logging.getLogger(__name__)
def main():
logging.basicConfig(level=logging.INFO)
input_doc_path = Path("./tests/data/2206.01062.pdf")
input_doc_path = Path("./tests/data/pdf/2206.01062.pdf")
output_dir = Path("scratch")
doc_converter = DocumentConverter()

2
docs/examples/full_page_ocr.py
View File

@ -14,7 +14,7 @@ from docling.document_converter import DocumentConverter, PdfFormatOption
def main():
input_doc = Path("./tests/data/2206.01062.pdf")
input_doc = Path("./tests/data/pdf/2206.01062.pdf")
pipeline_options = PdfPipelineOptions()
pipeline_options.do_ocr = True

2
docs/examples/inspect_picture_content.py
View File

@ -4,7 +4,7 @@ from docling.datamodel.base_models import InputFormat
from docling.datamodel.pipeline_options import PdfPipelineOptions
from docling.document_converter import DocumentConverter, PdfFormatOption
source = "tests/data/amt_handbook_sample.pdf"
source = "tests/data/pdf/amt_handbook_sample.pdf"
pipeline_options = PdfPipelineOptions()
pipeline_options.images_scale = 2

2
docs/examples/run_with_accelerator.py
View File

@ -14,7 +14,7 @@ from docling.document_converter import DocumentConverter, PdfFormatOption
def main():
input_doc = Path("./tests/data/2206.01062.pdf")
input_doc = Path("./tests/data/pdf/2206.01062.pdf")
# Explicitly set the accelerator
# accelerator_options = AcceleratorOptions(

2
docs/examples/run_with_formats.py
View File

@ -25,7 +25,7 @@ def main():
Path("tests/data/docx/lorem_ipsum.docx"),
Path("tests/data/pptx/powerpoint_sample.pptx"),
Path("tests/data/2305.03393v1-pg9-img.png"),
Path("tests/data/2206.01062.pdf"),
Path("tests/data/pdf/2206.01062.pdf"),
Path("tests/data/test_01.asciidoc"),
Path("tests/data/test_01.asciidoc"),
]

2
docs/examples/tesseract_lang_detection.py
View File

@ -10,7 +10,7 @@ from docling.document_converter import DocumentConverter, PdfFormatOption
def main():
input_doc = Path("./tests/data/2206.01062.pdf")
input_doc = Path("./tests/data/pdf/2206.01062.pdf")
# Set lang=["auto"] with a tesseract OCR engine: TesseractOcrOptions, TesseractCliOcrOptions
# ocr_options = TesseractOcrOptions(lang=["auto"])