mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-26 20:14:47 +00:00
Code Issues Packages Projects Releases Wiki Activity

make the example files location more generic

Browse Source 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
This commit is contained in:
Michele Dolfi 2025-05-14 09:51:00 +02:00
parent 4378be1480
commit d5d42ed4ed
13 changed files with 17 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
docs/examples/batch_convert.py
View File

@ -122,10 +122,10 @@ def main():
logging.basicConfig(level=logging.INFO)
input_doc_paths = [
Path("../../tests/data/pdf/2206.01062.pdf"),
Path("../../tests/data/pdf/2203.01017v2.pdf"),
Path("../../tests/data/pdf/2305.03393v1.pdf"),
Path("../../tests/data/pdf/redp5110_sampled.pdf"),
Path(__file__) / "../../tests/data/pdf/2206.01062.pdf",
Path(__file__) / "../../tests/data/pdf/2203.01017v2.pdf",
Path(__file__) / "../../tests/data/pdf/2305.03393v1.pdf",
Path(__file__) / "../../tests/data/pdf/redp5110_sampled.pdf",
]
# buf = BytesIO(Path("./test/data/2206.01062.pdf").open("rb").read())

2
docs/examples/custom_convert.py
View File

@ -17,7 +17,7 @@ _log = logging.getLogger(__name__)
def main():
logging.basicConfig(level=logging.INFO)
input_doc_path = Path("../../tests/data/pdf/2206.01062.pdf")
input_doc_path = Path(__file__) / "../../tests/data/pdf/2206.01062.pdf"
###########################################################################

2
docs/examples/develop_formula_understanding.py
View File

@ -71,7 +71,7 @@ class ExampleFormulaUnderstandingPipeline(StandardPdfPipeline):
def main():
logging.basicConfig(level=logging.INFO)
input_doc_path = Path("../../tests/data/pdf/2203.01017v2.pdf")
input_doc_path = Path(__file__) / "../../tests/data/pdf/2203.01017v2.pdf"
pipeline_options = ExampleFormulaUnderstandingPipelineOptions()
pipeline_options.do_formula_understanding = True

2
docs/examples/develop_picture_enrichment.py
View File

@ -76,7 +76,7 @@ class ExamplePictureClassifierPipeline(StandardPdfPipeline):
def main():
logging.basicConfig(level=logging.INFO)
input_doc_path = Path("../../tests/data/pdf/2206.01062.pdf")
input_doc_path = Path(__file__) / "../../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/pdf/2206.01062.pdf")
input_doc_path = Path(__file__) / "../../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/pdf/2206.01062.pdf")
input_doc_path = Path(__file__) / "../../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/pdf/2206.01062.pdf")
input_doc_path = Path(__file__) / "../../tests/data/pdf/2206.01062.pdf"
output_dir = Path("scratch")
doc_converter = DocumentConverter()

2
docs/examples/full_page_ocr.py
View File

@ -9,7 +9,7 @@ from docling.document_converter import DocumentConverter, PdfFormatOption
def main():
input_doc = Path("../../tests/data/pdf/2206.01062.pdf")
input_doc = Path(__file__) / "../../tests/data/pdf/2206.01062.pdf"
pipeline_options = PdfPipelineOptions()
pipeline_options.do_ocr = True

2
docs/examples/pictures_description_api.py
View File

@ -67,7 +67,7 @@ def watsonx_vlm_options():
def main():
logging.basicConfig(level=logging.INFO)
input_doc_path = Path("../../tests/data/pdf/2206.01062.pdf")
input_doc_path = Path(__file__) / "../../tests/data/pdf/2206.01062.pdf"
pipeline_options = PdfPipelineOptions(
enable_remote_services=True # <-- this is required!

2
docs/examples/run_with_accelerator.py
View File

@ -11,7 +11,7 @@ from docling.document_converter import DocumentConverter, PdfFormatOption
def main():
input_doc = Path("../../tests/data/pdf/2206.01062.pdf")
input_doc = Path(__file__) / "../../tests/data/pdf/2206.01062.pdf"
# Explicitly set the accelerator
# accelerator_options = AcceleratorOptions(

2
docs/examples/tesseract_lang_detection.py
View File

@ -9,7 +9,7 @@ from docling.document_converter import DocumentConverter, PdfFormatOption
def main():
input_doc = Path("../../tests/data/pdf/2206.01062.pdf")
input_doc = Path(__file__) / "../../tests/data/pdf/2206.01062.pdf"
# Set lang=["auto"] with a tesseract OCR engine: TesseractOcrOptions, TesseractCliOcrOptions
# ocr_options = TesseractOcrOptions(lang=["auto"])

2
docs/examples/translate.py
View File

@ -31,7 +31,7 @@ def translate(text: str, src: str = "en", dest: str = "de"):
def main():
logging.basicConfig(level=logging.INFO)
input_doc_path = Path("../../tests/data/pdf/2206.01062.pdf")
input_doc_path = Path(__file__) / "../../tests/data/pdf/2206.01062.pdf"
output_dir = Path("scratch")
# Important: For operating with page images, we must keep them, otherwise the DocumentConverter

4
docs/examples/vlm_pipeline_api_model.py
View File

@ -69,8 +69,8 @@ def watsonx_vlm_options(model: str, prompt: str):
def main():
logging.basicConfig(level=logging.INFO)
# input_doc_path = Path("../../tests/data/pdf/2206.01062.pdf")
input_doc_path = Path("../../tests/data/pdf/2305.03393v1-pg9.pdf")
# input_doc_path = Path(__file__) / "../../tests/data/pdf/2206.01062.pdf"
input_doc_path = Path(__file__) / "../../tests/data/pdf/2305.03393v1-pg9.pdf"
pipeline_options = VlmPipelineOptions(
enable_remote_services=True # <-- this is required!