NeoAnd/Docling
1
0
Fork 0
Code Issues Pull Requests Actions 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
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
13 changed files with 33 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
docs/examples/batch_convert.py vendored
View File

@ -121,14 +121,15 @@ def export_documents(
def main(): def main():
logging.basicConfig(level=logging.INFO) logging.basicConfig(level=logging.INFO)
data_folder = Path(__file__).parent / "../../tests/data"
input_doc_paths = [ input_doc_paths = [
Path("./tests/data/pdf/2206.01062.pdf"), data_folder / "pdf/2206.01062.pdf",
Path("./tests/data/pdf/2203.01017v2.pdf"), data_folder / "pdf/2203.01017v2.pdf",
Path("./tests/data/pdf/2305.03393v1.pdf"), data_folder / "pdf/2305.03393v1.pdf",
Path("./tests/data/pdf/redp5110_sampled.pdf"), data_folder / "pdf/redp5110_sampled.pdf",
] ]
# buf = BytesIO(Path("./test/data/2206.01062.pdf").open("rb").read()) # buf = BytesIO((data_folder / "pdf/2206.01062.pdf").open("rb").read())
# docs = [DocumentStream(name="my_doc.pdf", stream=buf)] # docs = [DocumentStream(name="my_doc.pdf", stream=buf)]
# input = DocumentConversionInput.from_streams(docs) # input = DocumentConversionInput.from_streams(docs)

3
docs/examples/custom_convert.py vendored
View File

@ -16,7 +16,8 @@ _log = logging.getLogger(__name__)
def main(): def main():
logging.basicConfig(level=logging.INFO) logging.basicConfig(level=logging.INFO)
input_doc_path = Path("./tests/data/pdf/2206.01062.pdf") data_folder = Path(__file__).parent / "../../tests/data"
input_doc_path = data_folder / "pdf/2206.01062.pdf"
########################################################################### ###########################################################################

3
docs/examples/develop_formula_understanding.py vendored
View File

@ -71,7 +71,8 @@ class ExampleFormulaUnderstandingPipeline(StandardPdfPipeline):
def main(): def main():
logging.basicConfig(level=logging.INFO) logging.basicConfig(level=logging.INFO)
input_doc_path = Path("./tests/data/pdf/2203.01017v2.pdf") data_folder = Path(__file__).parent / "../../tests/data"
input_doc_path = data_folder / "pdf/2203.01017v2.pdf"
pipeline_options = ExampleFormulaUnderstandingPipelineOptions() pipeline_options = ExampleFormulaUnderstandingPipelineOptions()
pipeline_options.do_formula_understanding = True pipeline_options.do_formula_understanding = True

3
docs/examples/develop_picture_enrichment.py vendored
View File

@ -76,7 +76,8 @@ class ExamplePictureClassifierPipeline(StandardPdfPipeline):
def main(): def main():
logging.basicConfig(level=logging.INFO) logging.basicConfig(level=logging.INFO)
input_doc_path = Path("./tests/data/pdf/2206.01062.pdf") data_folder = Path(__file__).parent / "../../tests/data"
input_doc_path = data_folder / "pdf/2206.01062.pdf"
pipeline_options = ExamplePictureClassifierPipelineOptions() pipeline_options = ExamplePictureClassifierPipelineOptions()
pipeline_options.images_scale = 2.0 pipeline_options.images_scale = 2.0

3
docs/examples/export_figures.py vendored
View File

@ -16,7 +16,8 @@ IMAGE_RESOLUTION_SCALE = 2.0
def main(): def main():
logging.basicConfig(level=logging.INFO) logging.basicConfig(level=logging.INFO)
input_doc_path = Path("./tests/data/pdf/2206.01062.pdf") data_folder = Path(__file__).parent / "../../tests/data"
input_doc_path = data_folder / "pdf/2206.01062.pdf"
output_dir = Path("scratch") output_dir = Path("scratch")
# Important: For operating with page images, we must keep them, otherwise the DocumentConverter # Important: For operating with page images, we must keep them, otherwise the DocumentConverter

3
docs/examples/export_multimodal.py vendored
View File

@ -19,7 +19,8 @@ IMAGE_RESOLUTION_SCALE = 2.0
def main(): def main():
logging.basicConfig(level=logging.INFO) logging.basicConfig(level=logging.INFO)
input_doc_path = Path("./tests/data/pdf/2206.01062.pdf") data_folder = Path(__file__).parent / "../../tests/data"
input_doc_path = data_folder / "pdf/2206.01062.pdf"
output_dir = Path("scratch") output_dir = Path("scratch")
# Important: For operating with page images, we must keep them, otherwise the DocumentConverter # Important: For operating with page images, we must keep them, otherwise the DocumentConverter

3
docs/examples/export_tables.py vendored
View File

@ -12,7 +12,8 @@ _log = logging.getLogger(__name__)
def main(): def main():
logging.basicConfig(level=logging.INFO) logging.basicConfig(level=logging.INFO)
input_doc_path = Path("./tests/data/pdf/2206.01062.pdf") data_folder = Path(__file__).parent / "../../tests/data"
input_doc_path = data_folder / "pdf/2206.01062.pdf"
output_dir = Path("scratch") output_dir = Path("scratch")
doc_converter = DocumentConverter() doc_converter = DocumentConverter()

5
docs/examples/full_page_ocr.py vendored
View File

@ -9,7 +9,8 @@ from docling.document_converter import DocumentConverter, PdfFormatOption
def main(): 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"
pipeline_options = PdfPipelineOptions() pipeline_options = PdfPipelineOptions()
pipeline_options.do_ocr = True pipeline_options.do_ocr = True
@ -32,7 +33,7 @@ def main():
} }
) )
doc = converter.convert(input_doc).document doc = converter.convert(input_doc_path).document
md = doc.export_to_markdown() md = doc.export_to_markdown()
print(md) print(md)

3
docs/examples/pictures_description_api.py vendored
View File

@ -96,7 +96,8 @@ def watsonx_vlm_options():
def main(): def main():
logging.basicConfig(level=logging.INFO) logging.basicConfig(level=logging.INFO)
input_doc_path = Path("./tests/data/pdf/2206.01062.pdf") data_folder = Path(__file__).parent / "../../tests/data"
input_doc_path = data_folder / "pdf/2206.01062.pdf"
pipeline_options = PdfPipelineOptions( pipeline_options = PdfPipelineOptions(
enable_remote_services=True # <-- this is required! enable_remote_services=True # <-- this is required!

5
docs/examples/run_with_accelerator.py vendored
View File

@ -10,7 +10,8 @@ from docling.document_converter import DocumentConverter, PdfFormatOption
def main(): 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"
# Explicitly set the accelerator # Explicitly set the accelerator
# accelerator_options = AcceleratorOptions( # accelerator_options = AcceleratorOptions(
@ -47,7 +48,7 @@ def main():
settings.debug.profile_pipeline_timings = True settings.debug.profile_pipeline_timings = True
# Convert the document # Convert the document
conversion_result = converter.convert(input_doc) conversion_result = converter.convert(input_doc_path)
doc = conversion_result.document doc = conversion_result.document
# List with total time per document # List with total time per document

5
docs/examples/tesseract_lang_detection.py vendored
View File

@ -9,7 +9,8 @@ from docling.document_converter import DocumentConverter, PdfFormatOption
def main(): 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 # Set lang=["auto"] with a tesseract OCR engine: TesseractOcrOptions, TesseractCliOcrOptions
# ocr_options = TesseractOcrOptions(lang=["auto"]) # 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() md = doc.export_to_markdown()
print(md) print(md)

3
docs/examples/translate.py vendored
View File

@ -30,7 +30,8 @@ def translate(text: str, src: str = "en", dest: str = "de"):
def main(): def main():
logging.basicConfig(level=logging.INFO) logging.basicConfig(level=logging.INFO)
input_doc_path = Path("./tests/data/pdf/2206.01062.pdf") data_folder = Path(__file__).parent / "../../tests/data"
input_doc_path = data_folder / "pdf/2206.01062.pdf"
output_dir = Path("scratch") output_dir = Path("scratch")
# Important: For operating with page images, we must keep them, otherwise the DocumentConverter # Important: For operating with page images, we must keep them, otherwise the DocumentConverter

4
docs/examples/vlm_pipeline_api_model.py vendored
View File

@ -95,8 +95,8 @@ def watsonx_vlm_options(model: str, prompt: str):
def main(): def main():
logging.basicConfig(level=logging.INFO) logging.basicConfig(level=logging.INFO)
# input_doc_path = Path("./tests/data/pdf/2206.01062.pdf") data_folder = Path(__file__).parent / "../../tests/data"
input_doc_path = Path("./tests/data/pdf/2305.03393v1-pg9.pdf") input_doc_path = data_folder / "pdf/2305.03393v1-pg9.pdf"
pipeline_options = VlmPipelineOptions( pipeline_options = VlmPipelineOptions(
enable_remote_services=True # <-- this is required! enable_remote_services=True # <-- this is required!