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

support running examples from root or subfolder

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

docs/examples/batch_convert.py

@@ -121,14 +121,15 @@ def export_documents(
 def main():
     logging.basicConfig(level=logging.INFO)
 
+    data_folder = Path(__file__).parent / "../../tests/data"
     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"),
+        data_folder / "pdf/2206.01062.pdf",
+        data_folder / "pdf/2203.01017v2.pdf",
+        data_folder / "pdf/2305.03393v1.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)]
     # input = DocumentConversionInput.from_streams(docs)
 

docs/examples/custom_convert.py

@@ -16,7 +16,8 @@ _log = logging.getLogger(__name__)
 def main():
     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"
 
     ###########################################################################
 

docs/examples/develop_formula_understanding.py

@@ -71,7 +71,8 @@ class ExampleFormulaUnderstandingPipeline(StandardPdfPipeline):
 def main():
     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.do_formula_understanding = True

docs/examples/develop_picture_enrichment.py

@@ -76,7 +76,8 @@ class ExamplePictureClassifierPipeline(StandardPdfPipeline):
 def main():
     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.images_scale = 2.0

docs/examples/export_figures.py

@@ -16,7 +16,8 @@ IMAGE_RESOLUTION_SCALE = 2.0
 def main():
     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")
 
     # Important: For operating with page images, we must keep them, otherwise the DocumentConverter

docs/examples/export_multimodal.py

@@ -19,7 +19,8 @@ IMAGE_RESOLUTION_SCALE = 2.0
 def main():
     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")
 
     # Important: For operating with page images, we must keep them, otherwise the DocumentConverter

docs/examples/export_tables.py

@@ -12,7 +12,8 @@ _log = logging.getLogger(__name__)
 def main():
     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")
 
     doc_converter = DocumentConverter()

docs/examples/full_page_ocr.py

@@ -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"
 
     pipeline_options = PdfPipelineOptions()
     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()
     print(md)
 

docs/examples/pictures_description_api.py

@@ -96,7 +96,8 @@ def watsonx_vlm_options():
 def main():
     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(
         enable_remote_services=True  # <-- this is required!

docs/examples/run_with_accelerator.py

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

docs/examples/tesseract_lang_detection.py

@@ -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)
 

docs/examples/translate.py

@@ -30,7 +30,8 @@ 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")
+    data_folder = Path(__file__).parent / "../../tests/data"
+    input_doc_path = data_folder / "pdf/2206.01062.pdf"
     output_dir = Path("scratch")
 
     # Important: For operating with page images, we must keep them, otherwise the DocumentConverter

docs/examples/vlm_pipeline_api_model.py

@@ -95,8 +95,8 @@ 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")
+    data_folder = Path(__file__).parent / "../../tests/data"
+    input_doc_path = data_folder / "pdf/2305.03393v1-pg9.pdf"
 
     pipeline_options = VlmPipelineOptions(
         enable_remote_services=True  # <-- this is required!