docs: Add example for inspection of picture content (#624)

* chore: Add example for inspection of picture content

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* fix: Test case re-generation

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* fix: Test case re-generation only on CPU

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* fix: Add missing GT files

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

---------

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
This commit is contained in:
Christoph Auer
2025-01-29 10:39:00 +01:00
committed by GitHub
parent 4d11d87d06
commit f9144f2bb6
34 changed files with 171 additions and 23 deletions

View File

@@ -3,7 +3,7 @@ from pathlib import Path
from docling.backend.docling_parse_backend import DoclingParseDocumentBackend
from docling.datamodel.base_models import InputFormat
from docling.datamodel.document import ConversionResult
from docling.datamodel.pipeline_options import PdfPipelineOptions
from docling.datamodel.pipeline_options import AcceleratorDevice, PdfPipelineOptions
from docling.document_converter import DocumentConverter, PdfFormatOption
from .verify_utils import verify_conversion_result_v1, verify_conversion_result_v2
@@ -28,6 +28,7 @@ def get_converter():
pipeline_options.do_ocr = False
pipeline_options.do_table_structure = True
pipeline_options.table_structure_options.do_cell_matching = True
pipeline_options.accelerator_options.device = AcceleratorDevice.CPU
converter = DocumentConverter(
format_options={