mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-08 20:58:11 +00:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source 
* 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
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/test_e2e_ocr_conversion.py
View File

@@ -6,6 +6,7 @@ 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 (
AcceleratorDevice,
EasyOcrOptions,
OcrMacOptions,
OcrOptions,
@@ -37,6 +38,7 @@ def get_converter(ocr_options: OcrOptions):
pipeline_options.do_table_structure = True
pipeline_options.table_structure_options.do_cell_matching = True
pipeline_options.ocr_options = ocr_options
pipeline_options.accelerator_options.device = AcceleratorDevice.CPU
converter = DocumentConverter(
format_options={