mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-27 04:24:45 +00:00
Code Issues Packages Projects Releases Wiki Activity

keep only one example

Browse Source 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
This commit is contained in:
Michele Dolfi 2024-10-08 18:36:53 +02:00
parent bb8cd0f7fc
commit 800b16beff
1 changed files with 10 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
examples/custom_convert.py
View File

@ -125,19 +125,19 @@ def main():
# Docling Parse with Tesseract
# ----------------------
pipeline_options = PipelineOptions()
pipeline_options.do_ocr = True
pipeline_options.do_table_structure = True
pipeline_options.table_structure_options.do_cell_matching = True
pipeline_options.ocr_options = TesseractOcrOptions()
# pipeline_options = PipelineOptions()
# pipeline_options.do_ocr = True
# pipeline_options.do_table_structure = True
# pipeline_options.table_structure_options.do_cell_matching = True
# pipeline_options.ocr_options = TesseractOcrOptions()
# Docling Parse with Tesseract CLI
# ----------------------
pipeline_options = PipelineOptions()
pipeline_options.do_ocr = True
pipeline_options.do_table_structure = True
pipeline_options.table_structure_options.do_cell_matching = True
pipeline_options.ocr_options = TesseractCliOcrOptions()
# pipeline_options = PipelineOptions()
# pipeline_options.do_ocr = True
# pipeline_options.do_table_structure = True
# pipeline_options.table_structure_options.do_cell_matching = True
# pipeline_options.ocr_options = TesseractCliOcrOptions()
doc_converter = DocumentConverter(
pipeline_options=pipeline_options,