mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-30 22:14:37 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs: update examples and installation for ocrmac support

Browse Source 
- Added `OcrMacOptions` to `custom_convert.py` and `full_page_ocr.py` examples.
- Included usage comments and examples for `OcrMacOptions` in OCR pipelines.
- Updated installation guide to include instructions for installing `ocrmac`, noting macOS version requirements (10.15+).
- Highlighted that `ocrmac` leverages Apple's Vision framework as an OCR backend.

This enhances documentation for users working on macOS to leverage `ocrmac` effectively.

Signed-off-by: Suhwan Seo <nuridol@gmail.com>
This commit is contained in:
Suhwan Seo 2024-11-20 17:31:57 +09:00
parent 0c23b69433
commit 2576e65753
3 changed files with 29 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
docs/examples/custom_convert.py
View File

@ -7,6 +7,7 @@ from docling.backend.pypdfium2_backend import PyPdfiumDocumentBackend
from docling.datamodel.base_models import InputFormat
from docling.datamodel.pipeline_options import PdfPipelineOptions
from docling.document_converter import DocumentConverter, PdfFormatOption
from docling.models.ocr_mac_model import OcrMacOptions
from docling.models.tesseract_ocr_cli_model import TesseractCliOcrOptions
from docling.models.tesseract_ocr_model import TesseractOcrOptions
@ -122,6 +123,20 @@ def main():
# }
# )
# Docling Parse with ocrmac(Mac only)
# ----------------------
# pipeline_options = PdfPipelineOptions()
# pipeline_options.do_ocr = True
# pipeline_options.do_table_structure = True
# pipeline_options.table_structure_options.do_cell_matching = True
# pipeline_options.ocr_options = OcrMacOptions()
# doc_converter = DocumentConverter(
# format_options={
# InputFormat.PDF: PdfFormatOption(pipeline_options=pipeline_options)
# }
# )
###########################################################################
start_time = time.time()

4
docs/examples/full_page_ocr.py
View File

@ -4,6 +4,7 @@ from docling.backend.docling_parse_backend import DoclingParseDocumentBackend
from docling.datamodel.base_models import InputFormat
from docling.datamodel.pipeline_options import (
EasyOcrOptions,
OcrMacOptions,
PdfPipelineOptions,
TesseractCliOcrOptions,
TesseractOcrOptions,
@ -19,9 +20,10 @@ def main():
pipeline_options.do_table_structure = True
pipeline_options.table_structure_options.do_cell_matching = True
# Any of the OCR options can be used:EasyOcrOptions, TesseractOcrOptions, TesseractCliOcrOptions
# Any of the OCR options can be used:EasyOcrOptions, TesseractOcrOptions, TesseractCliOcrOptions, OcrMacOptions(Mac only)
# ocr_options = EasyOcrOptions(force_full_page_ocr=True)
# ocr_options = TesseractOcrOptions(force_full_page_ocr=True)
# ocr_options = OcrMacOptions(force_full_page_ocr=True)
ocr_options = TesseractCliOcrOptions(force_full_page_ocr=True)
pipeline_options.ocr_options = ocr_options

11
docs/installation.md
View File

@ -92,6 +92,17 @@ Works on macOS, Linux, and Windows, with support for both x86_64 and arm64 archi
pip install --no-binary :all: tesserocr
```
<h3>ocrmac installation</h3>
[ocrmac](https://github.com/straussmaximilian/ocrmac) is using
Apple's vision(or livetext) framework as OCR backend.
For using this engine with Docling, ocrmac must be installed on your system.
This only works on macOS systems with newer macOS versions (10.15+).
```console
pip install ocrmac
```
## Development setup
To develop Docling features, bugfixes etc., install as follows from your local clone's root dir: