feat: add factory for ocr engines via plugins (#1010)

* add factory for ocr engines

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

* apply pre-commit after rebase

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

* add picture description factory

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

* fix enable option

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

* switch to create methods

Signed-off-by: Panos Vagenas <pva@zurich.ibm.com>

* make `options` an explicit kwarg

Signed-off-by: Panos Vagenas <pva@zurich.ibm.com>

* keep old lock of docling-core

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

* fix lock

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

* add allow_external_plugins option

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

* add factory return and ignore options type

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

---------

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Signed-off-by: Panos Vagenas <pva@zurich.ibm.com>
Co-authored-by: Panos Vagenas <pva@zurich.ibm.com>
This commit is contained in:
Michele Dolfi
2025-03-18 13:58:05 +01:00
committed by GitHub
parent 3960b199d6
commit 6eaae3cba0
21 changed files with 485 additions and 158 deletions

View File

@@ -10,16 +10,7 @@ from docling.backend.abstract_backend import AbstractDocumentBackend
from docling.backend.pdf_backend import PdfDocumentBackend
from docling.datamodel.base_models import AssembledUnit, Page
from docling.datamodel.document import ConversionResult
from docling.datamodel.pipeline_options import (
EasyOcrOptions,
OcrMacOptions,
PdfPipelineOptions,
PictureDescriptionApiOptions,
PictureDescriptionVlmOptions,
RapidOcrOptions,
TesseractCliOcrOptions,
TesseractOcrOptions,
)
from docling.datamodel.pipeline_options import PdfPipelineOptions
from docling.datamodel.settings import settings
from docling.models.base_ocr_model import BaseOcrModel
from docling.models.code_formula_model import CodeFormulaModel, CodeFormulaModelOptions
@@ -27,22 +18,16 @@ from docling.models.document_picture_classifier import (
DocumentPictureClassifier,
DocumentPictureClassifierOptions,
)
from docling.models.easyocr_model import EasyOcrModel
from docling.models.factories import get_ocr_factory, get_picture_description_factory
from docling.models.layout_model import LayoutModel
from docling.models.ocr_mac_model import OcrMacModel
from docling.models.page_assemble_model import PageAssembleModel, PageAssembleOptions
from docling.models.page_preprocessing_model import (
PagePreprocessingModel,
PagePreprocessingOptions,
)
from docling.models.picture_description_api_model import PictureDescriptionApiModel
from docling.models.picture_description_base_model import PictureDescriptionBaseModel
from docling.models.picture_description_vlm_model import PictureDescriptionVlmModel
from docling.models.rapid_ocr_model import RapidOcrModel
from docling.models.readingorder_model import ReadingOrderModel, ReadingOrderOptions
from docling.models.table_structure_model import TableStructureModel
from docling.models.tesseract_ocr_cli_model import TesseractOcrCliModel
from docling.models.tesseract_ocr_model import TesseractOcrModel
from docling.pipeline.base_pipeline import PaginatedPipeline
from docling.utils.model_downloader import download_models
from docling.utils.profiling import ProfilingScope, TimeRecorder
@@ -78,10 +63,7 @@ class StandardPdfPipeline(PaginatedPipeline):
self.glm_model = ReadingOrderModel(options=ReadingOrderOptions())
if (ocr_model := self.get_ocr_model(artifacts_path=artifacts_path)) is None:
raise RuntimeError(
f"The specified OCR kind is not supported: {pipeline_options.ocr_options.kind}."
)
ocr_model = self.get_ocr_model(artifacts_path=artifacts_path)
self.build_pipe = [
# Pre-processing
@@ -164,66 +146,30 @@ class StandardPdfPipeline(PaginatedPipeline):
output_dir = download_models(output_dir=local_dir, force=force, progress=False)
return output_dir
def get_ocr_model(
self, artifacts_path: Optional[Path] = None
) -> Optional[BaseOcrModel]:
if isinstance(self.pipeline_options.ocr_options, EasyOcrOptions):
return EasyOcrModel(
enabled=self.pipeline_options.do_ocr,
artifacts_path=artifacts_path,
options=self.pipeline_options.ocr_options,
accelerator_options=self.pipeline_options.accelerator_options,
)
elif isinstance(self.pipeline_options.ocr_options, TesseractCliOcrOptions):
return TesseractOcrCliModel(
enabled=self.pipeline_options.do_ocr,
options=self.pipeline_options.ocr_options,
)
elif isinstance(self.pipeline_options.ocr_options, TesseractOcrOptions):
return TesseractOcrModel(
enabled=self.pipeline_options.do_ocr,
options=self.pipeline_options.ocr_options,
)
elif isinstance(self.pipeline_options.ocr_options, RapidOcrOptions):
return RapidOcrModel(
enabled=self.pipeline_options.do_ocr,
options=self.pipeline_options.ocr_options,
accelerator_options=self.pipeline_options.accelerator_options,
)
elif isinstance(self.pipeline_options.ocr_options, OcrMacOptions):
if "darwin" != sys.platform:
raise RuntimeError(
f"The specified OCR type is only supported on Mac: {self.pipeline_options.ocr_options.kind}."
)
return OcrMacModel(
enabled=self.pipeline_options.do_ocr,
options=self.pipeline_options.ocr_options,
)
return None
def get_ocr_model(self, artifacts_path: Optional[Path] = None) -> BaseOcrModel:
factory = get_ocr_factory(
allow_external_plugins=self.pipeline_options.allow_external_plugins
)
return factory.create_instance(
options=self.pipeline_options.ocr_options,
enabled=self.pipeline_options.do_ocr,
artifacts_path=artifacts_path,
accelerator_options=self.pipeline_options.accelerator_options,
)
def get_picture_description_model(
self, artifacts_path: Optional[Path] = None
) -> Optional[PictureDescriptionBaseModel]:
if isinstance(
self.pipeline_options.picture_description_options,
PictureDescriptionApiOptions,
):
return PictureDescriptionApiModel(
enabled=self.pipeline_options.do_picture_description,
enable_remote_services=self.pipeline_options.enable_remote_services,
options=self.pipeline_options.picture_description_options,
)
elif isinstance(
self.pipeline_options.picture_description_options,
PictureDescriptionVlmOptions,
):
return PictureDescriptionVlmModel(
enabled=self.pipeline_options.do_picture_description,
artifacts_path=artifacts_path,
options=self.pipeline_options.picture_description_options,
accelerator_options=self.pipeline_options.accelerator_options,
)
return None
factory = get_picture_description_factory(
allow_external_plugins=self.pipeline_options.allow_external_plugins
)
return factory.create_instance(
options=self.pipeline_options.picture_description_options,
enabled=self.pipeline_options.do_picture_description,
enable_remote_services=self.pipeline_options.enable_remote_services,
artifacts_path=artifacts_path,
accelerator_options=self.pipeline_options.accelerator_options,
)
def initialize_page(self, conv_res: ConversionResult, page: Page) -> Page:
with TimeRecorder(conv_res, "page_init"):