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

@@ -1,12 +1,17 @@
import logging
from typing import Iterable
from pathlib import Path
from typing import Iterable, Optional, Type
from docling_core.types.doc import BoundingBox, CoordOrigin
from docling_core.types.doc.page import BoundingRectangle, TextCell
from docling.datamodel.base_models import Page
from docling.datamodel.document import ConversionResult
from docling.datamodel.pipeline_options import TesseractOcrOptions
from docling.datamodel.pipeline_options import (
AcceleratorOptions,
OcrOptions,
TesseractOcrOptions,
)
from docling.datamodel.settings import settings
from docling.models.base_ocr_model import BaseOcrModel
from docling.utils.ocr_utils import map_tesseract_script
@@ -16,8 +21,19 @@ _log = logging.getLogger(__name__)
class TesseractOcrModel(BaseOcrModel):
def __init__(self, enabled: bool, options: TesseractOcrOptions):
super().__init__(enabled=enabled, options=options)
def __init__(
self,
enabled: bool,
artifacts_path: Optional[Path],
options: TesseractOcrOptions,
accelerator_options: AcceleratorOptions,
):
super().__init__(
enabled=enabled,
artifacts_path=artifacts_path,
options=options,
accelerator_options=accelerator_options,
)
self.options: TesseractOcrOptions
self.scale = 3 # multiplier for 72 dpi == 216 dpi.
@@ -200,3 +216,7 @@ class TesseractOcrModel(BaseOcrModel):
self.draw_ocr_rects_and_cells(conv_res, page, ocr_rects)
yield page
@classmethod
def get_options_type(cls) -> Type[OcrOptions]:
return TesseractOcrOptions