Files
Docling/docling/models/factories/__init__.py
Michele Dolfi 6eaae3cba0 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>
2025-03-18 13:58:05 +01:00

28 lines
872 B
Python

import logging
from functools import lru_cache
from docling.models.factories.ocr_factory import OcrFactory
from docling.models.factories.picture_description_factory import (
PictureDescriptionFactory,
)
logger = logging.getLogger(__name__)
@lru_cache()
def get_ocr_factory(allow_external_plugins: bool = False) -> OcrFactory:
factory = OcrFactory()
factory.load_from_plugins(allow_external_plugins=allow_external_plugins)
logger.info("Registered ocr engines: %r", factory.registered_kind)
return factory
@lru_cache()
def get_picture_description_factory(
allow_external_plugins: bool = False,
) -> PictureDescriptionFactory:
factory = PictureDescriptionFactory()
factory.load_from_plugins(allow_external_plugins=allow_external_plugins)
logger.info("Registered picture descriptions: %r", factory.registered_kind)
return factory