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>

docling/models/plugins/defaults.py

@@ -0,0 +1,28 @@
+from docling.models.easyocr_model import EasyOcrModel
+from docling.models.ocr_mac_model import OcrMacModel
+from docling.models.picture_description_api_model import PictureDescriptionApiModel
+from docling.models.picture_description_vlm_model import PictureDescriptionVlmModel
+from docling.models.rapid_ocr_model import RapidOcrModel
+from docling.models.tesseract_ocr_cli_model import TesseractOcrCliModel
+from docling.models.tesseract_ocr_model import TesseractOcrModel
+
+
+def ocr_engines():
+    return {
+        "ocr_engines": [
+            EasyOcrModel,
+            OcrMacModel,
+            RapidOcrModel,
+            TesseractOcrModel,
+            TesseractOcrCliModel,
+        ]
+    }
+
+
+def picture_description():
+    return {
+        "picture_description": [
+            PictureDescriptionVlmModel,
+            PictureDescriptionApiModel,
+        ]
+    }