use granite-docling and add to the model downloader

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

docling/cli/main.py

@@ -336,7 +336,7 @@ def convert(  # noqa: C901
     vlm_model: Annotated[
         VlmModelType,
         typer.Option(..., help="Choose the VLM model to use with PDF or image files."),
-    ] = VlmModelType.SMOLDOCLING,
+    ] = VlmModelType.GRANITEDOCLING,
     asr_model: Annotated[
         AsrModelType,
         typer.Option(..., help="Choose the ASR model to use with audio/video files."),

docling/cli/models.py

@@ -33,6 +33,8 @@ class _AvailableModels(str, Enum):
     CODE_FORMULA = "code_formula"
     PICTURE_CLASSIFIER = "picture_classifier"
     SMOLVLM = "smolvlm"
+    GRANITEDOCLING = "granitedocling"
+    GRANITEDOCLING_MLX = "granitedocling_mlx"
     SMOLDOCLING = "smoldocling"
     SMOLDOCLING_MLX = "smoldocling_mlx"
     GRANITE_VISION = "granite_vision"
@@ -108,6 +110,8 @@ def download(
         with_code_formula=_AvailableModels.CODE_FORMULA in to_download,
         with_picture_classifier=_AvailableModels.PICTURE_CLASSIFIER in to_download,
         with_smolvlm=_AvailableModels.SMOLVLM in to_download,
+        with_granitedocling=_AvailableModels.GRANITEDOCLING in to_download,
+        with_granitedocling_mlx=_AvailableModels.GRANITEDOCLING_MLX in to_download,
         with_smoldocling=_AvailableModels.SMOLDOCLING in to_download,
         with_smoldocling_mlx=_AvailableModels.SMOLDOCLING_MLX in to_download,
         with_granite_vision=_AvailableModels.GRANITE_VISION in to_download,

docling/datamodel/pipeline_options.py

@@ -12,7 +12,7 @@ from pydantic import (
 )
 from typing_extensions import deprecated
 
-from docling.datamodel import asr_model_specs
+from docling.datamodel import asr_model_specs, vlm_model_specs
 
 # Import the following for backwards compatibility
 from docling.datamodel.accelerator_options import AcceleratorDevice, AcceleratorOptions
@@ -286,7 +286,7 @@ class VlmPipelineOptions(PaginatedPipelineOptions):
     )
     # If True, text from backend will be used instead of generated text
     vlm_options: Union[InlineVlmOptions, ApiVlmOptions] = (
-        smoldocling_vlm_conversion_options
+        vlm_model_specs.GRANITEDOCLING_TRANSFORMERS
     )
 
 

docling/utils/model_downloader.py

@@ -10,6 +10,8 @@ from docling.datamodel.pipeline_options import (
 )
 from docling.datamodel.settings import settings
 from docling.datamodel.vlm_model_specs import (
+    GRANITEDOCLING_MLX,
+    GRANITEDOCLING_TRANSFORMERS,
     SMOLDOCLING_MLX,
     SMOLDOCLING_TRANSFORMERS,
 )
@@ -34,6 +36,8 @@ def download_models(
     with_code_formula: bool = True,
     with_picture_classifier: bool = True,
     with_smolvlm: bool = False,
+    with_granitedocling: bool = False,
+    with_granitedocling_mlx: bool = False,
     with_smoldocling: bool = False,
     with_smoldocling_mlx: bool = False,
     with_granite_vision: bool = False,
@@ -86,6 +90,24 @@ def download_models(
             progress=progress,
         )
 
+    if with_granitedocling:
+        _log.info("Downloading GraniteDocling model...")
+        download_hf_model(
+            repo_id=GRANITEDOCLING_TRANSFORMERS.repo_id,
+            local_dir=output_dir / GRANITEDOCLING_TRANSFORMERS.repo_cache_folder,
+            force=force,
+            progress=progress,
+        )
+
+    if with_granitedocling_mlx:
+        _log.info("Downloading GraniteDocling MLX model...")
+        download_hf_model(
+            repo_id=GRANITEDOCLING_MLX.repo_id,
+            local_dir=output_dir / GRANITEDOCLING_MLX.repo_cache_folder,
+            force=force,
+            progress=progress,
+        )
+
     if with_smoldocling:
         _log.info("Downloading SmolDocling model...")
         download_hf_model(