From 127e38646fd7f23fcda0e392e756fe27f123bd78 Mon Sep 17 00:00:00 2001
From: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com>
Date: Mon, 12 May 2025 10:48:07 +0200
Subject: [PATCH] fix: add smoldocling in download utils (#1577)

add smoldocling in download utils

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
---
 docling/cli/models.py             |  4 ++++
 docling/utils/model_downloader.py | 24 ++++++++++++++++++++++++
 2 files changed, 28 insertions(+)

diff --git a/docling/cli/models.py b/docling/cli/models.py
index 982bbdd..4632053 100644
--- a/docling/cli/models.py
+++ b/docling/cli/models.py
@@ -32,6 +32,8 @@ class _AvailableModels(str, Enum):
     CODE_FORMULA = "code_formula"
     PICTURE_CLASSIFIER = "picture_classifier"
     SMOLVLM = "smolvlm"
+    SMOLDOCLING = "smoldocling"
+    SMOLDOCLING_MLX = "smoldocling_mlx"
     GRANITE_VISION = "granite_vision"
     EASYOCR = "easyocr"
 
@@ -105,6 +107,8 @@ 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_smoldocling=_AvailableModels.SMOLDOCLING in to_download,
+        with_smoldocling_mlx=_AvailableModels.SMOLDOCLING_MLX in to_download,
         with_granite_vision=_AvailableModels.GRANITE_VISION in to_download,
         with_easyocr=_AvailableModels.EASYOCR in to_download,
     )
diff --git a/docling/utils/model_downloader.py b/docling/utils/model_downloader.py
index 6a1eb83..eb20f25 100644
--- a/docling/utils/model_downloader.py
+++ b/docling/utils/model_downloader.py
@@ -4,12 +4,15 @@ from typing import Optional
 
 from docling.datamodel.pipeline_options import (
     granite_picture_description,
+    smoldocling_vlm_conversion_options,
+    smoldocling_vlm_mlx_conversion_options,
     smolvlm_picture_description,
 )
 from docling.datamodel.settings import settings
 from docling.models.code_formula_model import CodeFormulaModel
 from docling.models.document_picture_classifier import DocumentPictureClassifier
 from docling.models.easyocr_model import EasyOcrModel
+from docling.models.hf_vlm_model import HuggingFaceVlmModel
 from docling.models.layout_model import LayoutModel
 from docling.models.picture_description_vlm_model import PictureDescriptionVlmModel
 from docling.models.table_structure_model import TableStructureModel
@@ -27,6 +30,8 @@ def download_models(
     with_code_formula: bool = True,
     with_picture_classifier: bool = True,
     with_smolvlm: bool = False,
+    with_smoldocling: bool = False,
+    with_smoldocling_mlx: bool = False,
     with_granite_vision: bool = False,
     with_easyocr: bool = True,
 ):
@@ -77,6 +82,25 @@ def download_models(
             progress=progress,
         )
 
+    if with_smoldocling:
+        _log.info("Downloading SmolDocling model...")
+        HuggingFaceVlmModel.download_models(
+            repo_id=smoldocling_vlm_conversion_options.repo_id,
+            local_dir=output_dir / smoldocling_vlm_conversion_options.repo_cache_folder,
+            force=force,
+            progress=progress,
+        )
+
+    if with_smoldocling_mlx:
+        _log.info("Downloading SmolDocling MLX model...")
+        HuggingFaceVlmModel.download_models(
+            repo_id=smoldocling_vlm_mlx_conversion_options.repo_id,
+            local_dir=output_dir
+            / smoldocling_vlm_mlx_conversion_options.repo_cache_folder,
+            force=force,
+            progress=progress,
+        )
+
     if with_granite_vision:
         _log.info("Downloading Granite Vision model...")
         PictureDescriptionVlmModel.download_models(