feat: Describe pictures using vision models (#259)

* draft for picture description models

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

* vlm description using AutoModelForVision2Seq

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

* add generation options

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

* update vlm API

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

* allow only localhost traffic

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

* rename model

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

* do not run with vlm api

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

* more renaming

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

* fix examples path

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

* apply CLI download login

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

* fix name of cli argument

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

* use with_smolvlm in models download

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

---------

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

docling/utils/model_downloader.py

@@ -2,11 +2,13 @@ import logging
 from pathlib import Path
 from typing import Optional
 
+from docling.datamodel.pipeline_options import 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.layout_model import LayoutModel
+from docling.models.picture_description_vlm_model import PictureDescriptionVlmModel
 from docling.models.table_structure_model import TableStructureModel
 
 _log = logging.getLogger(__name__)
@@ -21,6 +23,7 @@ def download_models(
     with_tableformer: bool = True,
     with_code_formula: bool = True,
     with_picture_classifier: bool = True,
+    with_smolvlm: bool = True,
     with_easyocr: bool = True,
 ):
     if output_dir is None:
@@ -61,6 +64,15 @@ def download_models(
             progress=progress,
         )
 
+    if with_smolvlm:
+        _log.info(f"Downloading SmolVlm model...")
+        PictureDescriptionVlmModel.download_models(
+            repo_id=smolvlm_picture_description.repo_id,
+            local_dir=output_dir / smolvlm_picture_description.repo_cache_folder,
+            force=force,
+            progress=progress,
+        )
+
     if with_easyocr:
         _log.info(f"Downloading easyocr models...")
         EasyOcrModel.download_models(