docling 2.52.0__py3-none-any.whl → 2.53.0__py3-none-any.whl

docling/cli/main.py

@@ -64,6 +64,8 @@ from docling.datamodel.vlm_model_specs import (
     GOT2_TRANSFORMERS,
     GRANITE_VISION_OLLAMA,
     GRANITE_VISION_TRANSFORMERS,
+    GRANITEDOCLING_MLX,
+    GRANITEDOCLING_TRANSFORMERS,
     SMOLDOCLING_MLX,
     SMOLDOCLING_TRANSFORMERS,
     SMOLDOCLING_VLLM,
@@ -334,7 +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."),
@@ -684,6 +686,18 @@ def convert(  # noqa: C901
                             "To run SmolDocling faster, please install mlx-vlm:\n"
                             "pip install mlx-vlm"
                         )
+            elif vlm_model == VlmModelType.GRANITEDOCLING:
+                pipeline_options.vlm_options = GRANITEDOCLING_TRANSFORMERS
+                if sys.platform == "darwin":
+                    try:
+                        import mlx_vlm
+
+                        pipeline_options.vlm_options = GRANITEDOCLING_MLX
+                    except ImportError:
+                        _log.warning(
+                            "To run GraniteDocling faster, please install mlx-vlm:\n"
+                            "pip install mlx-vlm"
+                        )
             elif vlm_model == VlmModelType.SMOLDOCLING_VLLM:
                 pipeline_options.vlm_options = SMOLDOCLING_VLLM
 

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
@@ -114,7 +114,11 @@ class RapidOcrOptions(OcrOptions):
     cls_model_path: Optional[str] = None  # same default as rapidocr
     rec_model_path: Optional[str] = None  # same default as rapidocr
     rec_keys_path: Optional[str] = None  # same default as rapidocr
-    rec_font_path: Optional[str] = None  # same default as rapidocr
+    rec_font_path: Optional[str] = None  # Deprecated, please use font_path instead
+    font_path: Optional[str] = None  # same default as rapidocr
+
+    # Dictionary to overwrite or pass-through additional parameters
+    rapidocr_params: Dict[str, Any] = Field(default_factory=dict)
 
     model_config = ConfigDict(
         extra="forbid",
@@ -286,7 +290,7 @@ 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/datamodel/vlm_model_specs.py

@@ -18,6 +18,35 @@ from docling.datamodel.pipeline_options_vlm_model import (
 _log = logging.getLogger(__name__)
 
 
+# Granite-Docling
+GRANITEDOCLING_TRANSFORMERS = InlineVlmOptions(
+    repo_id="ibm-granite/granite-docling-258M",
+    prompt="Convert this page to docling.",
+    response_format=ResponseFormat.DOCTAGS,
+    inference_framework=InferenceFramework.TRANSFORMERS,
+    transformers_model_type=TransformersModelType.AUTOMODEL_IMAGETEXTTOTEXT,
+    supported_devices=[
+        AcceleratorDevice.CPU,
+        AcceleratorDevice.CUDA,
+    ],
+    scale=2.0,
+    temperature=0.0,
+    max_new_tokens=8192,
+    stop_strings=["</doctag>", "<|end_of_text|>"],
+)
+
+GRANITEDOCLING_MLX = InlineVlmOptions(
+    repo_id="ibm-granite/granite-docling-258M-mlx",
+    prompt="Convert this page to docling.",
+    response_format=ResponseFormat.DOCTAGS,
+    inference_framework=InferenceFramework.MLX,
+    supported_devices=[AcceleratorDevice.MPS],
+    scale=2.0,
+    temperature=0.0,
+    max_new_tokens=8192,
+    stop_strings=["</doctag>", "<|end_of_text|>"],
+)
+
 # SmolDocling
 SMOLDOCLING_MLX = InlineVlmOptions(
     repo_id="ds4sd/SmolDocling-256M-preview-mlx-bf16",
@@ -272,3 +301,4 @@ class VlmModelType(str, Enum):
     GRANITE_VISION_VLLM = "granite_vision_vllm"
     GRANITE_VISION_OLLAMA = "granite_vision_ollama"
     GOT_OCR_2 = "got_ocr_2"
+    GRANITEDOCLING = "granite_docling"

docling/models/rapid_ocr_model.py

@@ -62,32 +62,44 @@ class RapidOcrModel(BaseOcrModel):
             }
             backend_enum = _ALIASES.get(self.options.backend, EngineType.ONNXRUNTIME)
 
+            params = {
+                # Global settings (these are still correct)
+                "Global.text_score": self.options.text_score,
+                "Global.font_path": self.options.font_path,
+                # "Global.verbose": self.options.print_verbose,
+                # Detection model settings
+                "Det.model_path": self.options.det_model_path,
+                "Det.use_cuda": use_cuda,
+                "Det.use_dml": use_dml,
+                "Det.intra_op_num_threads": intra_op_num_threads,
+                # Classification model settings
+                "Cls.model_path": self.options.cls_model_path,
+                "Cls.use_cuda": use_cuda,
+                "Cls.use_dml": use_dml,
+                "Cls.intra_op_num_threads": intra_op_num_threads,
+                # Recognition model settings
+                "Rec.model_path": self.options.rec_model_path,
+                "Rec.font_path": self.options.rec_font_path,
+                "Rec.keys_path": self.options.rec_keys_path,
+                "Rec.use_cuda": use_cuda,
+                "Rec.use_dml": use_dml,
+                "Rec.intra_op_num_threads": intra_op_num_threads,
+                "Det.engine_type": backend_enum,
+                "Cls.engine_type": backend_enum,
+                "Rec.engine_type": backend_enum,
+            }
+
+            if self.options.rec_font_path is not None:
+                _log.warning(
+                    "The 'rec_font_path' option for RapidOCR is deprecated. Please use 'font_path' instead."
+                )
+            user_params = self.options.rapidocr_params
+            if user_params:
+                _log.debug("Overwriting RapidOCR params with user-provided values.")
+                params.update(user_params)
+
             self.reader = RapidOCR(
-                params={
-                    # Global settings (these are still correct)
-                    "Global.text_score": self.options.text_score,
-                    # "Global.verbose": self.options.print_verbose,
-                    # Detection model settings
-                    "Det.model_path": self.options.det_model_path,
-                    "Det.use_cuda": use_cuda,
-                    "Det.use_dml": use_dml,
-                    "Det.intra_op_num_threads": intra_op_num_threads,
-                    # Classification model settings
-                    "Cls.model_path": self.options.cls_model_path,
-                    "Cls.use_cuda": use_cuda,
-                    "Cls.use_dml": use_dml,
-                    "Cls.intra_op_num_threads": intra_op_num_threads,
-                    # Recognition model settings
-                    "Rec.model_path": self.options.rec_model_path,
-                    "Rec.font_path": self.options.rec_font_path,
-                    "Rec.keys_path": self.options.rec_keys_path,
-                    "Rec.use_cuda": use_cuda,
-                    "Rec.use_dml": use_dml,
-                    "Rec.intra_op_num_threads": intra_op_num_threads,
-                    "Det.engine_type": backend_enum,
-                    "Cls.engine_type": backend_enum,
-                    "Rec.engine_type": backend_enum,
-                }
+                params=params,
             )
 
     def __call__(
@@ -120,6 +132,9 @@ class RapidOcrModel(BaseOcrModel):
                             use_cls=self.options.use_cls,
                             use_rec=self.options.use_rec,
                         )
+                        if result is None or result.boxes is None:
+                            _log.warning("RapidOCR returned empty result!")
+                            continue
                         result = list(
                             zip(result.boxes.tolist(), result.txts, result.scores)
                         )

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(

{docling-2.52.0.dist-info → docling-2.53.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: docling
-Version: 2.52.0
+Version: 2.53.0
 Summary: SDK and CLI for parsing PDF, DOCX, HTML, and more, to a unified document representation for powering downstream workflows such as gen AI applications.
 Author-email: Christoph Auer <cau@zurich.ibm.com>, Michele Dolfi <dol@zurich.ibm.com>, Maxim Lysak <mly@zurich.ibm.com>, Nikos Livathinos <nli@zurich.ibm.com>, Ahmed Nassar <ahn@zurich.ibm.com>, Panos Vagenas <pva@zurich.ibm.com>, Peter Staar <taa@zurich.ibm.com>
 License-Expression: MIT
@@ -108,7 +108,7 @@ Docling simplifies document processing, parsing diverse formats — including ad
 * 🔒 Local execution capabilities for sensitive data and air-gapped environments
 * 🤖 Plug-and-play [integrations][integrations] incl. LangChain, LlamaIndex, Crew AI & Haystack for agentic AI
 * 🔍 Extensive OCR support for scanned PDFs and images
-* 👓 Support of several Visual Language Models ([SmolDocling](https://huggingface.co/ds4sd/SmolDocling-256M-preview))
+* 👓 Support of several Visual Language Models ([GraniteDocling](https://huggingface.co/ibm-granite/granite-docling-258M))
 * 🎙️ Audio support with Automatic Speech Recognition (ASR) models
 * 🔌 Connect to any agent using the [MCP server](https://docling-project.github.io/docling/usage/mcp/)
 * 💻 Simple and convenient CLI
@@ -160,9 +160,9 @@ Docling has a built-in CLI to run conversions.
 docling https://arxiv.org/pdf/2206.01062
 ```
 
-You can also use 🥚[SmolDocling](https://huggingface.co/ds4sd/SmolDocling-256M-preview) and other VLMs via Docling CLI:
+You can also use 🥚[GraniteDocling](https://huggingface.co/ibm-granite/granite-docling-258M) and other VLMs via Docling CLI:
 ```bash
-docling --pipeline vlm --vlm-model smoldocling https://arxiv.org/pdf/2206.01062
+docling --pipeline vlm --vlm-model granite_docling https://arxiv.org/pdf/2206.01062
 ```
 This will use MLX acceleration on supported Apple Silicon hardware.
 

{docling-2.52.0.dist-info → docling-2.53.0.dist-info}/RECORD

@@ -30,8 +30,8 @@ docling/backend/xml/jats_backend.py,sha256=LPj33EFdi2MRCakkLWrRLlUAc-B-949f8zp5g
 docling/backend/xml/uspto_backend.py,sha256=nyAMr5ht7dclxkVDwsKNeiOhLQrUtRLS8JdscB2AVJg,70924
 docling/chunking/__init__.py,sha256=h83TDs0AuOV6oEPLAPrn9dpGKiU-2Vg6IRNo4cv6GDA,346
 docling/cli/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/cli/main.py,sha256=K4m7dtnLUM2gqU8n_Mntpc_ODrwWtrjBPTUZakQ8erg,32111
-docling/cli/models.py,sha256=5C3CZz3HZXoCrBl92Is62KMCtUqsZK-oygj1hqzJ8vo,6008
+docling/cli/main.py,sha256=J_hXHclzT-uNu-cuKNdlc3vwCnyDRxXrJ5L2LJofzeo,32729
+docling/cli/models.py,sha256=rw_2JfeJ-k_iOLpz3JfgL1QbJY__W9nE23nHdov6VfU,6252
 docling/cli/tools.py,sha256=QhtRxQG0TVrfsMqdv5i7J0_qQy1ZZyWYnHPwJl7b5oY,322
 docling/datamodel/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/datamodel/accelerator_options.py,sha256=wv6dOFTVAwr9onkE-0pfUqX_fDb6gX53iPPE6o8nKjI,2511
@@ -40,11 +40,11 @@ docling/datamodel/base_models.py,sha256=vOt895z0GsFirHkkI3hM23e9oyUuz9RXfcGFtoIN
 docling/datamodel/document.py,sha256=ElY7G6FYJ6Bayyw433_tbnxyE47fnQRoBG_mygvOBrA,17370
 docling/datamodel/extraction.py,sha256=7dgvtK5SuvgfB8LHAwS1FwrW1kcMQJuJG0ol8uAQgoQ,1323
 docling/datamodel/layout_model_specs.py,sha256=GSkJ-Z_0PVgwWGi7C7TsxbzRjlrWS9ZrHJjHumv-Z5U,2339
-docling/datamodel/pipeline_options.py,sha256=N9g-3FA4hFU8A0uGvPmcy1emBBT4JH6u7CUzl3D-Ta0,11049
+docling/datamodel/pipeline_options.py,sha256=28opZ3woXA8IKaG2-BHM-lmmi-gyuScCMHGxhlxGOsk,11290
 docling/datamodel/pipeline_options_asr_model.py,sha256=7X068xl-qpbyPxC7-TwX7Q6tLyZXGT5h1osZ_xLNLM0,1454
 docling/datamodel/pipeline_options_vlm_model.py,sha256=AcqqThSW74hwQ6x7pazzm57LnJiUqB7gQi5wFayGlbk,2628
 docling/datamodel/settings.py,sha256=c0MTw6pO5be_BKxHKYl4SaBJAw_qL-aapxp-g5HHj1A,2084
-docling/datamodel/vlm_model_specs.py,sha256=8D-bF95EoaD-Wd29lVX094HPJT1gYN393aFmzv7RipQ,8713
+docling/datamodel/vlm_model_specs.py,sha256=UMXiTzWCXcx2BtF5slYfWhjRXAx0s1oiAvE-vCzrATo,9686
 docling/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/models/api_vlm_model.py,sha256=-zisU32pgDRbychyG6-neB0qweNbPaYnLXwiGT7SEdI,2859
 docling/models/base_model.py,sha256=beMGyrpl-yYX3YnLzQkLfxMLxwmDWnbcFhkjbUlWJSU,7146
@@ -59,7 +59,7 @@ docling/models/page_preprocessing_model.py,sha256=EmusNexws5ZmR93js_saVU0BedqZ_H
 docling/models/picture_description_api_model.py,sha256=o3EkV5aHW_6WzE_fdj_VRnNCrS_btclO_ZCLAUqrfl0,2377
 docling/models/picture_description_base_model.py,sha256=kLthLhdlgwhootQ4_xhhcAk6A-vso5-qcsFJ3TcYfO0,2991
 docling/models/picture_description_vlm_model.py,sha256=Uja_BQSk7F-U1J2hm4yeLguirUzKYv1K8zRyw1IYomY,4150
-docling/models/rapid_ocr_model.py,sha256=7yZC7I1qoC9xC8xJIjTk2c8VFm89RfB6Vr7IDOnr5gs,7102
+docling/models/rapid_ocr_model.py,sha256=anUVUwaj9Wubgu4FnHdYMuOVkQP_hJiLY1qRToelBoc,7700
 docling/models/readingorder_model.py,sha256=bZoXHaSwUsa8niSmJrbCuy784ixCeBXT-RQBUfgHJ4A,14925
 docling/models/table_structure_model.py,sha256=7vO8LisdoqCTsY8X8lsk9d-oD2hVjUtdaWlkMTQxEg0,12518
 docling/models/tesseract_ocr_cli_model.py,sha256=I3Gn28Y-LD8OfvyCElN9fLiNgpo2sT0uMkVt258253s,12881
@@ -93,15 +93,15 @@ docling/utils/export.py,sha256=VwVUnYDk3mhGmISDbVm306fwpGNnoojouStBD4UajXI,4673
 docling/utils/glm_utils.py,sha256=TKOWQqWAHsX_w4fvoAA7_2xCi_urhnp1DsmjY8_sk5w,12274
 docling/utils/layout_postprocessor.py,sha256=sE9UR3Nv4iOk26uoIsN3bFioE7ScfAjj0orDBDneLXg,25166
 docling/utils/locks.py,sha256=RzqQtD5UispgV71pGN_nU6GYfeN11BN0Sh_Dq9ycqGo,52
-docling/utils/model_downloader.py,sha256=lAIyevIC6dyv1TS0ElRSAGNylB5n_V8pWs1PhxH8wAQ,4104
+docling/utils/model_downloader.py,sha256=kFIxr5KUQbisQH0h8yP9GZMqsRJD3Xo1uOIiLiB1T78,4869
 docling/utils/ocr_utils.py,sha256=nmresYyfin0raanpQc_GGeU3WoLsfExf6SEXNIQ7Djg,2325
 docling/utils/orientation.py,sha256=jTyLxyT31FlOodZoBMlADHNQK2lAWKYVs5z7pXd_6Cg,1842
 docling/utils/profiling.py,sha256=YaMGoB9MMZpagF9mb5ndoHj8Lpb9aIdb7El-Pl7IcFs,1753
 docling/utils/utils.py,sha256=kJtIYuzXeOyJHYlxmLAo7dGM5rEsDa1i84qEsUj1nio,1908
 docling/utils/visualization.py,sha256=tY2ylE2aiQKkmzlSLnFW-HTfFyqUUMguW18ldd1PLfo,2868
-docling-2.52.0.dist-info/licenses/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
-docling-2.52.0.dist-info/METADATA,sha256=EhUePtqwKQJTgkU9pCtvpWT7wtU-84KXkc48XExkRSQ,11233
-docling-2.52.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-docling-2.52.0.dist-info/entry_points.txt,sha256=hzVlbeE0aMSTQ9S0-NTYN0Hmgsn6qL_EA2qX4UbkAuY,149
-docling-2.52.0.dist-info/top_level.txt,sha256=vkIywP-USjFyYo1AIRQbWQQaL3xB5jf8vkCYdTIfNic,8
-docling-2.52.0.dist-info/RECORD,,
+docling-2.53.0.dist-info/licenses/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
+docling-2.53.0.dist-info/METADATA,sha256=bpbaYrZCEppMQ3nPsq8wyn_Opp6IRK_P_rF5JQjCjr4,11247
+docling-2.53.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+docling-2.53.0.dist-info/entry_points.txt,sha256=hzVlbeE0aMSTQ9S0-NTYN0Hmgsn6qL_EA2qX4UbkAuY,149
+docling-2.53.0.dist-info/top_level.txt,sha256=vkIywP-USjFyYo1AIRQbWQQaL3xB5jf8vkCYdTIfNic,8
+docling-2.53.0.dist-info/RECORD,,