Merge remote-tracking branch 'origin/main' into bugfix/ignore_mypy_checking_in_find_images_in_sheet

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

docling/backend/abstract_backend.py

@@ -27,7 +27,6 @@ class AbstractDocumentBackend(ABC):
     def supports_pagination(cls) -> bool:
         pass
 
-    @abstractmethod
     def unload(self):
         if isinstance(self.path_or_stream, BytesIO):
             self.path_or_stream.close()

docling/backend/json/docling_json_backend.py

@@ -0,0 +1,58 @@
+from io import BytesIO
+from pathlib import Path
+from typing import Union
+
+from docling_core.types.doc import DoclingDocument
+from typing_extensions import override
+
+from docling.backend.abstract_backend import DeclarativeDocumentBackend
+from docling.datamodel.base_models import InputFormat
+from docling.datamodel.document import InputDocument
+
+
+class DoclingJSONBackend(DeclarativeDocumentBackend):
+    @override
+    def __init__(
+        self, in_doc: InputDocument, path_or_stream: Union[BytesIO, Path]
+    ) -> None:
+        super().__init__(in_doc, path_or_stream)
+
+        # given we need to store any actual conversion exception for raising it from
+        # convert(), this captures the successful result or the actual error in a
+        # mutually exclusive way:
+        self._doc_or_err = self._get_doc_or_err()
+
+    @override
+    def is_valid(self) -> bool:
+        return isinstance(self._doc_or_err, DoclingDocument)
+
+    @classmethod
+    @override
+    def supports_pagination(cls) -> bool:
+        return False
+
+    @classmethod
+    @override
+    def supported_formats(cls) -> set[InputFormat]:
+        return {InputFormat.JSON_DOCLING}
+
+    def _get_doc_or_err(self) -> Union[DoclingDocument, Exception]:
+        try:
+            json_data: Union[str, bytes]
+            if isinstance(self.path_or_stream, Path):
+                with open(self.path_or_stream, encoding="utf-8") as f:
+                    json_data = f.read()
+            elif isinstance(self.path_or_stream, BytesIO):
+                json_data = self.path_or_stream.getvalue()
+            else:
+                raise RuntimeError(f"Unexpected: {type(self.path_or_stream)=}")
+            return DoclingDocument.model_validate_json(json_data=json_data)
+        except Exception as e:
+            return e
+
+    @override
+    def convert(self) -> DoclingDocument:
+        if isinstance(self._doc_or_err, DoclingDocument):
+            return self._doc_or_err
+        else:
+            raise self._doc_or_err

docling/datamodel/base_models.py

@@ -41,6 +41,7 @@ class InputFormat(str, Enum):
     MD = "md"
     XLSX = "xlsx"
     XML_USPTO = "xml_uspto"
+    JSON_DOCLING = "json_docling"
 
 
 class OutputFormat(str, Enum):
@@ -62,6 +63,7 @@ FormatToExtensions: Dict[InputFormat, List[str]] = {
     InputFormat.ASCIIDOC: ["adoc", "asciidoc", "asc"],
     InputFormat.XLSX: ["xlsx"],
     InputFormat.XML_USPTO: ["xml", "txt"],
+    InputFormat.JSON_DOCLING: ["json"],
 }
 
 FormatToMimeType: Dict[InputFormat, List[str]] = {
@@ -90,6 +92,7 @@ FormatToMimeType: Dict[InputFormat, List[str]] = {
         "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
     ],
     InputFormat.XML_USPTO: ["application/xml", "text/plain"],
+    InputFormat.JSON_DOCLING: ["application/json"],
 }
 
 MimeTypeToFormat: dict[str, list[InputFormat]] = {

docling/datamodel/document.py

@@ -350,6 +350,8 @@ class _DocumentConversionInput(BaseModel):
             mime = FormatToMimeType[InputFormat.HTML][0]
         elif ext in FormatToExtensions[InputFormat.MD]:
             mime = FormatToMimeType[InputFormat.MD][0]
+        elif ext in FormatToExtensions[InputFormat.JSON_DOCLING]:
+            mime = FormatToMimeType[InputFormat.JSON_DOCLING][0]
         return mime
 
     @staticmethod

docling/datamodel/pipeline_options.py

@@ -221,6 +221,7 @@ class PdfPipelineOptions(PipelineOptions):
     do_ocr: bool = True  # True: perform OCR, replace programmatic PDF text
     do_code_enrichment: bool = False  # True: perform code OCR
     do_formula_enrichment: bool = False  # True: perform formula OCR, return Latex code
+    do_picture_classification: bool = False  # True: classify pictures in documents
 
     table_structure_options: TableStructureOptions = TableStructureOptions()
     ocr_options: Union[

docling/document_converter.py

@@ -11,6 +11,7 @@ from docling.backend.abstract_backend import AbstractDocumentBackend
 from docling.backend.asciidoc_backend import AsciiDocBackend
 from docling.backend.docling_parse_v2_backend import DoclingParseV2DocumentBackend
 from docling.backend.html_backend import HTMLDocumentBackend
+from docling.backend.json.docling_json_backend import DoclingJSONBackend
 from docling.backend.md_backend import MarkdownDocumentBackend
 from docling.backend.msexcel_backend import MsExcelDocumentBackend
 from docling.backend.mspowerpoint_backend import MsPowerpointDocumentBackend
@@ -136,6 +137,9 @@ def _get_default_option(format: InputFormat) -> FormatOption:
         InputFormat.PDF: FormatOption(
             pipeline_cls=StandardPdfPipeline, backend=DoclingParseV2DocumentBackend
         ),
+        InputFormat.JSON_DOCLING: FormatOption(
+            pipeline_cls=SimplePipeline, backend=DoclingJSONBackend
+        ),
     }
     if (options := format_to_default_options.get(format)) is not None:
         return options

docling/models/document_picture_classifier.py

@@ -0,0 +1,187 @@
+from pathlib import Path
+from typing import Iterable, List, Literal, Optional, Tuple, Union
+
+from docling_core.types.doc import (
+    DoclingDocument,
+    NodeItem,
+    PictureClassificationClass,
+    PictureClassificationData,
+    PictureItem,
+)
+from PIL import Image
+from pydantic import BaseModel
+
+from docling.datamodel.pipeline_options import AcceleratorOptions
+from docling.models.base_model import BaseEnrichmentModel
+from docling.utils.accelerator_utils import decide_device
+
+
+class DocumentPictureClassifierOptions(BaseModel):
+    """
+    Options for configuring the DocumentPictureClassifier.
+
+    Attributes
+    ----------
+    kind : Literal["document_picture_classifier"]
+        Identifier for the type of classifier.
+    """
+
+    kind: Literal["document_picture_classifier"] = "document_picture_classifier"
+
+
+class DocumentPictureClassifier(BaseEnrichmentModel):
+    """
+    A model for classifying pictures in documents.
+
+    This class enriches document pictures with predicted classifications
+    based on a predefined set of classes.
+
+    Attributes
+    ----------
+    enabled : bool
+        Whether the classifier is enabled for use.
+    options : DocumentPictureClassifierOptions
+        Configuration options for the classifier.
+    document_picture_classifier : DocumentPictureClassifierPredictor
+        The underlying prediction model, loaded if the classifier is enabled.
+
+    Methods
+    -------
+    __init__(enabled, artifacts_path, options, accelerator_options)
+        Initializes the classifier with specified configurations.
+    is_processable(doc, element)
+        Checks if the given element can be processed by the classifier.
+    __call__(doc, element_batch)
+        Processes a batch of elements and adds classification annotations.
+    """
+
+    images_scale = 2
+
+    def __init__(
+        self,
+        enabled: bool,
+        artifacts_path: Optional[Union[Path, str]],
+        options: DocumentPictureClassifierOptions,
+        accelerator_options: AcceleratorOptions,
+    ):
+        """
+        Initializes the DocumentPictureClassifier.
+
+        Parameters
+        ----------
+        enabled : bool
+            Indicates whether the classifier is enabled.
+        artifacts_path : Optional[Union[Path, str]],
+            Path to the directory containing model artifacts.
+        options : DocumentPictureClassifierOptions
+            Configuration options for the classifier.
+        accelerator_options : AcceleratorOptions
+            Options for configuring the device and parallelism.
+        """
+        self.enabled = enabled
+        self.options = options
+
+        if self.enabled:
+            device = decide_device(accelerator_options.device)
+            from docling_ibm_models.document_figure_classifier_model.document_figure_classifier_predictor import (
+                DocumentFigureClassifierPredictor,
+            )
+
+            if artifacts_path is None:
+                artifacts_path = self.download_models_hf()
+            else:
+                artifacts_path = Path(artifacts_path)
+
+            self.document_picture_classifier = DocumentFigureClassifierPredictor(
+                artifacts_path=artifacts_path,
+                device=device,
+                num_threads=accelerator_options.num_threads,
+            )
+
+    @staticmethod
+    def download_models_hf(
+        local_dir: Optional[Path] = None, force: bool = False
+    ) -> Path:
+        from huggingface_hub import snapshot_download
+        from huggingface_hub.utils import disable_progress_bars
+
+        disable_progress_bars()
+        download_path = snapshot_download(
+            repo_id="ds4sd/DocumentFigureClassifier",
+            force_download=force,
+            local_dir=local_dir,
+            revision="v1.0.0",
+        )
+
+        return Path(download_path)
+
+    def is_processable(self, doc: DoclingDocument, element: NodeItem) -> bool:
+        """
+        Determines if the given element can be processed by the classifier.
+
+        Parameters
+        ----------
+        doc : DoclingDocument
+            The document containing the element.
+        element : NodeItem
+            The element to be checked.
+
+        Returns
+        -------
+        bool
+            True if the element is a PictureItem and processing is enabled; False otherwise.
+        """
+        return self.enabled and isinstance(element, PictureItem)
+
+    def __call__(
+        self,
+        doc: DoclingDocument,
+        element_batch: Iterable[NodeItem],
+    ) -> Iterable[NodeItem]:
+        """
+        Processes a batch of elements and enriches them with classification predictions.
+
+        Parameters
+        ----------
+        doc : DoclingDocument
+            The document containing the elements to be processed.
+        element_batch : Iterable[NodeItem]
+            A batch of pictures to classify.
+
+        Returns
+        -------
+        Iterable[NodeItem]
+            An iterable of NodeItem objects after processing. The field
+            'data.classification' is added containing the classification for each picture.
+        """
+        if not self.enabled:
+            for element in element_batch:
+                yield element
+            return
+
+        images: List[Image.Image] = []
+        elements: List[PictureItem] = []
+        for el in element_batch:
+            assert isinstance(el, PictureItem)
+            elements.append(el)
+            img = el.get_image(doc)
+            assert img is not None
+            images.append(img)
+
+        outputs = self.document_picture_classifier.predict(images)
+
+        for element, output in zip(elements, outputs):
+            element.annotations.append(
+                PictureClassificationData(
+                    provenance="DocumentPictureClassifier",
+                    predicted_classes=[
+                        PictureClassificationClass(
+                            class_name=pred[0],
+                            confidence=pred[1],
+                        )
+                        for pred in output
+                    ],
+                )
+            )
+
+            yield element

docling/pipeline/standard_pdf_pipeline.py

@@ -19,6 +19,10 @@ from docling.datamodel.pipeline_options import (
 )
 from docling.models.base_ocr_model import BaseOcrModel
 from docling.models.code_formula_model import CodeFormulaModel, CodeFormulaModelOptions
+from docling.models.document_picture_classifier import (
+    DocumentPictureClassifier,
+    DocumentPictureClassifierOptions,
+)
 from docling.models.ds_glm_model import GlmModel, GlmOptions
 from docling.models.easyocr_model import EasyOcrModel
 from docling.models.layout_model import LayoutModel
@@ -104,6 +108,13 @@ class StandardPdfPipeline(PaginatedPipeline):
                 ),
                 accelerator_options=pipeline_options.accelerator_options,
             ),
+            # Document Picture Classifier
+            DocumentPictureClassifier(
+                enabled=pipeline_options.do_picture_classification,
+                artifacts_path=pipeline_options.artifacts_path,
+                options=DocumentPictureClassifierOptions(),
+                accelerator_options=pipeline_options.accelerator_options,
+            ),
         ]
 
         if (

poetry.lock

@@ -1,4 +1,4 @@
-# This file is automatically @generated by Poetry 1.8.3 and should not be changed by hand.
+# This file is automatically @generated by Poetry 1.8.5 and should not be changed by hand.
 
 [[package]]
 name = "aiohappyeyeballs"
@@ -3823,10 +3823,10 @@ files = [
 numpy = [
     {version = ">=1.21.0", markers = "python_version == \"3.9\" and platform_system == \"Darwin\" and platform_machine == \"arm64\""},
     {version = ">=1.19.3", markers = "platform_system == \"Linux\" and platform_machine == \"aarch64\" and python_version >= \"3.8\" and python_version < \"3.10\" or python_version > \"3.9\" and python_version < \"3.10\" or python_version >= \"3.9\" and platform_system != \"Darwin\" and python_version < \"3.10\" or python_version >= \"3.9\" and platform_machine != \"arm64\" and python_version < \"3.10\""},
+    {version = ">=1.26.0", markers = "python_version >= \"3.12\""},
+    {version = ">=1.23.5", markers = "python_version >= \"3.11\" and python_version < \"3.12\""},
     {version = ">=1.21.4", markers = "python_version >= \"3.10\" and platform_system == \"Darwin\" and python_version < \"3.11\""},
     {version = ">=1.21.2", markers = "platform_system != \"Darwin\" and python_version >= \"3.10\" and python_version < \"3.11\""},
-    {version = ">=1.23.5", markers = "python_version >= \"3.11\" and python_version < \"3.12\""},
-    {version = ">=1.26.0", markers = "python_version >= \"3.12\""},
 ]
 
 [[package]]
@@ -3849,10 +3849,10 @@ files = [
 numpy = [
     {version = ">=1.21.0", markers = "python_version == \"3.9\" and platform_system == \"Darwin\" and platform_machine == \"arm64\""},
     {version = ">=1.19.3", markers = "platform_system == \"Linux\" and platform_machine == \"aarch64\" and python_version >= \"3.8\" and python_version < \"3.10\" or python_version > \"3.9\" and python_version < \"3.10\" or python_version >= \"3.9\" and platform_system != \"Darwin\" and python_version < \"3.10\" or python_version >= \"3.9\" and platform_machine != \"arm64\" and python_version < \"3.10\""},
+    {version = ">=1.26.0", markers = "python_version >= \"3.12\""},
+    {version = ">=1.23.5", markers = "python_version >= \"3.11\" and python_version < \"3.12\""},
     {version = ">=1.21.4", markers = "python_version >= \"3.10\" and platform_system == \"Darwin\" and python_version < \"3.11\""},
     {version = ">=1.21.2", markers = "platform_system != \"Darwin\" and python_version >= \"3.10\" and python_version < \"3.11\""},
-    {version = ">=1.23.5", markers = "python_version >= \"3.11\" and python_version < \"3.12\""},
-    {version = ">=1.26.0", markers = "python_version >= \"3.12\""},
 ]
 
 [[package]]
@@ -3992,31 +3992,43 @@ python-versions = ">=3.9"
 files = [
     {file = "pandas-2.2.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:1948ddde24197a0f7add2bdc4ca83bf2b1ef84a1bc8ccffd95eda17fd836ecb5"},
     {file = "pandas-2.2.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:381175499d3802cde0eabbaf6324cce0c4f5d52ca6f8c377c29ad442f50f6348"},
+    {file = "pandas-2.2.3-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:d9c45366def9a3dd85a6454c0e7908f2b3b8e9c138f5dc38fed7ce720d8453ed"},
     {file = "pandas-2.2.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:86976a1c5b25ae3f8ccae3a5306e443569ee3c3faf444dfd0f41cda24667ad57"},
+    {file = "pandas-2.2.3-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:b8661b0238a69d7aafe156b7fa86c44b881387509653fdf857bebc5e4008ad42"},
     {file = "pandas-2.2.3-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:37e0aced3e8f539eccf2e099f65cdb9c8aa85109b0be6e93e2baff94264bdc6f"},
     {file = "pandas-2.2.3-cp310-cp310-win_amd64.whl", hash = "sha256:56534ce0746a58afaf7942ba4863e0ef81c9c50d3f0ae93e9497d6a41a057645"},
     {file = "pandas-2.2.3-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:66108071e1b935240e74525006034333f98bcdb87ea116de573a6a0dccb6c039"},
     {file = "pandas-2.2.3-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:7c2875855b0ff77b2a64a0365e24455d9990730d6431b9e0ee18ad8acee13dbd"},
+    {file = "pandas-2.2.3-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:cd8d0c3be0515c12fed0bdbae072551c8b54b7192c7b1fda0ba56059a0179698"},
     {file = "pandas-2.2.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c124333816c3a9b03fbeef3a9f230ba9a737e9e5bb4060aa2107a86cc0a497fc"},
+    {file = "pandas-2.2.3-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:63cc132e40a2e084cf01adf0775b15ac515ba905d7dcca47e9a251819c575ef3"},
     {file = "pandas-2.2.3-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:29401dbfa9ad77319367d36940cd8a0b3a11aba16063e39632d98b0e931ddf32"},
     {file = "pandas-2.2.3-cp311-cp311-win_amd64.whl", hash = "sha256:3fc6873a41186404dad67245896a6e440baacc92f5b716ccd1bc9ed2995ab2c5"},
     {file = "pandas-2.2.3-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:b1d432e8d08679a40e2a6d8b2f9770a5c21793a6f9f47fdd52c5ce1948a5a8a9"},
     {file = "pandas-2.2.3-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:a5a1595fe639f5988ba6a8e5bc9649af3baf26df3998a0abe56c02609392e0a4"},
+    {file = "pandas-2.2.3-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:5de54125a92bb4d1c051c0659e6fcb75256bf799a732a87184e5ea503965bce3"},
     {file = "pandas-2.2.3-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fffb8ae78d8af97f849404f21411c95062db1496aeb3e56f146f0355c9989319"},
+    {file = "pandas-2.2.3-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:6dfcb5ee8d4d50c06a51c2fffa6cff6272098ad6540aed1a76d15fb9318194d8"},
     {file = "pandas-2.2.3-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:062309c1b9ea12a50e8ce661145c6aab431b1e99530d3cd60640e255778bd43a"},
     {file = "pandas-2.2.3-cp312-cp312-win_amd64.whl", hash = "sha256:59ef3764d0fe818125a5097d2ae867ca3fa64df032331b7e0917cf5d7bf66b13"},
     {file = "pandas-2.2.3-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:f00d1345d84d8c86a63e476bb4955e46458b304b9575dcf71102b5c705320015"},
     {file = "pandas-2.2.3-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:3508d914817e153ad359d7e069d752cdd736a247c322d932eb89e6bc84217f28"},
+    {file = "pandas-2.2.3-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:22a9d949bfc9a502d320aa04e5d02feab689d61da4e7764b62c30b991c42c5f0"},
     {file = "pandas-2.2.3-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f3a255b2c19987fbbe62a9dfd6cff7ff2aa9ccab3fc75218fd4b7530f01efa24"},
+    {file = "pandas-2.2.3-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:800250ecdadb6d9c78eae4990da62743b857b470883fa27f652db8bdde7f6659"},
     {file = "pandas-2.2.3-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:6374c452ff3ec675a8f46fd9ab25c4ad0ba590b71cf0656f8b6daa5202bca3fb"},
     {file = "pandas-2.2.3-cp313-cp313-win_amd64.whl", hash = "sha256:61c5ad4043f791b61dd4752191d9f07f0ae412515d59ba8f005832a532f8736d"},
     {file = "pandas-2.2.3-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:3b71f27954685ee685317063bf13c7709a7ba74fc996b84fc6821c59b0f06468"},
     {file = "pandas-2.2.3-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:38cf8125c40dae9d5acc10fa66af8ea6fdf760b2714ee482ca691fc66e6fcb18"},
+    {file = "pandas-2.2.3-cp313-cp313t-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:ba96630bc17c875161df3818780af30e43be9b166ce51c9a18c1feae342906c2"},
     {file = "pandas-2.2.3-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1db71525a1538b30142094edb9adc10be3f3e176748cd7acc2240c2f2e5aa3a4"},
+    {file = "pandas-2.2.3-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:15c0e1e02e93116177d29ff83e8b1619c93ddc9c49083f237d4312337a61165d"},
     {file = "pandas-2.2.3-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:ad5b65698ab28ed8d7f18790a0dc58005c7629f227be9ecc1072aa74c0c1d43a"},
     {file = "pandas-2.2.3-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:bc6b93f9b966093cb0fd62ff1a7e4c09e6d546ad7c1de191767baffc57628f39"},
     {file = "pandas-2.2.3-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:5dbca4c1acd72e8eeef4753eeca07de9b1db4f398669d5994086f788a5d7cc30"},
+    {file = "pandas-2.2.3-cp39-cp39-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:8cd6d7cc958a3910f934ea8dbdf17b2364827bb4dafc38ce6eef6bb3d65ff09c"},
     {file = "pandas-2.2.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:99df71520d25fade9db7c1076ac94eb994f4d2673ef2aa2e86ee039b6746d20c"},
+    {file = "pandas-2.2.3-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:31d0ced62d4ea3e231a9f228366919a5ea0b07440d9d4dac345376fd8e1477ea"},
     {file = "pandas-2.2.3-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:7eee9e7cea6adf3e3d24e304ac6b8300646e2a5d1cd3a3c2abed9101b0846761"},
     {file = "pandas-2.2.3-cp39-cp39-win_amd64.whl", hash = "sha256:4850ba03528b6dd51d6c5d273c46f183f39a9baf3f0143e566b89450965b105e"},
     {file = "pandas-2.2.3.tar.gz", hash = "sha256:4f18ba62b61d7e192368b84517265a99b4d7ee8912f8708660fb4a366cc82667"},
@@ -4025,8 +4037,8 @@ files = [
 [package.dependencies]
 numpy = [
     {version = ">=1.22.4", markers = "python_version < \"3.11\""},
-    {version = ">=1.23.2", markers = "python_version == \"3.11\""},
     {version = ">=1.26.0", markers = "python_version >= \"3.12\""},
+    {version = ">=1.23.2", markers = "python_version == \"3.11\""},
 ]
 python-dateutil = ">=2.8.2"
 pytz = ">=2020.1"
@@ -7739,4 +7751,4 @@ tesserocr = ["tesserocr"]
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.9"
-content-hash = "55214611820f7e98e0e5399ce9f01256a185001c7cd361039171dc8e2d983169"
+content-hash = "08d30cee8d77f9beee32d5dbec1643367ecae2b4c4b47b57fcb337711471eb5c"

pyproject.toml

@@ -27,7 +27,7 @@ packages = [{include = "docling"}]
 python = "^3.9"
 pydantic = "^2.0.0"
 docling-core = { version = "^2.15.1", extras = ["chunking"] }
-docling-ibm-models = "^3.2.1"
+docling-ibm-models = "^3.3.0"
 deepsearch-glm = "^1.0.0"
 docling-parse = "^3.1.0"
 filetype = "^1.2.0"

tests/data/groundtruth/docling_v1/picture_classification.doctags.txt

@@ -0,0 +1,17 @@
+<document>
+<subtitle-level-1><location><page_1><loc_22><loc_83><loc_41><loc_84></location>Figures Example</subtitle-level-1>
+<paragraph><location><page_1><loc_22><loc_63><loc_78><loc_81></location>Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet.</paragraph>
+<caption><location><page_1><loc_37><loc_32><loc_63><loc_33></location>Figure 1: This is an example image.</caption>
+<figure>
+<location><page_1><loc_22><loc_36><loc_78><loc_62></location>
+<caption>Figure 1: This is an example image.</caption>
+</figure>
+<paragraph><location><page_1><loc_22><loc_15><loc_78><loc_30></location>Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua.</paragraph>
+<paragraph><location><page_2><loc_22><loc_66><loc_78><loc_84></location>Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet.</paragraph>
+<caption><location><page_2><loc_37><loc_33><loc_63><loc_34></location>Figure 2: This is an example image.</caption>
+<figure>
+<location><page_2><loc_36><loc_36><loc_64><loc_65></location>
+<caption>Figure 2: This is an example image.</caption>
+</figure>
+<paragraph><location><page_2><loc_22><loc_15><loc_78><loc_31></location>Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum.</paragraph>
+</document>

tests/data/groundtruth/docling_v1/picture_classification.md

@@ -0,0 +1,15 @@
+## Figures Example
+
+Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet.
+
+Figure 1: This is an example image.
+<!-- image -->
+
+Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua.
+
+Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet.
+
+Figure 2: This is an example image.
+<!-- image -->
+
+Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum.

tests/data/groundtruth/docling_v2/picture_classification.doctags.txt

@@ -0,0 +1,15 @@
+<document>
+<section_header_level_1><location><page_1><loc_22><loc_83><loc_41><loc_84></location>Figures Example</section_header_level_1>
+<text><location><page_1><loc_22><loc_63><loc_78><loc_81></location>Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet.</text>
+<figure>
+<location><page_1><loc_22><loc_36><loc_78><loc_62></location>
+<caption>Figure 1: This is an example image.</caption>
+</figure>
+<text><location><page_1><loc_22><loc_15><loc_78><loc_30></location>Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua.</text>
+<text><location><page_2><loc_22><loc_66><loc_78><loc_84></location>Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet.</text>
+<figure>
+<location><page_2><loc_36><loc_36><loc_64><loc_65></location>
+<caption>Figure 2: This is an example image.</caption>
+</figure>
+<text><location><page_2><loc_22><loc_15><loc_78><loc_31></location>Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum.</text>
+</document>

tests/data/groundtruth/docling_v2/picture_classification.md

@@ -0,0 +1,17 @@
+## Figures Example
+
+Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet.
+
+Figure 1: This is an example image.
+
+<!-- image -->
+
+Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua.
+
+Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet.
+
+Figure 2: This is an example image.
+
+<!-- image -->
+
+Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum.

tests/test_backend_docling_json.py

@@ -0,0 +1,58 @@
+"""Test methods in module docling.backend.json.docling_json_backend.py."""
+
+from io import BytesIO
+from pathlib import Path
+
+import pytest
+from pydantic import ValidationError
+
+from docling.backend.json.docling_json_backend import DoclingJSONBackend
+from docling.datamodel.base_models import InputFormat
+from docling.datamodel.document import DoclingDocument, InputDocument
+
+GT_PATH: Path = Path("./tests/data/groundtruth/docling_v2/2206.01062.json")
+
+
+def test_convert_valid_docling_json():
+    """Test ingestion of valid Docling JSON."""
+    cls = DoclingJSONBackend
+    path_or_stream = GT_PATH
+    in_doc = InputDocument(
+        path_or_stream=path_or_stream,
+        format=InputFormat.JSON_DOCLING,
+        backend=cls,
+    )
+    backend = cls(
+        in_doc=in_doc,
+        path_or_stream=path_or_stream,
+    )
+    assert backend.is_valid()
+
+    act_doc = backend.convert()
+    act_data = act_doc.export_to_dict()
+
+    exp_doc = DoclingDocument.load_from_json(GT_PATH)
+    exp_data = exp_doc.export_to_dict()
+
+    assert act_data == exp_data
+
+
+def test_invalid_docling_json():
+    """Test ingestion of invalid Docling JSON."""
+    cls = DoclingJSONBackend
+    path_or_stream = BytesIO(b"{}")
+    in_doc = InputDocument(
+        path_or_stream=path_or_stream,
+        format=InputFormat.JSON_DOCLING,
+        backend=cls,
+        filename="foo",
+    )
+    backend = cls(
+        in_doc=in_doc,
+        path_or_stream=path_or_stream,
+    )
+
+    assert not backend.is_valid()
+
+    with pytest.raises(ValidationError):
+        backend.convert()

tests/test_document_picture_classifier.py

@@ -0,0 +1,81 @@
+from pathlib import Path
+
+from docling_core.types.doc import PictureClassificationData
+
+from docling.backend.docling_parse_v2_backend import DoclingParseV2DocumentBackend
+from docling.datamodel.base_models import InputFormat
+from docling.datamodel.document import ConversionResult
+from docling.datamodel.pipeline_options import PdfPipelineOptions
+from docling.document_converter import DocumentConverter, PdfFormatOption
+from docling.pipeline.standard_pdf_pipeline import StandardPdfPipeline
+
+
+def get_converter():
+
+    pipeline_options = PdfPipelineOptions()
+    pipeline_options.generate_page_images = True
+
+    pipeline_options.do_ocr = False
+    pipeline_options.do_table_structure = False
+    pipeline_options.do_code_enrichment = False
+    pipeline_options.do_formula_enrichment = False
+    pipeline_options.do_picture_classification = True
+    pipeline_options.generate_picture_images = True
+    pipeline_options.images_scale = 2
+
+    converter = DocumentConverter(
+        format_options={
+            InputFormat.PDF: PdfFormatOption(
+                backend=DoclingParseV2DocumentBackend,
+                pipeline_cls=StandardPdfPipeline,
+                pipeline_options=pipeline_options,
+            )
+        }
+    )
+
+    return converter
+
+
+def test_picture_classifier():
+    pdf_path = Path("tests/data/picture_classification.pdf")
+    converter = get_converter()
+
+    print(f"converting {pdf_path}")
+
+    doc_result: ConversionResult = converter.convert(pdf_path)
+
+    results = doc_result.document.pictures
+
+    assert len(results) == 2
+
+    res = results[0]
+    assert len(res.annotations) == 1
+    assert type(res.annotations[0]) == PictureClassificationData
+    classification_data = res.annotations[0]
+    assert classification_data.provenance == "DocumentPictureClassifier"
+    assert (
+        len(classification_data.predicted_classes) == 16
+    ), "Number of predicted classes is not equal to 16"
+    confidences = [pred.confidence for pred in classification_data.predicted_classes]
+    assert confidences == sorted(
+        confidences, reverse=True
+    ), "Predictions are not sorted in descending order of confidence"
+    assert (
+        classification_data.predicted_classes[0].class_name == "bar_chart"
+    ), "The prediction is wrong for the bar chart image."
+
+    res = results[1]
+    assert len(res.annotations) == 1
+    assert type(res.annotations[0]) == PictureClassificationData
+    classification_data = res.annotations[0]
+    assert classification_data.provenance == "DocumentPictureClassifier"
+    assert (
+        len(classification_data.predicted_classes) == 16
+    ), "Number of predicted classes is not equal to 16"
+    confidences = [pred.confidence for pred in classification_data.predicted_classes]
+    assert confidences == sorted(
+        confidences, reverse=True
+    ), "Predictions are not sorted in descending order of confidence"
+    assert (
+        classification_data.predicted_classes[0].class_name == "map"
+    ), "The prediction is wrong for the bar chart image."

tests/test_input_doc.py

@@ -124,6 +124,25 @@ def test_guess_format(tmp_path):
     doc_path.write_text("xyz", encoding="utf-8")
     assert dci._guess_format(doc_path) == None
 
+    # Valid Docling JSON
+    test_str = '{"name": ""}'
+    stream = DocumentStream(name="test.json", stream=BytesIO(f"{test_str}".encode()))
+    assert dci._guess_format(stream) == InputFormat.JSON_DOCLING
+    doc_path = temp_dir / "test.json"
+    doc_path.write_text(test_str, encoding="utf-8")
+    assert dci._guess_format(doc_path) == InputFormat.JSON_DOCLING
+
+    # Non-Docling JSON
+    # TODO: Docling JSON is currently the single supported JSON flavor and the pipeline
+    # will try to validate *any* JSON (based on suffix/MIME) as Docling JSON; proper
+    # disambiguation seen as part of https://github.com/DS4SD/docling/issues/802
+    test_str = "{}"
+    stream = DocumentStream(name="test.json", stream=BytesIO(f"{test_str}".encode()))
+    assert dci._guess_format(stream) == InputFormat.JSON_DOCLING
+    doc_path = temp_dir / "test.json"
+    doc_path.write_text(test_str, encoding="utf-8")
+    assert dci._guess_format(doc_path) == InputFormat.JSON_DOCLING
+
 
 def _make_input_doc(path):
     in_doc = InputDocument(