docling 2.10.0__py3-none-any.whl → 2.11.0__py3-none-any.whl

docling/cli/main.py

@@ -27,8 +27,10 @@ from docling.datamodel.base_models import (
 from docling.datamodel.document import ConversionResult
 from docling.datamodel.pipeline_options import (
     EasyOcrOptions,
+    OcrEngine,
     OcrMacOptions,
     OcrOptions,
+    PdfBackend,
     PdfPipelineOptions,
     RapidOcrOptions,
     TableFormerMode,
@@ -68,22 +70,6 @@ def version_callback(value: bool):
         raise typer.Exit()
 
 
-# Define an enum for the backend options
-class PdfBackend(str, Enum):
-    PYPDFIUM2 = "pypdfium2"
-    DLPARSE_V1 = "dlparse_v1"
-    DLPARSE_V2 = "dlparse_v2"
-
-
-# Define an enum for the ocr engines
-class OcrEngine(str, Enum):
-    EASYOCR = "easyocr"
-    TESSERACT_CLI = "tesseract_cli"
-    TESSERACT = "tesseract"
-    OCRMAC = "ocrmac"
-    RAPIDOCR = "rapidocr"
-
-
 def export_documents(
     conv_results: Iterable[ConversionResult],
     output_dir: Path,
@@ -264,6 +250,13 @@ def convert(
             help="Show version information.",
         ),
     ] = None,
+    document_timeout: Annotated[
+        Optional[float],
+        typer.Option(
+            ...,
+            help="The timeout for processing each document, in seconds.",
+        ),
+    ] = None,
 ):
     if verbose == 0:
         logging.basicConfig(level=logging.WARNING)
@@ -347,6 +340,7 @@ def convert(
             do_ocr=ocr,
             ocr_options=ocr_options,
             do_table_structure=True,
+            document_timeout=document_timeout,
         )
         pipeline_options.table_structure_options.do_cell_matching = (
             True  # do_cell_matching

docling/datamodel/base_models.py

@@ -19,12 +19,12 @@ if TYPE_CHECKING:
 
 
 class ConversionStatus(str, Enum):
-    PENDING = auto()
-    STARTED = auto()
-    FAILURE = auto()
-    SUCCESS = auto()
-    PARTIAL_SUCCESS = auto()
-    SKIPPED = auto()
+    PENDING = "pending"
+    STARTED = "started"
+    FAILURE = "failure"
+    SUCCESS = "success"
+    PARTIAL_SUCCESS = "partial_success"
+    SKIPPED = "skipped"
 
 
 class InputFormat(str, Enum):
@@ -89,15 +89,15 @@ MimeTypeToFormat = {
 
 
 class DocInputType(str, Enum):
-    PATH = auto()
-    STREAM = auto()
+    PATH = "path"
+    STREAM = "stream"
 
 
 class DoclingComponentType(str, Enum):
-    DOCUMENT_BACKEND = auto()
-    MODEL = auto()
-    DOC_ASSEMBLER = auto()
-    USER_INPUT = auto()
+    DOCUMENT_BACKEND = "document_backend"
+    MODEL = "model"
+    DOC_ASSEMBLER = "doc_assembler"
+    USER_INPUT = "user_input"
 
 
 class ErrorItem(BaseModel):

docling/datamodel/pipeline_options.py

@@ -126,12 +126,33 @@ class OcrMacOptions(OcrOptions):
     )
 
 
+# Define an enum for the backend options
+class PdfBackend(str, Enum):
+    """Enum of valid PDF backends."""
+
+    PYPDFIUM2 = "pypdfium2"
+    DLPARSE_V1 = "dlparse_v1"
+    DLPARSE_V2 = "dlparse_v2"
+
+
+# Define an enum for the ocr engines
+class OcrEngine(str, Enum):
+    """Enum of valid OCR engines."""
+
+    EASYOCR = "easyocr"
+    TESSERACT_CLI = "tesseract_cli"
+    TESSERACT = "tesseract"
+    OCRMAC = "ocrmac"
+    RAPIDOCR = "rapidocr"
+
+
 class PipelineOptions(BaseModel):
     """Base pipeline options."""
 
     create_legacy_output: bool = (
-        True  # This defautl will be set to False on a future version of docling
+        True  # This default will be set to False on a future version of docling
     )
+    document_timeout: Optional[float] = None
 
 
 class PdfPipelineOptions(PipelineOptions):

docling/models/ds_glm_model.py

@@ -3,8 +3,7 @@ import random
 from pathlib import Path
 from typing import List, Union
 
-from deepsearch_glm.nlp_utils import init_nlp_model
-from deepsearch_glm.utils.load_pretrained_models import load_pretrained_nlp_models
+from deepsearch_glm.andromeda_nlp import nlp_model
 from docling_core.types.doc import BoundingBox, CoordOrigin, DoclingDocument
 from docling_core.types.legacy_doc.base import BoundingBox as DsBoundingBox
 from docling_core.types.legacy_doc.base import (
@@ -43,9 +42,7 @@ class GlmModel:
     def __init__(self, options: GlmOptions):
         self.options = options
 
-        if self.options.model_names != "":
-            load_pretrained_nlp_models()
-        self.model = init_nlp_model(model_names=self.options.model_names)
+        self.model = nlp_model(loglevel="error", text_ordering=True)
 
     def _to_legacy_document(self, conv_res) -> DsDocument:
         title = ""

docling/models/rapid_ocr_model.py

@@ -118,24 +118,25 @@ class RapidOcrModel(BaseOcrModel):
                         del high_res_image
                         del im
 
-                        cells = [
-                            OcrCell(
-                                id=ix,
-                                text=line[1],
-                                confidence=line[2],
-                                bbox=BoundingBox.from_tuple(
-                                    coord=(
-                                        (line[0][0][0] / self.scale) + ocr_rect.l,
-                                        (line[0][0][1] / self.scale) + ocr_rect.t,
-                                        (line[0][2][0] / self.scale) + ocr_rect.l,
-                                        (line[0][2][1] / self.scale) + ocr_rect.t,
+                        if result is not None:
+                            cells = [
+                                OcrCell(
+                                    id=ix,
+                                    text=line[1],
+                                    confidence=line[2],
+                                    bbox=BoundingBox.from_tuple(
+                                        coord=(
+                                            (line[0][0][0] / self.scale) + ocr_rect.l,
+                                            (line[0][0][1] / self.scale) + ocr_rect.t,
+                                            (line[0][2][0] / self.scale) + ocr_rect.l,
+                                            (line[0][2][1] / self.scale) + ocr_rect.t,
+                                        ),
+                                        origin=CoordOrigin.TOPLEFT,
                                     ),
-                                    origin=CoordOrigin.TOPLEFT,
-                                ),
-                            )
-                            for ix, line in enumerate(result)
-                        ]
-                        all_ocr_cells.extend(cells)
+                                )
+                                for ix, line in enumerate(result)
+                            ]
+                            all_ocr_cells.extend(cells)
 
                     # Post-process the cells
                     page.cells = self.post_process_cells(all_ocr_cells, page.cells)

docling/pipeline/base_pipeline.py

@@ -126,6 +126,7 @@ class PaginatedPipeline(BasePipeline):  # TODO this is a bad name.
             # conv_res.status = ConversionStatus.FAILURE
             # return conv_res
 
+        total_elapsed_time = 0.0
         with TimeRecorder(conv_res, "doc_build", scope=ProfilingScope.DOCUMENT):
 
             for i in range(0, conv_res.input.page_count):
@@ -136,7 +137,7 @@ class PaginatedPipeline(BasePipeline):  # TODO this is a bad name.
                 for page_batch in chunkify(
                     conv_res.pages, settings.perf.page_batch_size
                 ):
-                    start_pb_time = time.time()
+                    start_batch_time = time.monotonic()
 
                     # 1. Initialise the page resources
                     init_pages = map(
@@ -149,8 +150,21 @@ class PaginatedPipeline(BasePipeline):  # TODO this is a bad name.
                     for p in pipeline_pages:  # Must exhaust!
                         pass
 
-                    end_pb_time = time.time() - start_pb_time
-                    _log.debug(f"Finished converting page batch time={end_pb_time:.3f}")
+                    end_batch_time = time.monotonic()
+                    total_elapsed_time += end_batch_time - start_batch_time
+                    if (
+                        self.pipeline_options.document_timeout is not None
+                        and total_elapsed_time > self.pipeline_options.document_timeout
+                    ):
+                        _log.warning(
+                            f"Document processing time ({total_elapsed_time:.3f} seconds) exceeded the specified timeout of {self.pipeline_options.document_timeout:.3f} seconds"
+                        )
+                        conv_res.status = ConversionStatus.PARTIAL_SUCCESS
+                        break
+
+                    _log.debug(
+                        f"Finished converting page batch time={end_batch_time:.3f}"
+                    )
 
             except Exception as e:
                 conv_res.status = ConversionStatus.FAILURE

{docling-2.10.0.dist-info → docling-2.11.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling
-Version: 2.10.0
+Version: 2.11.0
 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.
 Home-page: https://github.com/DS4SD/docling
 License: MIT

{docling-2.10.0.dist-info → docling-2.11.0.dist-info}/RECORD

@@ -13,29 +13,29 @@ docling/backend/pdf_backend.py,sha256=unnw7QiRE1VXg6Pj-eYrtnFGrp5SSYiI324OlFxyv6
 docling/backend/pypdfium2_backend.py,sha256=B4bfv-dfzlWiKTfF8LN5fto_99YBu8A2c1_XIVwRUWI,8996
 docling/chunking/__init__.py,sha256=h83TDs0AuOV6oEPLAPrn9dpGKiU-2Vg6IRNo4cv6GDA,346
 docling/cli/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/cli/main.py,sha256=bLk1RG0jwM4dn6G5qa5Q-S4_N3agKnoE28pTfbpV4-k,14713
+docling/cli/main.py,sha256=FFDUDADvK7QNW7xCs6dlsC7Bt_BMyrKdbZewKTEjm54,14624
 docling/datamodel/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/datamodel/base_models.py,sha256=627IB8HZdXGmHNfsX4Qhf7kKSxx2btPjS7z8hitvhyE,5560
+docling/datamodel/base_models.py,sha256=vwy59eDrkzCSaay24RlUvx4zEyuaUukOdOhw3622u2I,5616
 docling/datamodel/document.py,sha256=GNlTsgKgDqdqv2dfhpYmnqymxDQWWWC8HgE8uAta8V4,10265
-docling/datamodel/pipeline_options.py,sha256=zQxLVioyBrldI4V9phQma1kTTgjmFQ6d3gVj2xq51gw,5010
+docling/datamodel/pipeline_options.py,sha256=1ouWNE5VhZolrWMb4RE6s_AxgNFr3_3PMtxB_YQ391A,5495
 docling/datamodel/settings.py,sha256=JK8lZPBjUx2kD2q-Qpg-o3vOElADMcyQbRUL0EHZ7us,1263
 docling/document_converter.py,sha256=Iz5eerBWFPVJoXAMlXEivRQX2VLBiUkA07BL4NNbaEs,11583
 docling/exceptions.py,sha256=-FoP46rFJgz_jn5uDv2V052udEEg8gckk6uhoItchXc,85
 docling/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/models/base_model.py,sha256=Yq_-FmUhqhE20vXYG3WiQXDRTIPjik1CyuEZ8iYTGAY,701
 docling/models/base_ocr_model.py,sha256=rGSpBF4dByITcsBaRIgvFKpiu0CrhmZS_PHIo686Dw0,6428
-docling/models/ds_glm_model.py,sha256=3UpFu3Oavw9p0GItx2S9R7bPDdjY2NvpUQQDSVMctys,12045
+docling/models/ds_glm_model.py,sha256=YJkGxV46wh7G2Wr4vVzt9b8oewkUDPWpvI6AEaZDrs0,11872
 docling/models/easyocr_model.py,sha256=c2m4x9dZpSc-cMgeEdFBRVBlB78uMGlYD8Q_2gzRuMU,3734
 docling/models/layout_model.py,sha256=ZvbTSyxvXB5yLHNEti0Wv3trz0vwGuHySI5TCdApb0U,14011
 docling/models/ocr_mac_model.py,sha256=bLP14UUmZcSzjDe-HLj-mtksTuBmsCTg2C1wCxUpan0,4502
 docling/models/page_assemble_model.py,sha256=kSGNiRKhmzkpFH7xCiT3rulMsgJmUXFa6Th_eB-cLEk,7103
 docling/models/page_preprocessing_model.py,sha256=1gVrZjObKxAvXkkKvXnIFApPOggzgiTFPtt1CGbMbSs,2763
-docling/models/rapid_ocr_model.py,sha256=VQ0jaFmOzB9f-1JaqZ6d0o_El55Lr-nsFHfTNubMAuc,6005
+docling/models/rapid_ocr_model.py,sha256=ui152cerv9b9OeWyyyefs8qMLwYn0qsE2DFE_gHmaCM,6124
 docling/models/table_structure_model.py,sha256=-ANSQpiN2avt3B9sbi7dHcoULUJbMBalAR5xxlrM7To,8421
 docling/models/tesseract_ocr_cli_model.py,sha256=aKQBaty4cYu6zG_C5uy6Zm3eeRQo5fxIierbKixa2kc,6622
 docling/models/tesseract_ocr_model.py,sha256=RDf6iV1q-oXaGfZXv0bW6SqjHNKQvBUDlUsOkuz0neY,6095
 docling/pipeline/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/pipeline/base_pipeline.py,sha256=IF1XWYgUGbdB4-teLkmM4Hvg_UNEfPrGuhExMRTUsk8,7168
+docling/pipeline/base_pipeline.py,sha256=hVvtk5E4DVZdl_SyNs_pYRUjN9C8PABhpVaeN5Z_fAY,7885
 docling/pipeline/simple_pipeline.py,sha256=mZqANqUtAOFAyqQEShErQnAUz6tJFOl6zVoazEDJ_wE,2254
 docling/pipeline/standard_pdf_pipeline.py,sha256=B1q8xt3Dfecpi8s8DrcfPzdATh8TYgL43FDzzcS4vEA,8885
 docling/py.typed,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
@@ -45,8 +45,8 @@ docling/utils/glm_utils.py,sha256=H1O_tDiRksMgw45rY9LhK6GjcZSOq5IyoGurGjoo-Ac,11
 docling/utils/layout_utils.py,sha256=vlN0rc8i0ayRGn3WnaG-pdmqEL00KKGl2zez3Gj-hrk,32074
 docling/utils/profiling.py,sha256=YaMGoB9MMZpagF9mb5ndoHj8Lpb9aIdb7El-Pl7IcFs,1753
 docling/utils/utils.py,sha256=llhXSbIDNZ1MHOwBEfLHBAoJIAYI7QlPIonlI1jLUJ0,1208
-docling-2.10.0.dist-info/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
-docling-2.10.0.dist-info/METADATA,sha256=YVI-dBKxqAxrLATigzeXPZvwDZUhLSl_doltc-HenQ4,7731
-docling-2.10.0.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-docling-2.10.0.dist-info/entry_points.txt,sha256=VOSzV77znM52dz5ysaDuJ0ijl1cnfrh1ZPg8od5OcTs,48
-docling-2.10.0.dist-info/RECORD,,
+docling-2.11.0.dist-info/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
+docling-2.11.0.dist-info/METADATA,sha256=ajUVy5CuNDUp0x9tMCqO2px2M-ia-Vs7frIyb0_HxMo,7731
+docling-2.11.0.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+docling-2.11.0.dist-info/entry_points.txt,sha256=VOSzV77znM52dz5ysaDuJ0ijl1cnfrh1ZPg8od5OcTs,48
+docling-2.11.0.dist-info/RECORD,,