docling 2.10.0__tar.gz → 2.11.0__tar.gz

{docling-2.10.0 → docling-2.11.0}/PKG-INFO

@@ -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 → docling-2.11.0}/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-2.10.0 → docling-2.11.0}/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-2.10.0 → docling-2.11.0}/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-2.10.0 → docling-2.11.0}/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-2.10.0 → docling-2.11.0}/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-2.10.0 → docling-2.11.0}/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 → docling-2.11.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "docling"
-version = "2.10.0"  # DO NOT EDIT, updated automatically
+version = "2.11.0"  # DO NOT EDIT, updated automatically
 description = "SDK and CLI for parsing PDF, DOCX, HTML, and more, to a unified document representation for powering downstream workflows such as gen AI applications."
 authors = ["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 = "MIT"