Merge from main

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

CHANGELOG.md

@@ -1,3 +1,19 @@
+## [v2.11.0](https://github.com/DS4SD/docling/releases/tag/v2.11.0) - 2024-12-12
+
+### Feature
+
+* Add timeout limit to document parsing job. DS4SD#270 ([#552](https://github.com/DS4SD/docling/issues/552)) ([`3da166e`](https://github.com/DS4SD/docling/commit/3da166eafa3c119de961510341cb92397652c222))
+
+### Fix
+
+* Do not import python modules from deepsearch-glm ([#569](https://github.com/DS4SD/docling/issues/569)) ([`aee9c0b`](https://github.com/DS4SD/docling/commit/aee9c0b324a07190ad03ad3a6266e76c465d4cdf))
+* Handle no result from RapidOcr reader ([#558](https://github.com/DS4SD/docling/issues/558)) ([`f45499c`](https://github.com/DS4SD/docling/commit/f45499ce9349fe55538dfb36d74c395e9193d9b1))
+* Make enum serializable with human-readable value ([#555](https://github.com/DS4SD/docling/issues/555)) ([`a7df337`](https://github.com/DS4SD/docling/commit/a7df337654fa5fa7633af8740fb5e4cc4a06f250))
+
+### Documentation
+
+* Update chunking usage docs, minor reorg ([#550](https://github.com/DS4SD/docling/issues/550)) ([`d0c9e8e`](https://github.com/DS4SD/docling/commit/d0c9e8e508d7edef5e733be6cdea2cea0a9a0695))
+
 ## [v2.10.0](https://github.com/DS4SD/docling/releases/tag/v2.10.0) - 2024-12-09
 
 ### Feature

docling/cli/main.py

@@ -256,6 +256,13 @@ def convert(
     device: Annotated[
         AcceleratorDevice, typer.Option(..., help="Accelerator device")
     ] = AcceleratorDevice.AUTO,
+    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)
@@ -341,6 +348,7 @@ 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/pipeline_options.py

@@ -214,9 +214,10 @@ 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
     )
     accelerator_options: AcceleratorOptions = AcceleratorOptions()
+    document_timeout: Optional[float] = None
 
 
 class PdfPipelineOptions(PipelineOptions):

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
+                    end_batch_time = time.monotonic()
-                    _log.debug(f"Finished converting page batch time={end_pb_time:.3f}")
+                    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

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"