docling 2.47.0__tar.gz → 2.47.1__tar.gz

{docling-2.47.0 → docling-2.47.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: docling
-Version: 2.47.0
+Version: 2.47.1
 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
@@ -59,7 +59,7 @@ Provides-Extra: vlm
 Requires-Dist: transformers<5.0.0,>=4.46.0; extra == "vlm"
 Requires-Dist: accelerate<2.0.0,>=1.2.1; extra == "vlm"
 Requires-Dist: mlx-vlm<1.0.0,>=0.3.0; (python_version >= "3.10" and sys_platform == "darwin" and platform_machine == "arm64") and extra == "vlm"
-Requires-Dist: vllm<1.0.0,>=0.10.0; (python_version >= "3.10" and sys_platform == "linux") and extra == "vlm"
+Requires-Dist: vllm<1.0.0,>=0.10.0; (python_version >= "3.10" and sys_platform == "linux" and platform_machine == "x86_64") and extra == "vlm"
 Provides-Extra: rapidocr
 Requires-Dist: rapidocr-onnxruntime<2.0.0,>=1.4.0; python_version < "3.13" and extra == "rapidocr"
 Requires-Dist: onnxruntime<2.0.0,>=1.7.0; extra == "rapidocr"

{docling-2.47.0 → docling-2.47.1}/docling/pipeline/base_pipeline.py

@@ -146,6 +146,7 @@ class PaginatedPipeline(BasePipeline):  # TODO this is a bad name.
                     conv_res.pages.append(Page(page_no=i))
 
             try:
+                total_pages_processed = 0
                 # Iterate batches of pages (page_batch_size) in the doc
                 for page_batch in chunkify(
                     conv_res.pages, settings.perf.page_batch_size
@@ -186,9 +187,9 @@ class PaginatedPipeline(BasePipeline):  # TODO this is a bad name.
                         )
                         conv_res.status = ConversionStatus.PARTIAL_SUCCESS
                         break
-
+                    total_pages_processed += len(page_batch)
                     _log.debug(
-                        f"Finished converting page batch time={end_batch_time:.3f}"
+                        f"Finished converting pages {total_pages_processed}/{len(conv_res.pages)} time={end_batch_time:.3f}"
                     )
 
             except Exception as e:

{docling-2.47.0 → docling-2.47.1}/docling.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: docling
-Version: 2.47.0
+Version: 2.47.1
 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
@@ -59,7 +59,7 @@ Provides-Extra: vlm
 Requires-Dist: transformers<5.0.0,>=4.46.0; extra == "vlm"
 Requires-Dist: accelerate<2.0.0,>=1.2.1; extra == "vlm"
 Requires-Dist: mlx-vlm<1.0.0,>=0.3.0; (python_version >= "3.10" and sys_platform == "darwin" and platform_machine == "arm64") and extra == "vlm"
-Requires-Dist: vllm<1.0.0,>=0.10.0; (python_version >= "3.10" and sys_platform == "linux") and extra == "vlm"
+Requires-Dist: vllm<1.0.0,>=0.10.0; (python_version >= "3.10" and sys_platform == "linux" and platform_machine == "x86_64") and extra == "vlm"
 Provides-Extra: rapidocr
 Requires-Dist: rapidocr-onnxruntime<2.0.0,>=1.4.0; python_version < "3.13" and extra == "rapidocr"
 Requires-Dist: onnxruntime<2.0.0,>=1.7.0; extra == "rapidocr"

{docling-2.47.0 → docling-2.47.1}/docling.egg-info/requires.txt

@@ -49,5 +49,5 @@ accelerate<2.0.0,>=1.2.1
 [vlm:python_version >= "3.10" and sys_platform == "darwin" and platform_machine == "arm64"]
 mlx-vlm<1.0.0,>=0.3.0
 
-[vlm:python_version >= "3.10" and sys_platform == "linux"]
+[vlm:python_version >= "3.10" and sys_platform == "linux" and platform_machine == "x86_64"]
 vllm<1.0.0,>=0.10.0

{docling-2.47.0 → docling-2.47.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "docling"
-version = "2.47.0"  # DO NOT EDIT, updated automatically
+version = "2.47.1"  # 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."
 license = "MIT"
 keywords = [
@@ -93,7 +93,7 @@ vlm = [
   'transformers (>=4.46.0,<5.0.0)',
   'accelerate (>=1.2.1,<2.0.0)',
   'mlx-vlm (>=0.3.0,<1.0.0) ; python_version >= "3.10" and sys_platform == "darwin" and platform_machine == "arm64"',
-  'vllm (>=0.10.0,<1.0.0) ; python_version >= "3.10" and sys_platform == "linux"',
+  'vllm (>=0.10.0,<1.0.0) ; python_version >= "3.10" and sys_platform == "linux" and platform_machine == "x86_64"',
 ]
 rapidocr = [
   'rapidocr-onnxruntime (>=1.4.0,<2.0.0) ; python_version < "3.13"',