docling 2.3.0__tar.gz → 2.3.1__tar.gz

{docling-2.3.0 → docling-2.3.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling
-Version: 2.3.0
+Version: 2.3.1
 Summary: Docling PDF conversion package
 Home-page: https://github.com/DS4SD/docling
 License: MIT
@@ -23,9 +23,9 @@ Provides-Extra: tesserocr
 Requires-Dist: beautifulsoup4 (>=4.12.3,<5.0.0)
 Requires-Dist: certifi (>=2024.7.4)
 Requires-Dist: deepsearch-glm (>=0.26.1,<0.27.0)
-Requires-Dist: docling-core (>=2.2.3,<3.0.0)
-Requires-Dist: docling-ibm-models (>=2.0.1,<3.0.0)
-Requires-Dist: docling-parse (>=2.0.0,<3.0.0)
+Requires-Dist: docling-core (>=2.3.0,<3.0.0)
+Requires-Dist: docling-ibm-models (>=2.0.3,<3.0.0)
+Requires-Dist: docling-parse (>=2.0.2,<3.0.0)
 Requires-Dist: easyocr (>=1.7,<2.0)
 Requires-Dist: filetype (>=1.2.0,<2.0.0)
 Requires-Dist: huggingface_hub (>=0.23,<1)
@@ -41,10 +41,6 @@ Requires-Dist: requests (>=2.32.3,<3.0.0)
 Requires-Dist: rtree (>=1.3.0,<2.0.0)
 Requires-Dist: scipy (>=1.14.1,<2.0.0)
 Requires-Dist: tesserocr (>=2.7.1,<3.0.0) ; extra == "tesserocr"
-Requires-Dist: torch (>=2.2.2,<2.3.0) ; sys_platform == "darwin" and platform_machine == "x86_64"
-Requires-Dist: torch (>=2.2.2,<3.0.0) ; sys_platform != "darwin" or platform_machine != "x86_64"
-Requires-Dist: torchvision (>=0,<1) ; sys_platform != "darwin" or platform_machine != "x86_64"
-Requires-Dist: torchvision (>=0.17.2,<0.18.0) ; sys_platform == "darwin" and platform_machine == "x86_64"
 Requires-Dist: typer (>=0.12.5,<0.13.0)
 Project-URL: Repository, https://github.com/DS4SD/docling
 Description-Content-Type: text/markdown

{docling-2.3.0 → docling-2.3.1}/docling/document_converter.py

@@ -139,6 +139,10 @@ class DocumentConverter:
 
         self.initialized_pipelines: Dict[Type[BasePipeline], BasePipeline] = {}
 
+    def initialize_pipeline(self, format: InputFormat):
+        """Initialize the conversion pipeline for the selected format."""
+        self._get_pipeline(doc_format=format)
+
     @validate_call(config=ConfigDict(strict=True))
     def convert(
         self,
@@ -219,13 +223,13 @@ class DocumentConverter:
                 else:
                     _log.info(f"Skipped a document. We lost {elapsed:.2f} sec.")
 
-    def _get_pipeline(self, doc: InputDocument) -> Optional[BasePipeline]:
+    def _get_pipeline(self, doc_format: InputFormat) -> Optional[BasePipeline]:
         assert self.format_to_options is not None
 
-        fopt = self.format_to_options.get(doc.format)
+        fopt = self.format_to_options.get(doc_format)
 
         if fopt is None:
-            raise RuntimeError(f"Could not get pipeline for document {doc.file}")
+            raise RuntimeError(f"Could not get pipeline for {doc_format}")
         else:
             pipeline_class = fopt.pipeline_cls
             pipeline_options = fopt.pipeline_options
@@ -256,7 +260,7 @@ class DocumentConverter:
         self, in_doc: InputDocument, raises_on_error: bool
     ) -> ConversionResult:
         if in_doc.valid:
-            pipeline = self._get_pipeline(in_doc)
+            pipeline = self._get_pipeline(in_doc.format)
             if pipeline is None:  # Can't find a default pipeline. Should this raise?
                 if raises_on_error:
                     raise RuntimeError(

{docling-2.3.0 → docling-2.3.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "docling"
-version = "2.3.0"  # DO NOT EDIT, updated automatically
+version = "2.3.1"  # DO NOT EDIT, updated automatically
 description = "Docling PDF conversion package"
 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>", "Peter Staar <taa@zurich.ibm.com>"]
 license = "MIT"
@@ -21,24 +21,13 @@ keywords= ["docling", "convert", "document", "pdf", "layout model", "segmentatio
 packages = [{include = "docling"}]
 
 [tool.poetry.dependencies]
-##############
-# constraints:
-##############
-torch = [
-  {version = "^2.2.2", optional = true, markers = "sys_platform != 'darwin' or platform_machine != 'x86_64'"},
-  {version = "~2.2.2", optional = true, markers = "sys_platform == 'darwin' and platform_machine == 'x86_64'"}
-]
-torchvision = [
-  {version = "^0", optional = true, markers = "sys_platform != 'darwin' or platform_machine != 'x86_64'"},
-  {version = "~0.17.2", optional = true, markers = "sys_platform == 'darwin' and platform_machine == 'x86_64'"}
-]
 ######################
 # actual dependencies:
 ######################
 python = "^3.10"
 pydantic = "^2.0.0"
-docling-core = "^2.2.3"
-docling-ibm-models = "^2.0.1"
+docling-core = "^2.3.0"
+docling-ibm-models = "^2.0.3"
 deepsearch-glm = "^0.26.1"
 filetype = "^1.2.0"
 pypdfium2 = "^4.30.0"
@@ -47,7 +36,7 @@ huggingface_hub = ">=0.23,<1"
 requests = "^2.32.3"
 easyocr = "^1.7"
 tesserocr = { version = "^2.7.1", optional = true }
-docling-parse = "^2.0.0"
+docling-parse = "^2.0.2"
 certifi = ">=2024.7.4"
 rtree = "^1.3.0"
 scipy = "^1.14.1"
@@ -94,6 +83,19 @@ langchain-huggingface = "^0.0.3"
 langchain-milvus = "^0.1.4"
 langchain-text-splitters = "^0.2.4"
 
+[tool.poetry.group.mac_intel]
+optional = true
+
+[tool.poetry.group.mac_intel.dependencies]
+torch = [
+  {markers = "sys_platform != 'darwin' or platform_machine != 'x86_64'", version = "^2.2.2"},
+  {markers = "sys_platform == 'darwin' and platform_machine == 'x86_64'", version = "~2.2.2"}
+]
+torchvision = [
+  {markers = "sys_platform != 'darwin' or platform_machine != 'x86_64'", version = "^0"},
+  {markers = "sys_platform == 'darwin' and platform_machine == 'x86_64'", version = "~0.17.2"}
+]
+
 [tool.poetry.extras]
 tesserocr = ["tesserocr"]