docling 2.31.1__tar.gz → 2.32.0__tar.gz

{docling-2.31.1 → docling-2.32.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling
-Version: 2.31.1
+Version: 2.32.0
 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/docling-project/docling
 License: MIT
@@ -28,6 +28,7 @@ Provides-Extra: vlm
 Requires-Dist: accelerate (>=1.2.1,<2.0.0) ; (sys_platform != "darwin" or platform_machine != "x86_64") and (extra == "vlm")
 Requires-Dist: beautifulsoup4 (>=4.12.3,<5.0.0)
 Requires-Dist: certifi (>=2024.7.4)
+Requires-Dist: click (<8.2.0)
 Requires-Dist: docling-core[chunking] (>=2.26.0,<3.0.0)
 Requires-Dist: docling-ibm-models (>=3.4.0,<4.0.0)
 Requires-Dist: docling-parse (>=4.0.0,<5.0.0)

{docling-2.31.1 → docling-2.32.0}/docling/backend/asciidoc_backend.py

@@ -287,7 +287,7 @@ class AsciiDocBackend(DeclarativeDocumentBackend):
 
     #   =========   Section headers
     def _is_section_header(self, line):
-        return re.match(r"^==+", line)
+        return re.match(r"^==+\s+", line)
 
     def _parse_section_header(self, line):
         match = re.match(r"^(=+)\s+(.*)", line)

{docling-2.31.1 → docling-2.32.0}/docling/datamodel/base_models.py

@@ -90,6 +90,7 @@ FormatToMimeType: Dict[InputFormat, List[str]] = {
         "image/tiff",
         "image/gif",
         "image/bmp",
+        "image/webp",
     ],
     InputFormat.PDF: ["application/pdf"],
     InputFormat.ASCIIDOC: ["text/asciidoc"],

{docling-2.31.1 → docling-2.32.0}/docling/datamodel/pipeline_options.py

@@ -225,6 +225,7 @@ class PictureDescriptionApiOptions(PictureDescriptionBaseOptions):
     headers: Dict[str, str] = {}
     params: Dict[str, Any] = {}
     timeout: float = 20
+    concurrency: int = 1
 
     prompt: str = "Describe this image in a few sentences."
     provenance: str = ""
@@ -295,6 +296,7 @@ class ApiVlmOptions(BaseVlmOptions):
     params: Dict[str, Any] = {}
     scale: float = 2.0
     timeout: float = 60
+    concurrency: int = 1
     response_format: ResponseFormat
 
 

{docling-2.31.1 → docling-2.32.0}/docling/datamodel/settings.py

@@ -56,13 +56,15 @@ class DebugSettings(BaseModel):
 
 
 class AppSettings(BaseSettings):
-    model_config = SettingsConfigDict(env_prefix="DOCLING_", env_nested_delimiter="_")
+    model_config = SettingsConfigDict(
+        env_prefix="DOCLING_", env_nested_delimiter="_", env_nested_max_split=1
+    )
 
-    perf: BatchConcurrencySettings
-    debug: DebugSettings
+    perf: BatchConcurrencySettings = BatchConcurrencySettings()
+    debug: DebugSettings = DebugSettings()
 
     cache_dir: Path = Path.home() / ".cache" / "docling"
     artifacts_path: Optional[Path] = None
 
 
-settings = AppSettings(perf=BatchConcurrencySettings(), debug=DebugSettings())
+settings = AppSettings()

{docling-2.31.1 → docling-2.32.0}/docling/models/api_vlm_model.py

@@ -1,4 +1,5 @@
 from collections.abc import Iterable
+from concurrent.futures import ThreadPoolExecutor
 
 from docling.datamodel.base_models import Page, VlmPrediction
 from docling.datamodel.document import ConversionResult
@@ -27,6 +28,7 @@ class ApiVlmModel(BasePageModel):
                 )
 
             self.timeout = self.vlm_options.timeout
+            self.concurrency = self.vlm_options.concurrency
             self.prompt_content = (
                 f"This is a page from a document.\n{self.vlm_options.prompt}"
             )
@@ -38,10 +40,10 @@ class ApiVlmModel(BasePageModel):
     def __call__(
         self, conv_res: ConversionResult, page_batch: Iterable[Page]
     ) -> Iterable[Page]:
-        for page in page_batch:
+        def _vlm_request(page):
             assert page._backend is not None
             if not page._backend.is_valid():
-                yield page
+                return page
             else:
                 with TimeRecorder(conv_res, "vlm"):
                     assert page.size is not None
@@ -63,4 +65,7 @@ class ApiVlmModel(BasePageModel):
 
                     page.predictions.vlm_response = VlmPrediction(text=page_tags)
 
-                yield page
+                return page
+
+        with ThreadPoolExecutor(max_workers=self.concurrency) as executor:
+            yield from executor.map(_vlm_request, page_batch)

{docling-2.31.1 → docling-2.32.0}/docling/models/picture_description_api_model.py

@@ -1,4 +1,5 @@
 from collections.abc import Iterable
+from concurrent.futures import ThreadPoolExecutor
 from pathlib import Path
 from typing import Optional, Type, Union
 
@@ -37,6 +38,7 @@ class PictureDescriptionApiModel(PictureDescriptionBaseModel):
             accelerator_options=accelerator_options,
         )
         self.options: PictureDescriptionApiOptions
+        self.concurrency = self.options.concurrency
 
         if self.enabled:
             if not enable_remote_services:
@@ -48,8 +50,8 @@ class PictureDescriptionApiModel(PictureDescriptionBaseModel):
     def _annotate_images(self, images: Iterable[Image.Image]) -> Iterable[str]:
         # Note: technically we could make a batch request here,
         # but not all APIs will allow for it. For example, vllm won't allow more than 1.
-        for image in images:
-            yield api_image_request(
+        def _api_request(image):
+            return api_image_request(
                 image=image,
                 prompt=self.options.prompt,
                 url=self.options.url,
@@ -57,3 +59,6 @@ class PictureDescriptionApiModel(PictureDescriptionBaseModel):
                 headers=self.options.headers,
                 **self.options.params,
             )
+
+        with ThreadPoolExecutor(max_workers=self.concurrency) as executor:
+            yield from executor.map(_api_request, images)

{docling-2.31.1 → docling-2.32.0}/docling/models/tesseract_ocr_cli_model.py

@@ -249,7 +249,7 @@ class TesseractOcrCliModel(BaseOcrModel):
                             cell = TextCell(
                                 index=ix,
                                 text=str(text),
-                                orig=text,
+                                orig=str(text),
                                 from_ocr=True,
                                 confidence=conf / 100.0,
                                 rect=BoundingRectangle.from_bounding_box(

{docling-2.31.1 → docling-2.32.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "docling"
-version = "2.31.1"  # DO NOT EDIT, updated automatically
+version = "2.32.0"  # 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>",
@@ -90,6 +90,7 @@ pillow = ">=10.0.0,<12.0.0"
 tqdm = "^4.65.0"
 pluggy = "^1.0.0"
 pylatexenc = "^2.10"
+click = "<8.2.0"
 
 [tool.poetry.group.dev.dependencies]
 python = "^3.9.2"