docling 2.31.2__py3-none-any.whl → 2.32.0__py3-none-any.whl

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/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/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/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/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/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-2.31.2.dist-info → docling-2.32.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling
-Version: 2.31.2
+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

{docling-2.31.2.dist-info → docling-2.32.0.dist-info}/RECORD

@@ -28,14 +28,14 @@ docling/cli/main.py,sha256=D7WEY4x6pQCVFRy3peK9KUDOb0Y5IVc-vTDqPnHPK00,26138
 docling/cli/models.py,sha256=9yLGp6QRJGpR86U3SjmWAXDt3MvBaJLLY4xDVdsu3O8,4160
 docling/cli/tools.py,sha256=QhtRxQG0TVrfsMqdv5i7J0_qQy1ZZyWYnHPwJl7b5oY,322
 docling/datamodel/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/datamodel/base_models.py,sha256=DRE_XoldtCreWF4ucO0iK0l8uOnfvnhQaYjV0z1Qe0M,7921
+docling/datamodel/base_models.py,sha256=3BmGoV2HLXOWFuRHFAa42YnWceh-JEpcLXzfFz9AD9Y,7943
 docling/datamodel/document.py,sha256=_0Z4zUgCB5677ZW8Y7C1fv75enLZJOJUjcUkGTSiTBA,15553
-docling/datamodel/pipeline_options.py,sha256=-1QG8dY0RZkTJb66lXErEAnPq4F_1vgnk_5AcIr3cgU,13350
-docling/datamodel/settings.py,sha256=bNMdowIKv7RUchabQTo4rFNEsxfB6pGg2LoZSY634zo,1869
+docling/datamodel/pipeline_options.py,sha256=uwjBvK4egrgcF1_w4B5EDxpGnl4IgBzmxP7dJ7zm394,13400
+docling/datamodel/settings.py,sha256=ajMz7Ao2m0ZGYkfArqTDDbiF89O408mtgeh06PUi0MA,1900
 docling/document_converter.py,sha256=PRRr65nigQ3LZDl4G2fBMkOtJyswT7xyGt7fpUeDO3w,13849
 docling/exceptions.py,sha256=K1WnCS1leK2JtMB5ewZWKkb0EaijFgl-tRzrO9ntgPM,134
 docling/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/models/api_vlm_model.py,sha256=w1SzdG3Ypz_0iZGiX-skMwV1E1JnOHH2BJiNkcEEIAA,2478
+docling/models/api_vlm_model.py,sha256=TuLUR-EeUcoUkQKz5Tv6rvphhJKyQShpb99d7bVTdJE,2728
 docling/models/base_model.py,sha256=Zx_nByGYkubTvvYiQxwiB6P8lc7wOD4ZTC2QIw6vCEg,2950
 docling/models/base_ocr_model.py,sha256=_iD8QCKQdv2VWrIuSRPyGP4oCz94h84WriHg9F2k-Z0,7172
 docling/models/code_formula_model.py,sha256=9cplJFvP7jcJGz-p-MmL8_lqUhmaXZu7wKyX2aOTujs,11504
@@ -51,7 +51,7 @@ docling/models/layout_model.py,sha256=0fiJXJ4aPmcMsYY7rbN9LJ2mZ0_8G0ODY9kyNTAN3W
 docling/models/ocr_mac_model.py,sha256=A3TlEbvvwhkWiq9YARos3Y9yNcpPYQ7JGc_4hFtAK-8,5370
 docling/models/page_assemble_model.py,sha256=GO7JI1D6T6EkSW94cLQobPGNQUahkxQqTPRwj5CnmFE,6304
 docling/models/page_preprocessing_model.py,sha256=6pOGXiFQ-oz06UmJdcaYMdVyfZ0YVLWS6efGcx7Mxws,3105
-docling/models/picture_description_api_model.py,sha256=qs3n0smC9DXhzwJeK_iQG08Y6ZFHInKtdGPVhzgvxgU,2091
+docling/models/picture_description_api_model.py,sha256=kCuAFOGEuI5QsRul7Pc1LccxWN7WIvIUhXEmSICYegw,2332
 docling/models/picture_description_base_model.py,sha256=FbBVXzAOB87xpJN28tuGCxoAdcf6mZNUOqJR7ljUg5g,2946
 docling/models/picture_description_vlm_model.py,sha256=DiTjnehVy1n0N04xPUvZl8rx4TiNHzHn9Cnzy_ePGts,4177
 docling/models/plugins/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -59,7 +59,7 @@ docling/models/plugins/defaults.py,sha256=qslXGnRX07Z3GGttNriqaox0v0vXp4zs4KLurH
 docling/models/rapid_ocr_model.py,sha256=Tq_1Egu5Hjx7Y69Vox17QTtRXztSyflB1fhN08CWQwY,5894
 docling/models/readingorder_model.py,sha256=S9ru2ApY9sE-Uue3hptWHmbmElwo36bUbAikxCFpHYs,14574
 docling/models/table_structure_model.py,sha256=1gxLaooK0IKMrnmS8nT1BItKqt1GAKghfpmLKb3i53g,12566
-docling/models/tesseract_ocr_cli_model.py,sha256=iFdOud5ymoW9WV8bWLCDpd3LJBo9M5bTT5vc635zEDY,10229
+docling/models/tesseract_ocr_cli_model.py,sha256=LXYUCMQAPxQA2pY3zs9wcPSrAHHorTffSmIIWgltoaw,10234
 docling/models/tesseract_ocr_model.py,sha256=72009TJL_7tXTEnhlsGRiw_KibrQ0LjZlCBtW8NtwUc,9339
 docling/pipeline/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/pipeline/base_pipeline.py,sha256=DnuxAf7EQusdSRae0QUVth-0f2mSff8JZjX-2vazk00,8751
@@ -79,8 +79,8 @@ docling/utils/ocr_utils.py,sha256=F7iOOjqolUcImUzir4qjDQd4QWSO3s6JC4WRn3U7uY4,26
 docling/utils/profiling.py,sha256=YaMGoB9MMZpagF9mb5ndoHj8Lpb9aIdb7El-Pl7IcFs,1753
 docling/utils/utils.py,sha256=kJtIYuzXeOyJHYlxmLAo7dGM5rEsDa1i84qEsUj1nio,1908
 docling/utils/visualization.py,sha256=tY2ylE2aiQKkmzlSLnFW-HTfFyqUUMguW18ldd1PLfo,2868
-docling-2.31.2.dist-info/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
-docling-2.31.2.dist-info/METADATA,sha256=V11tJajepssRJ-ltuRsNThmo9_6U6Gc28wqZlgDzdz0,10138
-docling-2.31.2.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
-docling-2.31.2.dist-info/entry_points.txt,sha256=pIxel-UeVo1S7FhoNG5xgEfPjLZfBLi_N9TsGPtJSLo,144
-docling-2.31.2.dist-info/RECORD,,
+docling-2.32.0.dist-info/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
+docling-2.32.0.dist-info/METADATA,sha256=Nd6x_-yL4ghk90c6Z--1nrkq6_8TpojB6K9iyDYQ2KM,10138
+docling-2.32.0.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
+docling-2.32.0.dist-info/entry_points.txt,sha256=pIxel-UeVo1S7FhoNG5xgEfPjLZfBLi_N9TsGPtJSLo,144
+docling-2.32.0.dist-info/RECORD,,