docling 2.2.1__py3-none-any.whl → 2.3.0__py3-none-any.whl

docling/pipeline/standard_pdf_pipeline.py

@@ -7,7 +7,7 @@ from docling_core.types.doc import DocItem, ImageRef, PictureItem, TableItem
 from docling.backend.abstract_backend import AbstractDocumentBackend
 from docling.backend.pdf_backend import PdfDocumentBackend
 from docling.datamodel.base_models import AssembledUnit, Page
-from docling.datamodel.document import ConversionResult, InputDocument
+from docling.datamodel.document import ConversionResult
 from docling.datamodel.pipeline_options import (
     EasyOcrOptions,
     PdfPipelineOptions,
@@ -27,6 +27,7 @@ from docling.models.table_structure_model import TableStructureModel
 from docling.models.tesseract_ocr_cli_model import TesseractOcrCliModel
 from docling.models.tesseract_ocr_model import TesseractOcrModel
 from docling.pipeline.base_pipeline import PaginatedPipeline
+from docling.utils.profiling import ProfilingScope, TimeRecorder
 
 _log = logging.getLogger(__name__)
 
@@ -119,73 +120,75 @@ class StandardPdfPipeline(PaginatedPipeline):
             )
         return None
 
-    def initialize_page(self, doc: InputDocument, page: Page) -> Page:
-        page._backend = doc._backend.load_page(page.page_no)  # type: ignore
-        if page._backend is not None and page._backend.is_valid():
-            page.size = page._backend.get_size()
+    def initialize_page(self, conv_res: ConversionResult, page: Page) -> Page:
+        with TimeRecorder(conv_res, "page_init"):
+            page._backend = conv_res.input._backend.load_page(page.page_no)  # type: ignore
+            if page._backend is not None and page._backend.is_valid():
+                page.size = page._backend.get_size()
 
         return page
 
-    def _assemble_document(
-        self, in_doc: InputDocument, conv_res: ConversionResult
-    ) -> ConversionResult:
+    def _assemble_document(self, conv_res: ConversionResult) -> ConversionResult:
         all_elements = []
         all_headers = []
         all_body = []
 
-        for p in conv_res.pages:
-            if p.assembled is not None:
-                for el in p.assembled.body:
-                    all_body.append(el)
-                for el in p.assembled.headers:
-                    all_headers.append(el)
-                for el in p.assembled.elements:
-                    all_elements.append(el)
-
-        conv_res.assembled = AssembledUnit(
-            elements=all_elements, headers=all_headers, body=all_body
-        )
-
-        conv_res.document = self.glm_model(conv_res)
+        with TimeRecorder(conv_res, "doc_assemble", scope=ProfilingScope.DOCUMENT):
+            for p in conv_res.pages:
+                if p.assembled is not None:
+                    for el in p.assembled.body:
+                        all_body.append(el)
+                    for el in p.assembled.headers:
+                        all_headers.append(el)
+                    for el in p.assembled.elements:
+                        all_elements.append(el)
+
+            conv_res.assembled = AssembledUnit(
+                elements=all_elements, headers=all_headers, body=all_body
+            )
 
-        # Generate page images in the output
-        if self.pipeline_options.generate_page_images:
-            for page in conv_res.pages:
-                assert page.image is not None
-                page_no = page.page_no + 1
-                conv_res.document.pages[page_no].image = ImageRef.from_pil(
-                    page.image, dpi=int(72 * self.pipeline_options.images_scale)
-                )
+            conv_res.document = self.glm_model(conv_res)
 
-        # Generate images of the requested element types
-        if (
-            self.pipeline_options.generate_picture_images
-            or self.pipeline_options.generate_table_images
-        ):
-            scale = self.pipeline_options.images_scale
-            for element, _level in conv_res.document.iterate_items():
-                if not isinstance(element, DocItem) or len(element.prov) == 0:
-                    continue
-                if (
-                    isinstance(element, PictureItem)
-                    and self.pipeline_options.generate_picture_images
-                ) or (
-                    isinstance(element, TableItem)
-                    and self.pipeline_options.generate_table_images
-                ):
-                    page_ix = element.prov[0].page_no - 1
-                    page = conv_res.pages[page_ix]
-                    assert page.size is not None
+            # Generate page images in the output
+            if self.pipeline_options.generate_page_images:
+                for page in conv_res.pages:
                     assert page.image is not None
-
-                    crop_bbox = (
-                        element.prov[0]
-                        .bbox.scaled(scale=scale)
-                        .to_top_left_origin(page_height=page.size.height * scale)
+                    page_no = page.page_no + 1
+                    conv_res.document.pages[page_no].image = ImageRef.from_pil(
+                        page.image, dpi=int(72 * self.pipeline_options.images_scale)
                     )
 
-                    cropped_im = page.image.crop(crop_bbox.as_tuple())
-                    element.image = ImageRef.from_pil(cropped_im, dpi=int(72 * scale))
+            # Generate images of the requested element types
+            if (
+                self.pipeline_options.generate_picture_images
+                or self.pipeline_options.generate_table_images
+            ):
+                scale = self.pipeline_options.images_scale
+                for element, _level in conv_res.document.iterate_items():
+                    if not isinstance(element, DocItem) or len(element.prov) == 0:
+                        continue
+                    if (
+                        isinstance(element, PictureItem)
+                        and self.pipeline_options.generate_picture_images
+                    ) or (
+                        isinstance(element, TableItem)
+                        and self.pipeline_options.generate_table_images
+                    ):
+                        page_ix = element.prov[0].page_no - 1
+                        page = conv_res.pages[page_ix]
+                        assert page.size is not None
+                        assert page.image is not None
+
+                        crop_bbox = (
+                            element.prov[0]
+                            .bbox.scaled(scale=scale)
+                            .to_top_left_origin(page_height=page.size.height * scale)
+                        )
+
+                        cropped_im = page.image.crop(crop_bbox.as_tuple())
+                        element.image = ImageRef.from_pil(
+                            cropped_im, dpi=int(72 * scale)
+                        )
 
         return conv_res
 

docling/utils/profiling.py

@@ -0,0 +1,62 @@
+import time
+from datetime import datetime
+from enum import Enum
+from typing import TYPE_CHECKING, List
+
+import numpy as np
+from pydantic import BaseModel
+
+from docling.datamodel.settings import settings
+
+if TYPE_CHECKING:
+    from docling.datamodel.document import ConversionResult
+
+
+class ProfilingScope(str, Enum):
+    PAGE = "page"
+    DOCUMENT = "document"
+
+
+class ProfilingItem(BaseModel):
+    scope: ProfilingScope
+    count: int = 0
+    times: List[float] = []
+    start_timestamps: List[datetime] = []
+
+    def avg(self) -> float:
+        return np.average(self.times)  # type: ignore
+
+    def std(self) -> float:
+        return np.std(self.times)  # type: ignore
+
+    def mean(self) -> float:
+        return np.mean(self.times)  # type: ignore
+
+    def percentile(self, perc: float) -> float:
+        return np.percentile(self.times, perc)  # type: ignore
+
+
+class TimeRecorder:
+    def __init__(
+        self,
+        conv_res: "ConversionResult",
+        key: str,
+        scope: ProfilingScope = ProfilingScope.PAGE,
+    ):
+        if settings.debug.profile_pipeline_timings:
+            if key not in conv_res.timings.keys():
+                conv_res.timings[key] = ProfilingItem(scope=scope)
+            self.conv_res = conv_res
+            self.key = key
+
+    def __enter__(self):
+        if settings.debug.profile_pipeline_timings:
+            self.start = time.monotonic()
+            self.conv_res.timings[self.key].start_timestamps.append(datetime.utcnow())
+        return self
+
+    def __exit__(self, *args):
+        if settings.debug.profile_pipeline_timings:
+            elapsed = time.monotonic() - self.start
+            self.conv_res.timings[self.key].times.append(elapsed)
+            self.conv_res.timings[self.key].count += 1

{docling-2.2.1.dist-info → docling-2.3.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling
-Version: 2.2.1
+Version: 2.3.0
 Summary: Docling PDF conversion package
 Home-page: https://github.com/DS4SD/docling
 License: MIT
@@ -23,7 +23,7 @@ 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 (>=2.2.1,<3.0.0)
+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: easyocr (>=1.7,<2.0)
@@ -73,8 +73,9 @@ Docling parses documents and exports them to the desired format with ease and sp
 
 ## Features
 
-* 🗂️ Multi-format support for input (PDF, DOCX etc.) & output (Markdown, JSON etc.)
-* 📑 Advanced PDF document understanding incl. page layout, reading order & table structures
+* 🗂️ Reads popular document formats (PDF, DOCX, PPTX, Images, HTML, AsciiDoc, Markdown) and exports to Markdown and JSON
+* 📑 Advanced PDF document understanding including page layout, reading order & table structures
+* 🧩 Unified, expressive [DoclingDocument](https://ds4sd.github.io/docling/concepts/docling_document/) representation format
 * 📝 Metadata extraction, including title, authors, references & language
 * 🤖 Seamless LlamaIndex 🦙 & LangChain 🦜🔗 integration for powerful RAG / QA applications
 * 🔍 OCR support for scanned PDFs

docling-2.3.0.dist-info/RECORD

@@ -0,0 +1,45 @@
+docling/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+docling/backend/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+docling/backend/abstract_backend.py,sha256=-or6kWVV7egQeyIuN-vI0Tr7Q1htalBZSlhgq_G2RdU,1678
+docling/backend/asciidoc_backend.py,sha256=kXZxOLk_LvLFVZwnJVVwjmvc3QWZ0iiG7VnwjgtC3hI,14051
+docling/backend/docling_parse_backend.py,sha256=TaIMli9vePd3fz9L6S4t75JPYZDpgYBLRGfWjbc9Hbk,7632
+docling/backend/docling_parse_v2_backend.py,sha256=QlVU8NgqKvVCa99E8oDa2Xvy__kq30C-myGY3o9Qoq4,8588
+docling/backend/html_backend.py,sha256=p3WlYta1f3e4osmvVR12KIUYLJimveTX8UwEkyPt7_g,15161
+docling/backend/md_backend.py,sha256=tmuSCghjor9PqKIiVieCuZ4_t5JEjZMy3cq7u3yTgyU,14032
+docling/backend/mspowerpoint_backend.py,sha256=J472AIH_IXvGg3D0FDmXhue1At_VSBD6n15c64Kxttw,15446
+docling/backend/msword_backend.py,sha256=FAUdP74QxGKo2xMZQ4WQGYwtpIBCTJ_FG17PBpRwhxI,17230
+docling/backend/pdf_backend.py,sha256=unnw7QiRE1VXg6Pj-eYrtnFGrp5SSYiI324OlFxyv6c,2050
+docling/backend/pypdfium2_backend.py,sha256=MJX6fQqwK3r967fyAAs-RA_YIkeQvhgsLkQAgaBTgaE,8995
+docling/cli/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+docling/cli/main.py,sha256=NRVGz0z-3EBwYNMJGVnLtDBcfOeutaUyYdkM0ymRnGA,8008
+docling/datamodel/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+docling/datamodel/base_models.py,sha256=fmkS6iTxGZCTtNCo2zsgMmBC11Ogf2Ht-mNIlZ9GP-o,5375
+docling/datamodel/document.py,sha256=9dQf_J18X_MEWs-Mg3Ed6BykFPJ79ETmkkxcssY-vYo,20698
+docling/datamodel/pipeline_options.py,sha256=WNjluKC-Ww63ifkGMHwws8zIDHnOS1z5Hw7_j3S0qao,2446
+docling/datamodel/settings.py,sha256=2-sYEnKLV_giGygUlBtiBd4CJYN5T9-3BdL6NpWkUYw,1155
+docling/document_converter.py,sha256=Y0Tngh-seNSty7Ov71DDAJzbBgruoEdwYPunVn7DT00,10413
+docling/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+docling/models/base_model.py,sha256=Yq_-FmUhqhE20vXYG3WiQXDRTIPjik1CyuEZ8iYTGAY,701
+docling/models/base_ocr_model.py,sha256=Ti0glL-_DVRfmP3MpywYVmkNf5RP6qhRg_UKzJuV1Dc,5663
+docling/models/ds_glm_model.py,sha256=2OpWW8MMzCIshrtP36gDSRPYOCjv1ex34FqxD2nYjP4,11986
+docling/models/easyocr_model.py,sha256=23hWq484qVS3nkch6nRRWowfQamN-McFZgfbHfp5Vuo,3818
+docling/models/layout_model.py,sha256=ZvbTSyxvXB5yLHNEti0Wv3trz0vwGuHySI5TCdApb0U,14011
+docling/models/page_assemble_model.py,sha256=kSGNiRKhmzkpFH7xCiT3rulMsgJmUXFa6Th_eB-cLEk,7103
+docling/models/page_preprocessing_model.py,sha256=1gVrZjObKxAvXkkKvXnIFApPOggzgiTFPtt1CGbMbSs,2763
+docling/models/table_structure_model.py,sha256=-ANSQpiN2avt3B9sbi7dHcoULUJbMBalAR5xxlrM7To,8421
+docling/models/tesseract_ocr_cli_model.py,sha256=ZflwQcD7YjhPqEB8bbgNgP14OBD4NNEJefUS8Lbr5X0,6511
+docling/models/tesseract_ocr_model.py,sha256=AccCgaYNzGryiJnkwR4sv2FeOdlSgO3uspdQOmo1sNY,5569
+docling/pipeline/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+docling/pipeline/base_pipeline.py,sha256=IF1XWYgUGbdB4-teLkmM4Hvg_UNEfPrGuhExMRTUsk8,7168
+docling/pipeline/simple_pipeline.py,sha256=mZqANqUtAOFAyqQEShErQnAUz6tJFOl6zVoazEDJ_wE,2254
+docling/pipeline/standard_pdf_pipeline.py,sha256=h59eA0CLMYuuJoH-0SyCRkYEregNs6i0pa46Ioqf8kU,7947
+docling/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+docling/utils/export.py,sha256=KyGF1BVDHPFfHVXZc8vegsWlFfOgGPP2YckWpTadyI8,4694
+docling/utils/layout_utils.py,sha256=vlN0rc8i0ayRGn3WnaG-pdmqEL00KKGl2zez3Gj-hrk,32074
+docling/utils/profiling.py,sha256=YaMGoB9MMZpagF9mb5ndoHj8Lpb9aIdb7El-Pl7IcFs,1753
+docling/utils/utils.py,sha256=llhXSbIDNZ1MHOwBEfLHBAoJIAYI7QlPIonlI1jLUJ0,1208
+docling-2.3.0.dist-info/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
+docling-2.3.0.dist-info/METADATA,sha256=e3LTQgbktuUHzQlI4qXDhIDMGOX0duC1EJWws6j6_y8,6373
+docling-2.3.0.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+docling-2.3.0.dist-info/entry_points.txt,sha256=VOSzV77znM52dz5ysaDuJ0ijl1cnfrh1ZPg8od5OcTs,48
+docling-2.3.0.dist-info/RECORD,,

docling-2.2.1.dist-info/RECORD

@@ -1,44 +0,0 @@
-docling/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/backend/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/backend/abstract_backend.py,sha256=-or6kWVV7egQeyIuN-vI0Tr7Q1htalBZSlhgq_G2RdU,1678
-docling/backend/asciidoc_backend.py,sha256=WW0eIanPIObcg5ci9YcnqFxwipmqRFsRY8zjZDdKvJA,14116
-docling/backend/docling_parse_backend.py,sha256=TaIMli9vePd3fz9L6S4t75JPYZDpgYBLRGfWjbc9Hbk,7632
-docling/backend/docling_parse_v2_backend.py,sha256=QlVU8NgqKvVCa99E8oDa2Xvy__kq30C-myGY3o9Qoq4,8588
-docling/backend/html_backend.py,sha256=TUY5EVv3bo28A_w5CvBgNW4ZqL1d-VxOQPh1_taPHgU,15070
-docling/backend/md_backend.py,sha256=tmuSCghjor9PqKIiVieCuZ4_t5JEjZMy3cq7u3yTgyU,14032
-docling/backend/mspowerpoint_backend.py,sha256=J472AIH_IXvGg3D0FDmXhue1At_VSBD6n15c64Kxttw,15446
-docling/backend/msword_backend.py,sha256=FAUdP74QxGKo2xMZQ4WQGYwtpIBCTJ_FG17PBpRwhxI,17230
-docling/backend/pdf_backend.py,sha256=unnw7QiRE1VXg6Pj-eYrtnFGrp5SSYiI324OlFxyv6c,2050
-docling/backend/pypdfium2_backend.py,sha256=MJX6fQqwK3r967fyAAs-RA_YIkeQvhgsLkQAgaBTgaE,8995
-docling/cli/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/cli/main.py,sha256=NRVGz0z-3EBwYNMJGVnLtDBcfOeutaUyYdkM0ymRnGA,8008
-docling/datamodel/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/datamodel/base_models.py,sha256=Mx0xR6YmRP8thu8CjOxjbGHLUJctqIvFwRZQ-8tQowY,5380
-docling/datamodel/document.py,sha256=mkPXDms9jtPFY1pfBSicNaVRZwbbfzYFUj0dJDbMgG8,20612
-docling/datamodel/pipeline_options.py,sha256=WNjluKC-Ww63ifkGMHwws8zIDHnOS1z5Hw7_j3S0qao,2446
-docling/datamodel/settings.py,sha256=KBFVeQviR1hoCFjA1ZwuLuQ6EAAYR7saIa6EUYiOkHI,767
-docling/document_converter.py,sha256=T-Y2pWwbCIofW209XJ3wlc5TiGeQqMbDqgzcVWyZ_0Y,10227
-docling/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/models/base_model.py,sha256=wSBGAIAbLqrqP_SMtkzXMuyFvvzjVU6iCqgSNnGIR4Y,603
-docling/models/base_ocr_model.py,sha256=SYelQRValiUo6M_p_9-J7CqNIOFO-EkK58j90SMsKQY,5028
-docling/models/ds_glm_model.py,sha256=vJLngchZonqFzGWbUr2izFSXk9DloPDhAfN2c3nkzNU,11254
-docling/models/easyocr_model.py,sha256=YfvdodjZ20WuOfouQXJmDyQL78QDOqWYsWSs2zSxWFc,3327
-docling/models/layout_model.py,sha256=zd2ULW3U6v9OJl4TnjWFEY6Q2O-lBfrIqtvrnDzF7HU,12596
-docling/models/page_assemble_model.py,sha256=LOKHho-r-RpeIVh8CpJ9tid_QIp5um3ukcrucZsyUlY,6645
-docling/models/page_preprocessing_model.py,sha256=cfhUIlGAGaX1RxILi69ZEV9Kmhhd3Y0XaSlQnGo18o4,1964
-docling/models/table_structure_model.py,sha256=YWSZKOz56gvicjTzVgSE-8Z_hI3NcRD5EN0yOUoM-_g,6979
-docling/models/tesseract_ocr_cli_model.py,sha256=fKc05V73ibMvAeuA4PForhYNtunpT5rR0k_xHZsew-E,5980
-docling/models/tesseract_ocr_model.py,sha256=v6td0vq8NogePuRTJRZhKF0DtZXITj70r9rKJKO5u9k,4984
-docling/pipeline/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/pipeline/base_pipeline.py,sha256=7DTzVvM_jVHCxyY-BuuGRhmUsD_sgX4DD00oBFJWdB8,6723
-docling/pipeline/simple_pipeline.py,sha256=pxce0-3He5Lqa-xXT-7h173XVOSMZiMHl6HOfAJmQ7o,2162
-docling/pipeline/standard_pdf_pipeline.py,sha256=AVNSxGc6kPmBPDLWDc9eI8fryc25eOtiIVrOyVhZMZM,7527
-docling/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/utils/export.py,sha256=KyGF1BVDHPFfHVXZc8vegsWlFfOgGPP2YckWpTadyI8,4694
-docling/utils/layout_utils.py,sha256=vlN0rc8i0ayRGn3WnaG-pdmqEL00KKGl2zez3Gj-hrk,32074
-docling/utils/utils.py,sha256=llhXSbIDNZ1MHOwBEfLHBAoJIAYI7QlPIonlI1jLUJ0,1208
-docling-2.2.1.dist-info/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
-docling-2.2.1.dist-info/METADATA,sha256=BOYg-5kaA2Fjxc2bwaJOuAd9LmrQerOzQLHCyaiQ1aE,6205
-docling-2.2.1.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-docling-2.2.1.dist-info/entry_points.txt,sha256=VOSzV77znM52dz5ysaDuJ0ijl1cnfrh1ZPg8od5OcTs,48
-docling-2.2.1.dist-info/RECORD,,