docling 1.9.0__tar.gz → 1.11.0__tar.gz

{docling-1.9.0 → docling-1.11.0}/LICENSE

@@ -1,6 +1,6 @@
 MIT License
 
-Copyright (c) [year] [fullname]
+Copyright (c) 2024 International Business Machines
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

{docling-1.9.0 → docling-1.11.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling
-Version: 1.9.0
+Version: 1.11.0
 Summary: Docling PDF conversion package
 Home-page: https://github.com/DS4SD/docling
 License: MIT
@@ -20,14 +20,14 @@ Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Requires-Dist: certifi (>=2024.7.4)
-Requires-Dist: deepsearch-glm (>=0.19.1,<0.20.0)
-Requires-Dist: docling-core (>=1.1.3,<2.0.0)
-Requires-Dist: docling-ibm-models (>=1.1.3,<2.0.0)
-Requires-Dist: docling-parse (>=1.1.3,<2.0.0)
+Requires-Dist: deepsearch-glm (>=0.21.0,<0.22.0)
+Requires-Dist: docling-core (>=1.2.0,<2.0.0)
+Requires-Dist: docling-ibm-models (>=1.1.7,<2.0.0)
+Requires-Dist: docling-parse (>=1.2.0,<2.0.0)
 Requires-Dist: easyocr (>=1.7,<2.0)
 Requires-Dist: filetype (>=1.2.0,<2.0.0)
 Requires-Dist: huggingface_hub (>=0.23,<1)
-Requires-Dist: pyarrow (>=17.0.0,<18.0.0)
+Requires-Dist: pyarrow (>=16.1.0,<17.0.0)
 Requires-Dist: pydantic (>=2.0.0,<3.0.0)
 Requires-Dist: pydantic-settings (>=2.3.0,<3.0.0)
 Requires-Dist: pypdfium2 (>=4.30.0,<5.0.0)
@@ -63,7 +63,7 @@ Docling bundles PDF document conversion to JSON and Markdown in an easy, self-co
 * 📝 Extracts metadata from the document, such as title, authors, references and language
 * 🔍 Optionally applies OCR (use with scanned PDFs)
 
-Doing RAG or Q/A? Also consider [Quackling](https://github.com/DS4SD/quackling) to get the most out of your documents. 
+For RAG, check out [Quackling](https://github.com/DS4SD/quackling) to get the most out of your docs, be it using LlamaIndex, LangChain or your pipeline.
 
 ## Installation
 
@@ -183,6 +183,10 @@ results = doc_converter.convert(conv_input)
 You can limit the CPU threads used by Docling by setting the environment variable `OMP_NUM_THREADS` accordingly. The default setting is using 4 CPU threads.
 
 
+## Technical report
+
+For more details on Docling's inner workings, check out the [Docling Technical Report](https://arxiv.org/abs/2408.09869).
+
 ## Contributing
 
 Please read [Contributing to Docling](https://github.com/DS4SD/docling/blob/main/CONTRIBUTING.md) for details.
@@ -196,10 +200,10 @@ If you use Docling in your projects, please consider citing the following:
 @techreport{Docling,
   author = {Deep Search Team},
   month = {8},
-  title = {{Docling Technical Report}},
-  url={https://arxiv.org/abs/2408.09869},
-  eprint={2408.09869},
-  doi = "10.48550/arXiv.2408.09869",
+  title = {Docling Technical Report},
+  url = {https://arxiv.org/abs/2408.09869},
+  eprint = {2408.09869},
+  doi = {10.48550/arXiv.2408.09869},
   version = {1.0.0},
   year = {2024}
 }

{docling-1.9.0 → docling-1.11.0}/README.md

@@ -24,7 +24,7 @@ Docling bundles PDF document conversion to JSON and Markdown in an easy, self-co
 * 📝 Extracts metadata from the document, such as title, authors, references and language
 * 🔍 Optionally applies OCR (use with scanned PDFs)
 
-Doing RAG or Q/A? Also consider [Quackling](https://github.com/DS4SD/quackling) to get the most out of your documents. 
+For RAG, check out [Quackling](https://github.com/DS4SD/quackling) to get the most out of your docs, be it using LlamaIndex, LangChain or your pipeline.
 
 ## Installation
 
@@ -144,6 +144,10 @@ results = doc_converter.convert(conv_input)
 You can limit the CPU threads used by Docling by setting the environment variable `OMP_NUM_THREADS` accordingly. The default setting is using 4 CPU threads.
 
 
+## Technical report
+
+For more details on Docling's inner workings, check out the [Docling Technical Report](https://arxiv.org/abs/2408.09869).
+
 ## Contributing
 
 Please read [Contributing to Docling](https://github.com/DS4SD/docling/blob/main/CONTRIBUTING.md) for details.
@@ -157,10 +161,10 @@ If you use Docling in your projects, please consider citing the following:
 @techreport{Docling,
   author = {Deep Search Team},
   month = {8},
-  title = {{Docling Technical Report}},
-  url={https://arxiv.org/abs/2408.09869},
-  eprint={2408.09869},
-  doi = "10.48550/arXiv.2408.09869",
+  title = {Docling Technical Report},
+  url = {https://arxiv.org/abs/2408.09869},
+  eprint = {2408.09869},
+  doi = {10.48550/arXiv.2408.09869},
   version = {1.0.0},
   year = {2024}
 }

{docling-1.9.0 → docling-1.11.0}/docling/datamodel/document.py

@@ -11,6 +11,7 @@ from docling_core.types import FileInfoObject as DsFileInfoObject
 from docling_core.types import PageDimensions, PageReference, Prov, Ref
 from docling_core.types import Table as DsSchemaTable
 from docling_core.types import TableCell
+from docling_core.types.doc.base import Figure
 from pydantic import BaseModel
 from typing_extensions import deprecated
 
@@ -279,7 +280,7 @@ class ConvertedDocument(BaseModel):
                     ),
                 )
                 figures.append(
-                    BaseCell(
+                    Figure(
                         prov=[
                             Prov(
                                 bbox=target_bbox,
@@ -312,8 +313,76 @@ class ConvertedDocument(BaseModel):
     def render_as_dict(self):
         return self.output.model_dump(by_alias=True, exclude_none=True)
 
-    def render_as_markdown(self):
-        return self.output.export_to_markdown()
+    def render_as_markdown(
+        self,
+        delim: str = "\n\n",
+        main_text_start: int = 0,
+        main_text_stop: Optional[int] = None,
+        main_text_labels: list[str] = [
+            "title",
+            "subtitle-level-1",
+            "paragraph",
+            "caption",
+            "table",
+        ],
+        strict_text: bool = False,
+    ):
+        return self.output.export_to_markdown(
+            delim=delim,
+            main_text_start=main_text_start,
+            main_text_stop=main_text_stop,
+            main_text_labels=main_text_labels,
+            strict_text=strict_text,
+        )
+
+    def render_as_text(
+        self,
+        delim: str = "\n\n",
+        main_text_start: int = 0,
+        main_text_stop: Optional[int] = None,
+        main_text_labels: list[str] = [
+            "title",
+            "subtitle-level-1",
+            "paragraph",
+            "caption",
+        ],
+    ):
+        return self.output.export_to_markdown(
+            delim=delim,
+            main_text_start=main_text_start,
+            main_text_stop=main_text_stop,
+            main_text_labels=main_text_labels,
+            strict_text=True,
+        )
+
+    def render_as_doctags(
+        self,
+        delim: str = "\n\n",
+        main_text_start: int = 0,
+        main_text_stop: Optional[int] = None,
+        main_text_labels: list[str] = [
+            "title",
+            "subtitle-level-1",
+            "paragraph",
+            "caption",
+            "table",
+            "figure",
+        ],
+        page_tagging: bool = True,
+        location_tagging: bool = True,
+        location_dimensions: Tuple[int, int] = (100, 100),
+        add_new_line: bool = True,
+    ) -> str:
+        return self.output.export_to_document_tokens(
+            delim=delim,
+            main_text_start=main_text_start,
+            main_text_stop=main_text_stop,
+            main_text_labels=main_text_labels,
+            page_tagging=page_tagging,
+            location_tagging=location_tagging,
+            location_dimensions=location_dimensions,
+            add_new_line=add_new_line,
+        )
 
     def render_element_images(
         self, element_types: Tuple[PageElement] = (FigureElement,)

{docling-1.9.0 → docling-1.11.0}/docling/models/ds_glm_model.py

@@ -2,7 +2,7 @@ import copy
 import random
 
 from deepsearch_glm.nlp_utils import init_nlp_model
-from deepsearch_glm.utils.ds_utils import to_legacy_document_format
+from deepsearch_glm.utils.doc_utils import to_legacy_document_format
 from deepsearch_glm.utils.load_pretrained_models import load_pretrained_nlp_models
 from docling_core.types import BaseText
 from docling_core.types import Document as DsDocument

{docling-1.9.0 → docling-1.11.0}/docling/utils/export.py

@@ -163,8 +163,12 @@ def generate_multimodal_pages(
         content_md = doc.export_to_markdown(
             main_text_start=start_ix, main_text_stop=end_ix
         )
+        # No page-tagging since we only do 1 page at the time
+        content_dt = doc.export_to_document_tokens(
+            main_text_start=start_ix, main_text_stop=end_ix, page_tagging=False
+        )
 
-        return content_text, content_md, page_cells, page_segments, page
+        return content_text, content_md, content_dt, page_cells, page_segments, page
 
     for ix, orig_item in enumerate(doc.main_text):
 

{docling-1.9.0 → docling-1.11.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "docling"
-version = "1.9.0"  # DO NOT EDIT, updated automatically
+version = "1.11.0"  # 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"
@@ -23,20 +23,20 @@ packages = [{include = "docling"}]
 [tool.poetry.dependencies]
 python = "^3.10"
 pydantic = "^2.0.0"
-docling-core = "^1.1.3"
-docling-ibm-models = "^1.1.3"
-deepsearch-glm = "^0.19.1"
+docling-core = "^1.2.0"
+docling-ibm-models = "^1.1.7"
+deepsearch-glm = "^0.21.0"
 filetype = "^1.2.0"
 pypdfium2 = "^4.30.0"
 pydantic-settings = "^2.3.0"
 huggingface_hub = ">=0.23,<1"
 requests = "^2.32.3"
 easyocr = "^1.7"
-docling-parse = "^1.1.3"
+docling-parse = "^1.2.0"
 certifi = ">=2024.7.4"
 rtree = "^1.3.0"
 scipy = "^1.14.1"
-pyarrow = "^17.0.0"
+pyarrow = "^16.1.0"
 
 [tool.poetry.group.dev.dependencies]
 black = {extras = ["jupyter"], version = "^24.4.2"}