docling 1.13.0__tar.gz → 1.14.0__tar.gz

{docling-1.13.0 → docling-1.14.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling
-Version: 1.13.0
+Version: 1.14.0
 Summary: Docling PDF conversion package
 Home-page: https://github.com/DS4SD/docling
 License: MIT
@@ -22,7 +22,7 @@ Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Provides-Extra: examples
 Requires-Dist: certifi (>=2024.7.4)
 Requires-Dist: deepsearch-glm (>=0.21.1,<0.22.0)
-Requires-Dist: docling-core (>=1.4.0,<2.0.0)
+Requires-Dist: docling-core (>=1.5.0,<2.0.0)
 Requires-Dist: docling-ibm-models (>=1.2.0,<2.0.0)
 Requires-Dist: docling-parse (>=1.2.0,<2.0.0)
 Requires-Dist: easyocr (>=1.7,<2.0)
@@ -74,8 +74,9 @@ Docling bundles PDF document conversion to JSON and Markdown in an easy, self-co
 * ⚡ Converts any PDF document to JSON or Markdown format, stable and lightning fast
 * 📑 Understands detailed page layout, reading order and recovers table structures
 * 📝 Extracts metadata from the document, such as title, authors, references and language
-* 🔍 Optionally applies OCR (use with scanned PDFs)
+* 🔍 Includes OCR support for scanned PDFs
 * 🤖 Integrates easily with LLM app / RAG frameworks like 🦙 LlamaIndex and 🦜🔗 LangChain
+* 💻 Provides a simple and convenient CLI
 
 ## Installation
 
@@ -87,31 +88,33 @@ pip install docling
 > [!NOTE]
 > Works on macOS and Linux environments. Windows platforms are currently not tested.
 
+<details>
+  <summary><b>Alternative PyTorch distributions</b></summary>
 
-### Use alternative PyTorch distributions
+  The Docling models depend on the [PyTorch](https://pytorch.org/) library.
+  Depending on your architecture, you might want to use a different distribution of `torch`.
+  For example, you might want support for different accelerator or for a cpu-only version.
+  All the different ways for installing `torch` are listed on their website <https://pytorch.org/>.
 
-The Docling models depend on the [PyTorch](https://pytorch.org/) library.
-Depending on your architecture, you might want to use a different distribution of `torch`.
-For example, you might want support for different accelerator or for a cpu-only version.
-All the different ways for installing `torch` are listed on their website <https://pytorch.org/>.
+  One common situation is the installation on Linux systems with cpu-only support.
+  In this case, we suggest the installation of Docling with the following options
 
-One common situation is the installation on Linux systems with cpu-only support.
-In this case, we suggest the installation of Docling with the following options
+  ```bash
+  # Example for installing on the Linux cpu-only version
+  pip install docling --extra-index-url https://download.pytorch.org/whl/cpu
+  ```
+</details>
 
-```bash
-# Example for installing on the Linux cpu-only version
-pip install docling --extra-index-url https://download.pytorch.org/whl/cpu
-```
+<details>
+  <summary><b>Docling development setup</b></summary>
 
+  To develop for Docling (features, bugfixes etc.), install as follows from your local clone's root dir:
+  ```bash
+  poetry install --all-extras
+  ```
+</details>
 
-### Development setup
-
-To develop for Docling, you need Python 3.10 / 3.11 / 3.12 and Poetry. You can then install from your local clone's root dir:
-```bash
-poetry install --all-extras
-```
-
-## Usage
+## Getting started
 
 ### Convert a single document
 
@@ -123,6 +126,7 @@ source = "https://arxiv.org/pdf/2408.09869"  # PDF path or URL
 converter = DocumentConverter()
 result = converter.convert_single(source)
 print(result.render_as_markdown())  # output: "## Docling Technical Report[...]"
+print(result.render_as_doctags())  # output: "<document><title><page_1><loc_20>..."
 ```
 
 ### Convert a batch of documents
@@ -136,6 +140,51 @@ python examples/batch_convert.py
 ```
 The output of the above command will be written to `./scratch`.
 
+### CLI
+
+You can also use Docling directly from your command line to convert individual files —be it local or by URL— or whole directories.
+
+A simple example would look like this:
+```console
+docling https://arxiv.org/pdf/2206.01062
+```
+
+To see all available options (export formats etc.) run `docling --help`.
+
+<details>
+  <summary><b>CLI reference</b></summary>
+
+  Here are the available options as of this writing (for an up-to-date listing, run `docling --help`):
+
+  ```console
+  $ docling --help
+
+  Usage: docling [OPTIONS] source
+
+  ╭─ Arguments ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
+  │ *    input_sources      source  PDF files to convert. Can be local file / directory paths or URL. [default: None] [required] │
+  ╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
+  ╭─ Options ────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
+  │ --json       --no-json                            If enabled the document is exported as JSON. [default: no-json]            │
+  │ --md         --no-md                              If enabled the document is exported as Markdown. [default: md]             │
+  │ --txt        --no-txt                             If enabled the document is exported as Text. [default: no-txt]             │
+  │ --doctags    --no-doctags                         If enabled the document is exported as Doc Tags. [default: no-doctags]     │
+  │ --ocr        --no-ocr                             If enabled, the bitmap content will be processed using OCR. [default: ocr] │
+  │ --backend                    [pypdfium2|docling]  The PDF backend to use. [default: docling]                                 │
+  │ --output                     PATH                 Output directory where results are saved. [default: .]                     │
+  │ --version                                         Show version information.                                                  │
+  │ --help                                            Show this message and exit.                                                │
+  ╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
+  ```
+</details>
+
+### RAG
+Check out the following examples showcasing RAG using Docling with standard LLM application frameworks:
+- [Basic RAG pipeline with 🦙 LlamaIndex](https://github.com/DS4SD/docling/tree/main/examples/rag_llamaindex.ipynb)
+- [Basic RAG pipeline with 🦜🔗 LangChain](https://github.com/DS4SD/docling/tree/main/examples/rag_langchain.ipynb)
+
+## Advanced features
+
 ### Adjust pipeline features
 
 The example file [custom_convert.py](https://github.com/DS4SD/docling/blob/main/examples/custom_convert.py) contains multiple ways
@@ -194,11 +243,6 @@ 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.
 
-### RAG
-Check out the following examples showcasing RAG using Docling with standard LLM application frameworks:
-- [Basic RAG pipeline with 🦙 LlamaIndex](https://github.com/DS4SD/docling/tree/main/examples/rag_llamaindex.ipynb)
-- [Basic RAG pipeline with 🦜🔗 LangChain](https://github.com/DS4SD/docling/tree/main/examples/rag_langchain.ipynb)
-
 ## Technical report
 
 For more details on Docling's inner workings, check out the [Docling Technical Report](https://arxiv.org/abs/2408.09869).

{docling-1.13.0 → docling-1.14.0}/README.md

@@ -22,8 +22,9 @@ Docling bundles PDF document conversion to JSON and Markdown in an easy, self-co
 * ⚡ Converts any PDF document to JSON or Markdown format, stable and lightning fast
 * 📑 Understands detailed page layout, reading order and recovers table structures
 * 📝 Extracts metadata from the document, such as title, authors, references and language
-* 🔍 Optionally applies OCR (use with scanned PDFs)
+* 🔍 Includes OCR support for scanned PDFs
 * 🤖 Integrates easily with LLM app / RAG frameworks like 🦙 LlamaIndex and 🦜🔗 LangChain
+* 💻 Provides a simple and convenient CLI
 
 ## Installation
 
@@ -35,31 +36,33 @@ pip install docling
 > [!NOTE]
 > Works on macOS and Linux environments. Windows platforms are currently not tested.
 
+<details>
+  <summary><b>Alternative PyTorch distributions</b></summary>
 
-### Use alternative PyTorch distributions
+  The Docling models depend on the [PyTorch](https://pytorch.org/) library.
+  Depending on your architecture, you might want to use a different distribution of `torch`.
+  For example, you might want support for different accelerator or for a cpu-only version.
+  All the different ways for installing `torch` are listed on their website <https://pytorch.org/>.
 
-The Docling models depend on the [PyTorch](https://pytorch.org/) library.
-Depending on your architecture, you might want to use a different distribution of `torch`.
-For example, you might want support for different accelerator or for a cpu-only version.
-All the different ways for installing `torch` are listed on their website <https://pytorch.org/>.
+  One common situation is the installation on Linux systems with cpu-only support.
+  In this case, we suggest the installation of Docling with the following options
 
-One common situation is the installation on Linux systems with cpu-only support.
-In this case, we suggest the installation of Docling with the following options
+  ```bash
+  # Example for installing on the Linux cpu-only version
+  pip install docling --extra-index-url https://download.pytorch.org/whl/cpu
+  ```
+</details>
 
-```bash
-# Example for installing on the Linux cpu-only version
-pip install docling --extra-index-url https://download.pytorch.org/whl/cpu
-```
+<details>
+  <summary><b>Docling development setup</b></summary>
 
+  To develop for Docling (features, bugfixes etc.), install as follows from your local clone's root dir:
+  ```bash
+  poetry install --all-extras
+  ```
+</details>
 
-### Development setup
-
-To develop for Docling, you need Python 3.10 / 3.11 / 3.12 and Poetry. You can then install from your local clone's root dir:
-```bash
-poetry install --all-extras
-```
-
-## Usage
+## Getting started
 
 ### Convert a single document
 
@@ -71,6 +74,7 @@ source = "https://arxiv.org/pdf/2408.09869"  # PDF path or URL
 converter = DocumentConverter()
 result = converter.convert_single(source)
 print(result.render_as_markdown())  # output: "## Docling Technical Report[...]"
+print(result.render_as_doctags())  # output: "<document><title><page_1><loc_20>..."
 ```
 
 ### Convert a batch of documents
@@ -84,6 +88,51 @@ python examples/batch_convert.py
 ```
 The output of the above command will be written to `./scratch`.
 
+### CLI
+
+You can also use Docling directly from your command line to convert individual files —be it local or by URL— or whole directories.
+
+A simple example would look like this:
+```console
+docling https://arxiv.org/pdf/2206.01062
+```
+
+To see all available options (export formats etc.) run `docling --help`.
+
+<details>
+  <summary><b>CLI reference</b></summary>
+
+  Here are the available options as of this writing (for an up-to-date listing, run `docling --help`):
+
+  ```console
+  $ docling --help
+
+  Usage: docling [OPTIONS] source
+
+  ╭─ Arguments ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
+  │ *    input_sources      source  PDF files to convert. Can be local file / directory paths or URL. [default: None] [required] │
+  ╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
+  ╭─ Options ────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
+  │ --json       --no-json                            If enabled the document is exported as JSON. [default: no-json]            │
+  │ --md         --no-md                              If enabled the document is exported as Markdown. [default: md]             │
+  │ --txt        --no-txt                             If enabled the document is exported as Text. [default: no-txt]             │
+  │ --doctags    --no-doctags                         If enabled the document is exported as Doc Tags. [default: no-doctags]     │
+  │ --ocr        --no-ocr                             If enabled, the bitmap content will be processed using OCR. [default: ocr] │
+  │ --backend                    [pypdfium2|docling]  The PDF backend to use. [default: docling]                                 │
+  │ --output                     PATH                 Output directory where results are saved. [default: .]                     │
+  │ --version                                         Show version information.                                                  │
+  │ --help                                            Show this message and exit.                                                │
+  ╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
+  ```
+</details>
+
+### RAG
+Check out the following examples showcasing RAG using Docling with standard LLM application frameworks:
+- [Basic RAG pipeline with 🦙 LlamaIndex](https://github.com/DS4SD/docling/tree/main/examples/rag_llamaindex.ipynb)
+- [Basic RAG pipeline with 🦜🔗 LangChain](https://github.com/DS4SD/docling/tree/main/examples/rag_langchain.ipynb)
+
+## Advanced features
+
 ### Adjust pipeline features
 
 The example file [custom_convert.py](https://github.com/DS4SD/docling/blob/main/examples/custom_convert.py) contains multiple ways
@@ -142,11 +191,6 @@ 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.
 
-### RAG
-Check out the following examples showcasing RAG using Docling with standard LLM application frameworks:
-- [Basic RAG pipeline with 🦙 LlamaIndex](https://github.com/DS4SD/docling/tree/main/examples/rag_llamaindex.ipynb)
-- [Basic RAG pipeline with 🦜🔗 LangChain](https://github.com/DS4SD/docling/tree/main/examples/rag_langchain.ipynb)
-
 ## Technical report
 
 For more details on Docling's inner workings, check out the [Docling Technical Report](https://arxiv.org/abs/2408.09869).

{docling-1.13.0 → docling-1.14.0}/docling/cli/main.py

@@ -8,7 +8,7 @@ from pathlib import Path
 from typing import Annotated, Iterable, List, Optional
 
 import typer
-from pydantic import AnyUrl
+from docling_core.utils.file import resolve_file_source
 
 from docling.backend.docling_parse_backend import DoclingParseDocumentBackend
 from docling.backend.pypdfium2_backend import PyPdfiumDocumentBackend
@@ -109,11 +109,11 @@ def export_documents(
 @app.command(no_args_is_help=True)
 def convert(
     input_sources: Annotated[
-        List[Path],
+        List[str],
         typer.Argument(
             ...,
             metavar="source",
-            help="PDF files to convert. Directories are also accepted.",
+            help="PDF files to convert. Can be local file / directory paths or URL.",
         ),
     ],
     export_json: Annotated[
@@ -167,7 +167,8 @@ def convert(
     logging.basicConfig(level=logging.INFO)
 
     input_doc_paths: List[Path] = []
-    for source in input_sources:
+    for src in input_sources:
+        source = resolve_file_source(source=src)
         if not source.exists():
             err_console.print(
                 f"[red]Error: The input file {source} does not exist.[/red]"
@@ -179,58 +180,25 @@ def convert(
         else:
             input_doc_paths.append(source)
 
-    ###########################################################################
-
-    # The following sections contain a combination of PipelineOptions
-    # and PDF Backends for various configurations.
-    # Uncomment one section at the time to see the differences in the output.
-
-    doc_converter = None
-    if backend == Backend.PYPDFIUM2 and not ocr:  # PyPdfium without OCR
-        pipeline_options = PipelineOptions()
-        pipeline_options.do_ocr = False
-        pipeline_options.do_table_structure = True
-        pipeline_options.table_structure_options.do_cell_matching = False
-
-        doc_converter = DocumentConverter(
-            pipeline_options=pipeline_options,
-            pdf_backend=PyPdfiumDocumentBackend,
-        )
-
-    elif backend == Backend.PYPDFIUM2.value and ocr:  # PyPdfium with OCR
-        pipeline_options = PipelineOptions()
-        pipeline_options.do_ocr = False
-        pipeline_options.do_table_structure = True
-        pipeline_options.table_structure_options.do_cell_matching = True
-
-        doc_converter = DocumentConverter(
-            pipeline_options=pipeline_options,
-            pdf_backend=PyPdfiumDocumentBackend,
-        )
-
-    elif backend == Backend.DOCLING.value and not ocr:  # Docling Parse without OCR
-        pipeline_options = PipelineOptions()
-        pipeline_options.do_ocr = False
-        pipeline_options.do_table_structure = True
-        pipeline_options.table_structure_options.do_cell_matching = True
-
-        doc_converter = DocumentConverter(
-            pipeline_options=pipeline_options,
-            pdf_backend=DoclingParseDocumentBackend,
-        )
-
-    elif backend == Backend.DOCLING.value and ocr:  # Docling Parse with OCR
-        pipeline_options = PipelineOptions()
-        pipeline_options.do_ocr = True
-        pipeline_options.do_table_structure = True
-        pipeline_options.table_structure_options.do_cell_matching = True
-
-        doc_converter = DocumentConverter(
-            pipeline_options=pipeline_options,
-            pdf_backend=DoclingParseDocumentBackend,
-        )
-
-    ###########################################################################
+    match backend:
+        case Backend.PYPDFIUM2:
+            do_cell_matching = ocr  # only do cell matching when OCR enabled
+            pdf_backend = PyPdfiumDocumentBackend
+        case Backend.DOCLING:
+            do_cell_matching = True
+            pdf_backend = DoclingParseDocumentBackend
+        case _:
+            raise RuntimeError(f"Unexpected backend type {backend}")
+
+    pipeline_options = PipelineOptions(
+        do_ocr=ocr,
+        do_table_structure=True,
+    )
+    pipeline_options.table_structure_options.do_cell_matching = do_cell_matching
+    doc_converter = DocumentConverter(
+        pipeline_options=pipeline_options,
+        pdf_backend=pdf_backend,
+    )
 
     # Define input files
     input = DocumentConversionInput.from_paths(input_doc_paths)

{docling-1.13.0 → docling-1.14.0}/docling/datamodel/document.py

@@ -368,20 +368,30 @@ class ConvertedDocument(BaseModel):
             "table",
             "figure",
         ],
-        page_tagging: bool = True,
-        location_tagging: bool = True,
-        location_dimensions: Tuple[int, int] = (100, 100),
-        add_new_line: bool = True,
+        xsize: int = 100,
+        ysize: int = 100,
+        add_location: bool = True,
+        add_content: bool = True,
+        add_page_index: bool = True,
+        # table specific flags
+        add_table_cell_location: bool = False,
+        add_table_cell_label: bool = True,
+        add_table_cell_text: 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,
+            xsize=xsize,
+            ysize=ysize,
+            add_location=add_location,
+            add_content=add_content,
+            add_page_index=add_page_index,
+            # table specific flags
+            add_table_cell_location=add_table_cell_location,
+            add_table_cell_label=add_table_cell_label,
+            add_table_cell_text=add_table_cell_text,
         )
 
     def render_element_images(

{docling-1.13.0 → docling-1.14.0}/docling/utils/export.py

@@ -111,7 +111,7 @@ def generate_multimodal_pages(
         )
         # 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
+            main_text_start=start_ix, main_text_stop=end_ix, add_page_index=False
         )
 
         return content_text, content_md, content_dt, page_cells, page_segments, page

{docling-1.13.0 → docling-1.14.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "docling"
-version = "1.13.0"  # DO NOT EDIT, updated automatically
+version = "1.14.0"  # 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"
@@ -23,7 +23,7 @@ packages = [{include = "docling"}]
 [tool.poetry.dependencies]
 python = "^3.10"
 pydantic = "^2.0.0"
-docling-core = "^1.4.0"
+docling-core = "^1.5.0"
 docling-ibm-models = "^1.2.0"
 deepsearch-glm = "^0.21.1"
 filetype = "^1.2.0"