feat: simplify dependencies, switch to uv (#1700)

* refactor with uv Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * constraints for onnxruntime Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * more constraints Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> --------- Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
2025-06-27 05:20:05 +00:00 · 2025-06-03 15:18:54 +02:00 · 2025-06-03 15:18:54 +02:00 · cdd401847a
commit cdd401847a
parent 61d0d6c755
17 changed files with 7142 additions and 8379 deletions
--- a/.github/actions/setup-poetry/action.yml
+++ b/.github/actions/setup-poetry/action.yml
@ -1,19 +0,0 @@
-name: 'Set up Poetry and install'
-description: 'Set up a specific version of Poetry and install dependencies using caching.'
-inputs:
-  python-version:
-    description: "Version range or exact version of Python or PyPy to use, using SemVer's version range syntax."
-    default: '3.11'
-runs:
-  using: 'composite'
-  steps:
-    - name: Install poetry
-      run: pipx install poetry==1.8.5
-      shell: bash
-    - uses: actions/setup-python@v5
-      with:
-        python-version: ${{ inputs.python-version }}
-        cache: 'poetry'
-    - name: Install dependencies
-      run: poetry install --all-extras
-      shell: bash
--- a/.github/scripts/release.sh
+++ b/.github/scripts/release.sh
@ -10,11 +10,12 @@ fi
 CHGLOG_FILE="${CHGLOG_FILE:-CHANGELOG.md}"

 # update package version
-poetry version "${TARGET_VERSION}"
+uvx --from=toml-cli toml set --toml-path=pyproject.toml project.version "${TARGET_VERSION}"
+UV_FROZEN=0 uv lock --upgrade-package docling

 # collect release notes
 REL_NOTES=$(mktemp)
-poetry run semantic-release changelog --unreleased >> "${REL_NOTES}"
+uv run --no-sync semantic-release changelog --unreleased >> "${REL_NOTES}"

 # update changelog
 TMP_CHGLOG=$(mktemp)
@ -30,7 +31,7 @@ mv "${TMP_CHGLOG}" "${CHGLOG_FILE}"
 # push changes
 git config --global user.name 'github-actions[bot]'
 git config --global user.email 'github-actions[bot]@users.noreply.github.com'
-git add pyproject.toml "${CHGLOG_FILE}"
+git add pyproject.toml uv.lock "${CHGLOG_FILE}"
 COMMIT_MSG="chore: bump version to ${TARGET_VERSION} [skip ci]"
 git commit -m "${COMMIT_MSG}"
 git push origin main
--- a/.github/workflows/cd.yml
+++ b/.github/workflows/cd.yml
@ -4,9 +4,8 @@ on:
  workflow_dispatch:

 env:
-  # disable keyring (https://github.com/actions/runner-images/issues/6185):
-  PYTHON_KEYRING_BACKEND: keyring.backends.null.Keyring
-
+  UV_FROZEN: "1"
+    
 jobs:
  code-checks:
    uses: ./.github/workflows/checks.yml
@ -20,15 +19,20 @@ jobs:
      - uses: actions/checkout@v4
        with:
          fetch-depth: 0  # for fetching tags, required for semantic-release
-      - uses: ./.github/actions/setup-poetry
+      - name: Install uv and set the python version
+        uses: astral-sh/setup-uv@v5
+        with:
+          enable-cache: true
+      - name: Install dependencies
+        run: uv sync --only-dev
      - name: Check version of potential release
        id: version_check
        run: |
-            TRGT_VERSION=$(poetry run semantic-release print-version)
-            echo "TRGT_VERSION=${TRGT_VERSION}" >> $GITHUB_OUTPUT
-            echo "${TRGT_VERSION}"
+          TRGT_VERSION=$(uv run --no-sync semantic-release print-version)
+          echo "TRGT_VERSION=${TRGT_VERSION}" >> "$GITHUB_OUTPUT"
+          echo "${TRGT_VERSION}"
      - name: Check notes of potential release
-        run: poetry run semantic-release changelog --unreleased
+        run: uv run --no-sync semantic-release changelog --unreleased
  release:
    needs: [code-checks, pre-release-check]
    if: needs.pre-release-check.outputs.TARGET_TAG_V != ''
@ -45,7 +49,12 @@ jobs:
        with:
          token: ${{ steps.app-token.outputs.token }}
          fetch-depth: 0  # for fetching tags, required for semantic-release
-      - uses: ./.github/actions/setup-poetry
+      - name: Install uv and set the python version
+        uses: astral-sh/setup-uv@v5
+        with:
+          enable-cache: true
+      - name: Install dependencies
+        run: uv sync --only-dev
      - name: Run release script
        env:
          GH_TOKEN: ${{ steps.app-token.outputs.token }}
--- a/.github/workflows/checks.yml
+++ b/.github/workflows/checks.yml
@ -12,6 +12,7 @@ on:
 env:
  HF_HUB_DOWNLOAD_TIMEOUT: "60"
  HF_HUB_ETAG_TIMEOUT: "60"
+  UV_FROZEN: "1"

 jobs:
  run-checks:
@ -31,16 +32,24 @@ jobs:
        with:
          path: ~/.cache/huggingface
          key: huggingface-cache-py${{ matrix.python-version }}
-      - uses: ./.github/actions/setup-poetry
+      - name: Install uv and set the python version
+        uses: astral-sh/setup-uv@v5
        with:
          python-version: ${{ matrix.python-version }}
-      - name: Run styling check
-        run: poetry run pre-commit run --all-files
-      - name: Install with poetry
-        run: poetry install --all-extras
+          enable-cache: true
+      - name: pre-commit cache key
+        run: echo "PY=$(python -VV | sha256sum | cut -d' ' -f1)" >> "$GITHUB_ENV"
+      - uses: actions/cache@v4
+        with:
+          path: ~/.cache/pre-commit
+          key: pre-commit|${{ env.PY }}|${{ hashFiles('.pre-commit-config.yaml') }}
+      - name: Install dependencies
+        run: uv sync --frozen --all-extras
+      - name: Check style and run tests
+        run: pre-commit run --all-files
      - name: Testing
        run: |
-          poetry run pytest -v --cov=docling --cov-report=xml tests
+          uv run --no-sync pytest -v --cov=docling --cov-report=xml tests
      - name: Upload coverage to Codecov
        if: inputs.push_coverage
        uses: codecov/codecov-action@v5
@ -57,7 +66,52 @@ jobs:
            fi

            echo "Running example $file"
-            poetry run python "$file" || exit 1
+            uv run --no-sync python "$file" || exit 1
          done
-      - name: Build with poetry
-        run: poetry build
+
+  build-package:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ['3.12']
+    steps:
+      - uses: actions/checkout@v4
+      - name: Install uv and set the python version
+        uses: astral-sh/setup-uv@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+          enable-cache: true
+      - name: Install dependencies
+        run: uv sync --all-extras
+      - name: Build package
+        run: uv build
+      - name: Check content of wheel
+        run: unzip -l dist/*.whl
+      - name: Store the distribution packages
+        uses: actions/upload-artifact@v4
+        with:
+          name: python-package-distributions
+          path: dist/
+
+  test-package:
+    needs:
+      - build-package
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ['3.12']
+    steps:
+      - name: Download all the dists
+        uses: actions/download-artifact@v4
+        with:
+          name: python-package-distributions
+          path: dist/
+      - name: Install uv and set the python version
+        uses: astral-sh/setup-uv@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+          enable-cache: true
+      - name: Install package
+        run: uv pip install dist/*.whl
+      - name: Run docling
+        run: docling --help
--- a/.github/workflows/ci-docs.yml
+++ b/.github/workflows/ci-docs.yml
@ -8,6 +8,9 @@ on:
      - "**"
      - "!gh-pages"

+env:
+  UV_FROZEN: "1"
+
 jobs:
  build-docs:
    if: ${{ github.event_name == 'push' || (github.event.pull_request.head.repo.full_name != 'docling-project/docling' && github.event.pull_request.head.repo.full_name != 'docling-project/docling') }}
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@ -9,10 +9,6 @@ on:
      - "!main"
      - "!gh-pages"

-env:
-  # disable keyring (https://github.com/actions/runner-images/issues/6185):
-  PYTHON_KEYRING_BACKEND: keyring.backends.null.Keyring
-
 jobs:
  code-checks:
    if: ${{ github.event_name == 'push' || (github.event.pull_request.head.repo.full_name != 'docling-project/docling' && github.event.pull_request.head.repo.full_name != 'docling-project/docling') }}
--- a/.github/workflows/docs.yml
+++ b/.github/workflows/docs.yml
@ -6,14 +6,21 @@ on:
                description: "If true, the docs will be deployed."
                default: false

+env:
+  UV_FROZEN: "1"
+
 jobs:
    run-docs:
        runs-on: ubuntu-latest
        steps:
        - uses: actions/checkout@v4
-        - uses: ./.github/actions/setup-poetry
+        - name: Install uv and set the python version
+          uses: astral-sh/setup-uv@v5
+          with:
+            python-version: ${{ matrix.python-version }}
+            enable-cache: true
        - name: Build docs
-          run: poetry run mkdocs build --verbose --clean
+          run: uv run mkdocs build --verbose --clean
        - name: Build and push docs
          if: inputs.deploy
-          run: poetry run mkdocs gh-deploy --force
+          run: uv run --no-sync mkdocs gh-deploy --force
--- a/.github/workflows/pypi.yml
+++ b/.github/workflows/pypi.yml
@ -4,16 +4,18 @@ on:
  release:
    types: [published]

+env:
+  UV_FROZEN: "1"
+
 permissions:
  contents: read

-env:
-  # disable keyring (https://github.com/actions/runner-images/issues/6185):
-  PYTHON_KEYRING_BACKEND: keyring.backends.null.Keyring
-
 jobs:
  build-and-publish:
    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ['3.12']
    environment:
      name: pypi
      url: https://pypi.org/p/docling
@ -21,9 +23,15 @@ jobs:
      id-token: write  # IMPORTANT: mandatory for trusted publishing
    steps:
      - uses: actions/checkout@v4
-      - uses: ./.github/actions/setup-poetry
-      - name: Build and publish
-        run: poetry build
+      - name: Install uv and set the python version
+        uses: astral-sh/setup-uv@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+          enable-cache: true
+      - name: Install dependencies
+        run: uv sync --all-extras
+      - name: Build package
+        run: uv build
      - name: Publish distribution 📦 to PyPI
        uses: pypa/gh-action-pypi-publish@release/v1
        with:
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@ -17,12 +17,11 @@ repos:
    hooks:
      - id: mypy
        name: MyPy
-        entry: poetry run mypy docling
+        entry: uv run --no-sync mypy docling
        pass_filenames: false
        language: system
        files: '\.py$'
-      - id: poetry
-        name: Poetry check
-        entry: poetry check --lock
-        pass_filenames: false
-        language: system
+  - repo: https://github.com/astral-sh/uv-pre-commit
+    rev: 0.7.8
+    hooks:
+      - id: uv-lock
--- a/CONTRIBUTING.md
+++ b/CONTRIBUTING.md
@ -6,70 +6,52 @@ For more details on the contributing guidelines head to the Docling Project [com

 ## Developing

-### Usage of Poetry
+### Usage of uv

-We use Poetry to manage dependencies.
+We use [uv](https://docs.astral.sh/uv/) as package and project manager.

 #### Installation

-To install Poetry, follow the documentation here: https://python-poetry.org/docs/master/#installing-with-the-official-installer
+To install `uv`, check the documentation on [Installing uv](https://docs.astral.sh/uv/getting-started/installation/).

-1. Install Poetry globally on your machine:
-    ```bash
-    curl -sSL https://install.python-poetry.org | python3 -
-    ```
-    The installation script will print the installation bin folder `POETRY_BIN` which you need in the next steps.
+#### Create an environment and sync it

-2. Make sure Poetry is in your `$PATH`:
-    - for `zsh`:
-        ```sh
-        echo 'export PATH="POETRY_BIN:$PATH"' >> ~/.zshrc
-        ```
-    - for `bash`:
-        ```sh
-        echo 'export PATH="POETRY_BIN:$PATH"' >> ~/.bashrc
-        ```
-
-3. The official guidelines linked above include useful details on configuring autocomplete for most shell environments, e.g., Bash and Zsh.
-
-#### Create a Virtual Environment and Install Dependencies
-
-To activate the Virtual Environment, run:
+You can use the `uv sync` to create a project virtual environment (if it does not already exist) and sync
+the project's dependencies with the environment.

 ```bash
-poetry shell
+uv sync
 ```

-This will spawn a shell with the Virtual Environment activated. If the Virtual Environment doesn't exist, Poetry will create one for you. Then, to install dependencies, run:
+#### Use a specific Python version (optional)
+
+If you need to work with a specific version of Python, you can create a new virtual environment for that version
+and run the sync command:

 ```bash
-poetry install
+uv venv --python 3.12
+uv sync
 ```

-**(Advanced) Use a Specific Python Version**
+More detailed options are described on the [Using Python environments](https://docs.astral.sh/uv/pip/environments/) documentation.

-If you need to work with a specific (older) version of Python, run:
+#### Add a new dependency
+
+Simply use the `uv add` command. The `pyproject.toml` and `uv.lock` files will be updated.

 ```bash
-poetry env use $(which python3.8)
-```
-
-This creates a Virtual Environment with Python 3.8. For other versions, replace `$(which python3.8)` with the path to the interpreter (e.g., `/usr/bin/python3.8`) or use `$(which pythonX.Y)`.
-
-#### Add a New Dependency
-
-```bash
-poetry add NAME
+uv add [OPTIONS] <PACKAGES|--requirements <REQUIREMENTS>>
 ```

 ## Coding Style Guidelines

 We use the following tools to enforce code style:

- iSort, to sort imports
- Black, to format code
+- [Ruff](https://docs.astral.sh/ruff/), as linter and code formatter
+- [MyPy](https://mypy.readthedocs.io), as static type checker

-We run a series of checks on the codebase on every commit using `pre-commit`. To install the hooks, run:
+A set of styling checks, as well as regression tests, are defined and managed through the [pre-commit](https://pre-commit.com/) framework.
+To ensure that those scripts run automatically before a commit is finalized, install `pre-commit` on your local repository:

 ```bash
 pre-commit install
@ -81,7 +63,7 @@ To run the checks on-demand, run:
 pre-commit run --all-files
 ```

-Note: Checks like `Black` and `isort` will "fail" if they modify files. This is because `pre-commit` doesn't like to see files modified by its hooks. In these cases, `git add` the modified files and `git commit` again.
+Note: Checks like `Ruff` will "fail" if they modify files. This is because `pre-commit` doesn't like to see files modified by its hooks. In these cases, `git add` the modified files and `git commit` again.

 ## Tests

@ -94,7 +76,7 @@ When a change improves the conversion results, multiple reference documents must
 The reference data can be regenerated with

 ```sh
-DOCLING_GEN_TEST_DATA=1 poetry run pytest
+DOCLING_GEN_TEST_DATA=1 uv run pytest
 ```

 All PRs modifying the reference test data require a double review to guarantee we don't miss edge cases.
--- a/README.md
+++ b/README.md
@ -14,9 +14,8 @@
 [![Docs](https://img.shields.io/badge/docs-live-brightgreen)](https://docling-project.github.io/docling/)
 [![PyPI version](https://img.shields.io/pypi/v/docling)](https://pypi.org/project/docling/)
 [![PyPI - Python Version](https://img.shields.io/pypi/pyversions/docling)](https://pypi.org/project/docling/)
-[![Poetry](https://img.shields.io/endpoint?url=https://python-poetry.org/badge/v0.json)](https://python-poetry.org/)
-[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
-[![Imports: isort](https://img.shields.io/badge/%20imports-isort-%231674b1?style=flat&labelColor=ef8336)](https://pycqa.github.io/isort/)
+[![uv](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/uv/main/assets/badge/v0.json)](https://github.com/astral-sh/uv)
+[![Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff)
 [![Pydantic v2](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/pydantic/pydantic/main/docs/badge/v2.json)](https://pydantic.dev)
 [![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit&logoColor=white)](https://github.com/pre-commit/pre-commit)
 [![License MIT](https://img.shields.io/github/license/docling-project/docling)](https://opensource.org/licenses/MIT)
--- a/docs/faq/index.md
+++ b/docs/faq/index.md
@ -44,6 +44,23 @@ This is a collection of FAQ collected from the user questions on <https://github
    Source: Issue [#283](https://github.com/docling-project/docling/issues/283#issuecomment-2465035868)


+??? question "Is macOS x86_64 supported?"
+
+    ### Is macOS x86_64 supported?
+
+    Yes, Docling (still) supports running the standard pipeline on macOS x86_64.
+
+    However, users might get into a combination of incompatible dependencies on a fresh install.
+    Because Docling depends on PyTorch which dropped support for macOS x86_64 after the 2.2.2 release,
+    and this old version of PyTorch works only with NumPy 1.x, users **must** ensure the correct NumPy version is running.
+
+    ```shell
+    pip install docling "numpy<2.0.0"
+    ```
+
+    Source: Issue [#1694](https://github.com/docling-project/docling/issues/1694).
+
+
 ??? question "Are text styles (bold, underline, etc) supported?"

    ### Are text styles (bold, underline, etc) supported?
--- a/docs/index.md
+++ b/docs/index.md
@ -6,13 +6,13 @@
 [![arXiv](https://img.shields.io/badge/arXiv-2408.09869-b31b1b.svg)](https://arxiv.org/abs/2408.09869)
 [![PyPI version](https://img.shields.io/pypi/v/docling)](https://pypi.org/project/docling/)
 [![PyPI - Python Version](https://img.shields.io/pypi/pyversions/docling)](https://pypi.org/project/docling/)
-[![Poetry](https://img.shields.io/endpoint?url=https://python-poetry.org/badge/v0.json)](https://python-poetry.org/)
-[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
-[![Imports: isort](https://img.shields.io/badge/%20imports-isort-%231674b1?style=flat&labelColor=ef8336)](https://pycqa.github.io/isort/)
+[![uv](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/uv/main/assets/badge/v0.json)](https://github.com/astral-sh/uv)
+[![Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff)
 [![Pydantic v2](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/pydantic/pydantic/main/docs/badge/v2.json)](https://pydantic.dev)
 [![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit&logoColor=white)](https://github.com/pre-commit/pre-commit)
 [![License MIT](https://img.shields.io/github/license/docling-project/docling)](https://opensource.org/licenses/MIT)
 [![PyPI Downloads](https://static.pepy.tech/badge/docling/month)](https://pepy.tech/projects/docling)
+[![Docling Actor](https://apify.com/actor-badge?actor=vancura/docling?fpr=docling)](https://apify.com/vancura/docling)
 [![OpenSSF Best Practices](https://www.bestpractices.dev/projects/10101/badge)](https://www.bestpractices.dev/projects/10101)
 [![LF AI & Data](https://img.shields.io/badge/LF%20AI%20%26%20Data-003778?logo=linuxfoundation&logoColor=fff&color=0094ff&labelColor=003778)](https://lfaidata.foundation/projects/)

--- a/docs/installation/index.md
+++ b/docs/installation/index.md
@ -129,5 +129,5 @@ Works on macOS, Linux, and Windows, with support for both x86_64 and arm64 archi
 To develop Docling features, bugfixes etc., install as follows from your local clone's root dir:

 ```bash
-poetry install --all-extras
+uv sync --all-extras
 ```
--- a/poetry.lock
+++ b/poetry.lock
--- a/pyproject.toml
+++ b/pyproject.toml
@ -1,20 +1,8 @@
-[tool.poetry]
+[project]
 name = "docling"
 version = "2.35.0"  # 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>",
-  "Michele Dolfi <dol@zurich.ibm.com>",
-  "Maxim Lysak <mly@zurich.ibm.com>",
-  "Nikos Livathinos <nli@zurich.ibm.com>",
-  "Ahmed Nassar <ahn@zurich.ibm.com>",
-  "Panos Vagenas <pva@zurich.ibm.com>",
-  "Peter Staar <taa@zurich.ibm.com>",
-]
 license = "MIT"
-readme = "README.md"
-repository = "https://github.com/docling-project/docling"
-homepage = "https://github.com/docling-project/docling"
 keywords = [
  "docling",
  "convert",
@ -29,149 +17,137 @@ keywords = [
  "table former",
 ]
 classifiers = [
-  "License :: OSI Approved :: MIT License",
  "Operating System :: MacOS :: MacOS X",
  "Operating System :: POSIX :: Linux",
+  "Operating System :: Microsoft :: Windows",
  "Development Status :: 5 - Production/Stable",
  "Intended Audience :: Developers",
  "Intended Audience :: Science/Research",
  "Topic :: Scientific/Engineering :: Artificial Intelligence",
  "Programming Language :: Python :: 3",
+  "Programming Language :: Python :: 3.9",
+  "Programming Language :: Python :: 3.10",
+  "Programming Language :: Python :: 3.11",
+  "Programming Language :: Python :: 3.12",
+  "Programming Language :: Python :: 3.13",
 ]
-packages = [{ include = "docling" }]
-
-[tool.poetry.dependencies]
-######################
-# actual dependencies:
-######################
-python = "^3.9"
-pydantic = "^2.0.0"
-docling-core = {version = "^2.31.2", extras = ["chunking"]}
-docling-ibm-models = "^3.4.0"
-docling-parse = "^4.0.0"
-filetype = "^1.2.0"
-pypdfium2 = "^4.30.0"
-pydantic-settings = "^2.3.0"
-huggingface_hub = ">=0.23,<1"
-requests = "^2.32.2"
-easyocr = "^1.7"
-tesserocr = { version = "^2.7.1", optional = true }
-certifi = ">=2024.7.4"
-rtree = "^1.3.0"
-scipy = [
-  { version = "^1.6.0", markers = "python_version >= '3.10'" },
-  { version = ">=1.6.0,<1.14.0", markers = "python_version < '3.10'" },
+readme = "README.md"
+authors = [
+  { name = "Christoph Auer", email = "cau@zurich.ibm.com" },
+  { name = "Michele Dolfi", email = "dol@zurich.ibm.com" },
+  { name = "Maxim Lysak", email = "mly@zurich.ibm.com" },
+  { name = "Nikos Livathinos", email = "nli@zurich.ibm.com" },
+  { name = "Ahmed Nassar", email = "ahn@zurich.ibm.com" },
+  { name = "Panos Vagenas", email = "pva@zurich.ibm.com" },
+  { name = "Peter Staar", email = "taa@zurich.ibm.com" },
 ]
-typer = ">=0.12.5,<0.16.0"
-python-docx = "^1.1.2"
-python-pptx = "^1.0.2"
-beautifulsoup4 = "^4.12.3"
-pandas = "^2.1.4"
-marko = "^2.1.2"
-openpyxl = "^3.1.5"
-lxml = ">=4.0.0,<6.0.0"
-ocrmac = { version = "^1.0.0", markers = "sys_platform == 'darwin'", optional = true }
-rapidocr-onnxruntime = { version = "^1.4.0", optional = true, markers = "python_version < '3.13'" }
-onnxruntime = [
-  # 1.19.2 is the last version with python3.9 support,
-  # see https://github.com/microsoft/onnxruntime/releases/tag/v1.20.0
-  { version = ">=1.7.0,<1.20.0", optional = true, markers = "python_version < '3.10'" },
-  { version = "^1.7.0", optional = true, markers = "python_version >= '3.10'" },
+requires-python = '>=3.9,<4.0'
+dependencies = [
+  'pydantic (>=2.0.0,<3.0.0)',
+  'docling-core[chunking] (>=2.29.0,<3.0.0)',
+  'docling-ibm-models (>=3.4.4,<4.0.0)',
+  'docling-parse (>=4.0.0,<5.0.0)',
+  'filetype (>=1.2.0,<2.0.0)',
+  'pypdfium2 (>=4.30.0,<5.0.0)',
+  'pydantic-settings (>=2.3.0,<3.0.0)',
+  'huggingface_hub (>=0.23,<1)',
+  'requests (>=2.32.2,<3.0.0)',
+  'easyocr (>=1.7,<2.0)',
+  'certifi (>=2024.7.4)',
+  'rtree (>=1.3.0,<2.0.0)',
+  'typer (>=0.12.5,<0.16.0)',
+  'python-docx (>=1.1.2,<2.0.0)',
+  'python-pptx (>=1.0.2,<2.0.0)',
+  'beautifulsoup4 (>=4.12.3,<5.0.0)',
+  'pandas (>=2.1.4,<3.0.0)',
+  'marko (>=2.1.2,<3.0.0)',
+  'openpyxl (>=3.1.5,<4.0.0)',
+  'lxml (>=4.0.0,<6.0.0)',
+  'pillow (>=10.0.0,<12.0.0)',
+  'tqdm (>=4.65.0,<5.0.0)',
+  'pluggy (>=1.0.0,<2.0.0)',
+  'pylatexenc (>=2.10,<3.0)',
+  'click (<8.2.0)',
+  'scipy (>=1.6.0,<2.0.0)',
+  # 'scipy (>=1.6.0,<2.0.0) ; python_version >= "3.10"',
+  # 'scipy (>=1.6.0,<1.14.0) ; python_version < "3.10"',
 ]

-transformers = [
-  { markers = "sys_platform != 'darwin' or platform_machine != 'x86_64'", version = "^4.46.0", optional = true },
-  { markers = "sys_platform == 'darwin' and platform_machine == 'x86_64'", version = "~4.42.0", optional = true },
-]
-accelerate = [
-  { markers = "sys_platform != 'darwin' or platform_machine != 'x86_64'", version = "^1.2.1", optional = true },
-]
-pillow = ">=10.0.0,<12.0.0"
-tqdm = "^4.65.0"
-pluggy = "^1.0.0"
-pylatexenc = "^2.10"
-click = "<8.2.0"
+[project.urls]
+homepage = "https://github.com/docling-project/docling"
+repository = "https://github.com/docling-project/docling"
+issues = "https://github.com/docling-project/docling/issues"
+changelog = "https://github.com/docling-project/docling/blob/main/CHANGELOG.md"

-[tool.poetry.group.dev.dependencies]
-python = "^3.9.2"
-black = { extras = ["jupyter"], version = "^24.4.2" }
-pytest = "^7.2.2"
-pre-commit = "^3.7.1"
-mypy = "^1.10.1"
-isort = "^5.10.1"
-python-semantic-release = "^7.32.2"
-flake8 = "^6.0.0"
-pyproject-flake8 = "^6.0.0"
-pytest-xdist = "^3.3.1"
-types-requests = "^2.31.0.2"
-flake8-pyproject = "^1.2.3"
-pylint = "^2.17.5"
-pandas-stubs = "^2.1.4.231227"
-ipykernel = "^6.29.5"
-ipywidgets = "^8.1.5"
-nbqa = "^1.9.0"
-types-openpyxl = "^3.1.5.20241114"
-types-tqdm = "^4.67.0.20241221"
-coverage = "^7.6.2"
-pytest-cov = "^6.0.0"
+[project.entry-points.docling]
+"docling_defaults" = "docling.models.plugins.defaults"

-[tool.poetry.group.docs.dependencies]
-mkdocs-material = "^9.5.40"
-mkdocs-jupyter = "^0.25.0"
-mkdocs-click = "^0.8.1"
-mkdocstrings = { extras = ["python"], version = "^0.27.0" }
-griffe-pydantic = "^1.1.0"
-
-[tool.poetry.group.examples.dependencies]
-datasets = "^2.21.0"
-python-dotenv = "^1.0.1"
-langchain-huggingface = "^0.0.3"
-langchain-milvus = "^0.1.4"
-langchain-text-splitters = "^0.2.4"
-
-[tool.poetry.group.constraints]
-optional = true
-
-[tool.poetry.group.constraints.dependencies]
-numpy = [
-  { version = ">=1.24.4,<3.0.0", markers = 'python_version >= "3.10"' },
-  { version = ">=1.24.4,<2.1.0", markers = 'python_version < "3.10"' },
-]
-
-[tool.poetry.group.mac_intel]
-optional = true
-
-[tool.poetry.group.mac_intel.dependencies]
-torch = [
-  { markers = "sys_platform != 'darwin' or platform_machine != 'x86_64'", version = "^2.2.2" },
-  { markers = "sys_platform == 'darwin' and platform_machine == 'x86_64'", version = "~2.2.2" },
-]
-torchvision = [
-  { markers = "sys_platform != 'darwin' or platform_machine != 'x86_64'", version = "^0" },
-  { markers = "sys_platform == 'darwin' and platform_machine == 'x86_64'", version = "~0.17.2" },
-]
-
-
-[tool.poetry.group.lm.dependencies]
-peft = "^0.15.2"
-backoff = "^2.2.1"
-
-[tool.poetry.extras]
-tesserocr = ["tesserocr"]
-ocrmac = ["ocrmac"]
-vlm = ["transformers", "accelerate"]
-rapidocr = ["rapidocr-onnxruntime", "onnxruntime"]
-
-[tool.poetry.scripts]
+[project.scripts]
 docling = "docling.cli.main:app"
 docling-tools = "docling.cli.tools:app"

-[tool.poetry.plugins."docling"]
-"docling_defaults" = "docling.models.plugins.defaults"
+[project.optional-dependencies]
+tesserocr = ['tesserocr (>=2.7.1,<3.0.0)']
+ocrmac = ['ocrmac (>=1.0.0,<2.0.0) ; sys_platform == "darwin"']
+vlm = [
+  'transformers (>=4.46.0,<5.0.0)',
+  'accelerate (>=1.2.1,<2.0.0)',
+  'mlx-vlm >=0.1.22 ; python_version >= "3.10" and sys_platform == "darwin" and platform_machine == "arm64"',
+]
+rapidocr = [
+  'rapidocr-onnxruntime (>=1.4.0,<2.0.0) ; python_version < "3.13"',
+  'onnxruntime (>=1.7.0,<2.0.0)',
+  # 'onnxruntime (>=1.7.0,<2.0.0) ; python_version >= "3.10"',
+  # 'onnxruntime (>=1.7.0,<1.20.0) ; python_version < "3.10"',
+]

-[build-system]
-requires = ["poetry-core"]
-build-backend = "poetry.core.masonry.api"
+[dependency-groups]
+dev = [
+    "pre-commit~=3.7",
+    "mypy~=1.10",
+    "types-setuptools~=70.3",
+    "pandas-stubs~=2.1",
+    "types-openpyxl~=3.1",
+    "types-requests~=2.31",
+    "boto3-stubs~=1.37",
+    "types-urllib3~=1.26",
+    "types-tqdm~=4.67",
+    "coverage~=7.6",
+    "pytest~=8.3",
+    "pytest-cov>=6.1.1",
+    "pytest-dependency~=0.6",
+    "pytest-xdist~=3.3",
+    "ipykernel~=6.29",
+    "ipywidgets~=8.1",
+    "nbqa~=1.9",
+    "python-semantic-release~=7.32",
+]
+docs = [
+  "mkdocs-material~=9.5",
+  "mkdocs-jupyter~=0.25",
+  "mkdocs-click~=0.8",
+  "mkdocstrings[python]~=0.27",
+  "griffe-pydantic~=1.1",
+]
+examples = [
+  "datasets~=2.21",
+  "python-dotenv~=1.0",
+  "langchain-huggingface>=0.0.3",
+  "langchain-milvus~=0.1",
+  "langchain-text-splitters~=0.2",
+]
+constraints = [
+  'onnxruntime (>=1.7.0,<2.0.0) ; python_version >= "3.10"',
+  'onnxruntime (>=1.7.0,<1.20.0) ; python_version < "3.10"',
+]
+
+
+[tool.uv]
+package = true
+default-groups = "all"
+
+[tool.setuptools.packages.find]
+include = ["docling*"]

 [tool.ruff]
 target-version = "py39"
@ -187,51 +163,51 @@ skip-magic-trailing-comma = false

 [tool.ruff.lint]
 select = [
-    # "B",  # flake8-bugbear
-    "C",  # flake8-comprehensions
-    "C9",  # mccabe
-    # "D",  # flake8-docstrings
-    "E",  # pycodestyle errors (default)
-    "F",  # pyflakes (default)
-    "I",  # isort
-    "PD", # pandas-vet
-    "PIE", # pie
-    # "PTH", # pathlib
-    "Q",  # flake8-quotes
-    # "RET", # return
-    "RUF", # Enable all ruff-specific checks
-    # "SIM", # simplify
-    "S307", # eval
-    # "T20",  # (disallow print statements) keep debugging statements out of the codebase
-    "W",  # pycodestyle warnings
-    "ASYNC", # async
-    "UP", # pyupgrade
+  # "B",  # flake8-bugbear
+  "C",  # flake8-comprehensions
+  "C9", # mccabe
+  # "D",  # flake8-docstrings
+  "E",   # pycodestyle errors (default)
+  "F",   # pyflakes (default)
+  "I",   # isort
+  "PD",  # pandas-vet
+  "PIE", # pie
+  # "PTH", # pathlib
+  "Q", # flake8-quotes
+  # "RET", # return
+  "RUF", # Enable all ruff-specific checks
+  # "SIM", # simplify
+  "S307", # eval
+  # "T20",  # (disallow print statements) keep debugging statements out of the codebase
+  "W",     # pycodestyle warnings
+  "ASYNC", # async
+  "UP",    # pyupgrade
 ]

 ignore = [
-    "C408",  # Unnecessary `dict()` call (rewrite as a literal)
-    "E501",  # Line too long, handled by ruff formatter
-    "D107", # "Missing docstring in __init__",
-    "F401",  # imported but unused; consider using `importlib.util.find_spec` to test for "
-    "F811", # "redefinition of the same function"
-    "PL", # Pylint
-    "RUF012", # Mutable Class Attributes
-    "UP006",  # List vs list, etc
-    "UP007", # Option and Union
-    "UP035",  # `typing.Set` is deprecated, use `set` instead"
+  "C408",   # Unnecessary `dict()` call (rewrite as a literal)
+  "E501",   # Line too long, handled by ruff formatter
+  "D107",   # "Missing docstring in __init__",
+  "F401",   # imported but unused; consider using `importlib.util.find_spec` to test for "
+  "F811",   # "redefinition of the same function"
+  "PL",     # Pylint
+  "RUF012", # Mutable Class Attributes
+  "UP006",  # List vs list, etc
+  "UP007",  # Option and Union
+  "UP035",  # `typing.Set` is deprecated, use `set` instead"
 ]

 #extend-select = []

 [tool.ruff.lint.pep8-naming]
 classmethod-decorators = [
-    # Allow Pydantic's `@validator` decorator to trigger class method treatment.
-    "pydantic.validator",
+  # Allow Pydantic's `@validator` decorator to trigger class method treatment.
+  "pydantic.validator",
 ]

 [tool.ruff.lint.per-file-ignores]
 "__init__.py" = ["E402", "F401"]
-"tests/*.py" = ["ASYNC"] # Disable ASYNC check for tests
+"tests/*.py" = ["ASYNC"]         # Disable ASYNC check for tests

 [tool.ruff.lint.mccabe]
 max-complexity = 20
--- a/uv.lock
+++ b/uv.lock