fix: support python 3.13 and docling updates and switch to uv (#48)

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
2025-11-29 00:23:36 +00:00 · 2025-02-19 09:53:07 +01:00
parent 7a351fcdea
commit ae3b4906f1
15 changed files with 4148 additions and 5518 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: '3.12'
-runs:
-  using: 'composite'
-  steps:
-    - name: Install poetry
-      run: pipx install poetry==1.8.5
-      shell: bash
-    - uses: actions/setup-python@v4
-      with:
-        python-version: ${{ inputs.python-version }}
-        cache: 'poetry'
-    - name: Install dependencies
-      run: poetry install --all-extras
-      shell: bash
--- a/.github/scripts/release.sh
+++ b/.github/scripts/release.sh
@@ -10,11 +10,11 @@ fi
 CHGLOG_FILE="${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}"

 # 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=$(mktemp)
--- a/.github/workflows/cd.yml
+++ b/.github/workflows/cd.yml
@@ -14,15 +14,20 @@ jobs:
      - uses: actions/checkout@v4
        with:
          fetch-depth: 0  # for fetching tags, required for semantic-release
-      - uses: ./.github/actions/setup-poetry
+      - name: Install uv and set the python version
+        uses: astral-sh/setup-uv@v5
+        with:
+          enable-cache: true
+      - name: Install dependencies
+        run: uv sync --only-dev
      - name: Check version of potential release
        id: version_check
        run: |
-          TRGT_VERSION=$(poetry run semantic-release print-version)
+          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 != ''
@@ -39,7 +44,12 @@ 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/ci-images-dryrun.yml
+++ b/.github/workflows/ci-images-dryrun.yml
@@ -20,7 +20,7 @@ jobs:
    with:
      publish: false
      build_args: |
-        --build-arg CPU_ONLY=true
+        CPU_ONLY=true
      ghcr_image_name: ds4sd/docling-serve-cpu
      quay_image_name: ""

@@ -37,6 +37,7 @@ jobs:
    with:
      publish: false
      build_args: |
-        --build-arg CPU_ONLY=false
+        CPU_ONLY=false
+      platforms: linux/amd64
      ghcr_image_name: ds4sd/docling-serve
      quay_image_name: ""
--- a/.github/workflows/images.yml
+++ b/.github/workflows/images.yml
@@ -34,7 +34,7 @@ jobs:
      publish: true
      environment: registry-creds
      build_args: |
-        --build-arg CPU_ONLY=true
+        CPU_ONLY=true
      ghcr_image_name: ds4sd/docling-serve-cpu
      quay_image_name: ds4sd/docling-serve-cpu

@@ -53,7 +53,8 @@ jobs:
      publish: true
      environment: registry-creds
      build_args: |
-        --build-arg CPU_ONLY=false
+        CPU_ONLY=false
+      platforms: linux/amd64
      ghcr_image_name: ds4sd/docling-serve
      quay_image_name: ds4sd/docling-serve

--- a/.github/workflows/job-checks.yml
+++ b/.github/workflows/job-checks.yml
@@ -11,11 +11,15 @@ jobs:
        python-version: ['3.12']
    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: Install dependencies
+        run: uv sync --all-extras --no-extra cu124
      - name: Run styling check
-        run: poetry run pre-commit run --all-files
+        run: uv run --no-sync pre-commit run --all-files

  markdown-lint:
    runs-on: ubuntu-latest
--- a/.github/workflows/pypi.yml
+++ b/.github/workflows/pypi.yml
@@ -17,9 +17,14 @@ jobs:
      id-token: write  # IMPORTANT: mandatory for trusted publishing
    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:
+          enable-cache: true
+      - name: Install dependencies
+        run: uv sync --all-extras --no-extra cu124
      - name: Build
-        run: poetry build
+        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
@@ -4,7 +4,7 @@ repos:
    hooks:
      - id: system
        name: Black
-        entry: poetry run black docling_serve tests
+        entry: uv run --no-sync black docling_serve tests
        pass_filenames: false
        language: system
        files: '\.py$'
@@ -12,7 +12,7 @@ repos:
    hooks:
      - id: system
        name: isort
-        entry: poetry run isort docling_serve tests
+        entry: uv run --no-sync isort docling_serve tests
        pass_filenames: false
        language: system
        files: '\.py$'
@@ -20,7 +20,7 @@ repos:
    hooks:
      - id: autoflake
        name: autoflake
-        entry: poetry run autoflake docling_serve tests
+        entry: uv run --no-sync autoflake docling_serve tests
        pass_filenames: false
        language: system
        files: '\.py$'
@@ -28,7 +28,7 @@ repos:
    hooks:
      - id: system
        name: flake8
-        entry: poetry run flake8 docling_serve
+        entry: uv run --no-sync flake8 docling_serve
        pass_filenames: false
        language: system
        files: '\.py$'
@@ -36,14 +36,12 @@ repos:
    hooks:
      - id: system
        name: MyPy
-        entry: poetry run mypy docling_serve
+        entry: uv run --no-sync mypy docling_serve
        pass_filenames: false
        language: system
        files: '\.py$'
-  - repo: local
+  - repo: https://github.com/astral-sh/uv-pre-commit
+    # uv version.
+    rev: 0.6.1
    hooks:
-      - id: system
-        name: Poetry check
-        entry: poetry check --lock
-        pass_filenames: false
-        language: system
+      - id: uv-lock
--- a/.python-version
+++ b/.python-version
@@ -0,0 +1 @@
+3.12
--- a/27
+++ b/27
@@ -3,6 +3,7 @@ ARG BASE_IMAGE=quay.io/sclorg/python-312-c9s:c9s
 FROM ${BASE_IMAGE}

 ARG CPU_ONLY=false
+ARG MODELS_LIST="layout tableformer picture_classifier easyocr"

 USER 0

@@ -21,6 +22,8 @@ RUN --mount=type=bind,source=os-packages.txt,target=/tmp/os-packages.txt \

 ENV TESSDATA_PREFIX=/usr/share/tesseract/tessdata/

+COPY --from=ghcr.io/astral-sh/uv:0.6.1 /uv /uvx /bin/
+
 ###################################################################################################
 # Docling layer                                                                                   #
 ###################################################################################################
@@ -35,27 +38,29 @@ ENV OMP_NUM_THREADS=4
 ENV LANG=en_US.UTF-8
 ENV LC_ALL=en_US.UTF-8
 ENV PYTHONIOENCODING=utf-8
+ENV UV_COMPILE_BYTECODE=1 UV_LINK_MODE=copy
+ENV UV_PROJECT_ENVIRONMENT=/opt/app-root

 ENV WITH_UI=True

-COPY --chown=1001:0 pyproject.toml poetry.lock models_download.py README.md ./
+COPY --chown=1001:0 pyproject.toml uv.lock README.md ./

-RUN pip install --no-cache-dir poetry && \
-    # We already are in a virtual environment, so we don't need to create a new one, only activate it.
-    poetry config virtualenvs.create false && \
-    source /opt/app-root/bin/activate && \
+RUN --mount=type=cache,target=/opt/app-root/src/.cache/uv,uid=1001 \
    if [ "$CPU_ONLY" = "true" ]; then \
-        poetry install --no-root --no-cache --no-interaction --all-extras --with cpu --without dev; \
+        NO_EXTRA=cu124; \
    else \
-        poetry install --no-root --no-cache --no-interaction --all-extras --without dev; \
+        NO_EXTRA=cpu; \
    fi && \
-    echo "Downloading models..." && \
-    python models_download.py && \
-    chown -R 1001:0 /opt/app-root/src && \
-    chmod -R g=u /opt/app-root/src
+    uv sync --frozen --no-install-project --no-dev --all-extras --no-extra ${NO_EXTRA}
+
+RUN echo "Downloading models..." && \
+    docling-tools models download ${MODELS_LIST} && \
+    chown -R 1001:0 /opt/app-root/src/.cache && \
+    chmod -R g=u /opt/app-root/src/.cache

 COPY --chown=1001:0 --chmod=664 ./docling_serve ./docling_serve

+
 EXPOSE 5001

 CMD ["python", "-m", "docling_serve"]
--- a/README.md
+++ b/README.md
@@ -325,10 +325,11 @@ RELOAD=true bash start_server.sh

 The following variables are available:

-`TESSDATA_PREFIX`: Tesseract data location, example `/usr/share/tesseract/tessdata/`.
-`UVICORN_WORKERS`: Number of workers to use.
-`RELOAD`: If `True`, this will enable auto-reload when you modify files, useful for development.
-`WITH_UI`: If `True`, The Gradio UI will be available at `/ui`.
+- `DOCLING_ARTIFACTS_PATH`: if set Docling will use only the local weights of models, for example `/opt/app-root/.cache/docling/cache`.
+- `TESSDATA_PREFIX`: Tesseract data location, example `/usr/share/tesseract/tessdata/`.
+- `UVICORN_WORKERS`: Number of workers to use.
+- `RELOAD`: If `True`, this will enable auto-reload when you modify files, useful for development.
+- `WITH_UI`: If `True`, The Gradio UI will be available at `/ui`.

 ## Get help and support

--- a/models_download.py
+++ b/models_download.py
@@ -1,36 +0,0 @@
-import os
-import zipfile
-
-import requests
-from deepsearch_glm.utils.load_pretrained_models import load_pretrained_nlp_models
-from docling.pipeline.standard_pdf_pipeline import StandardPdfPipeline
-
-# Download Docling models
-StandardPdfPipeline.download_models_hf(force=True)
-load_pretrained_nlp_models(verbose=True)
-
-# Download EasyOCR models
-urls = [
-    "https://github.com/JaidedAI/EasyOCR/releases/download/v1.3/latin_g2.zip",
-    "https://github.com/JaidedAI/EasyOCR/releases/download/pre-v1.1.6/craft_mlt_25k.zip"
-]
-
-local_zip_paths = [
-    "/opt/app-root/src/latin_g2.zip",
-    "/opt/app-root/src/craft_mlt_25k.zip"
-]
-
-extract_path = "/opt/app-root/src/.EasyOCR/model/"
-
-for url, local_zip_path in zip(urls, local_zip_paths):
-    # Download the file
-    response = requests.get(url)
-    with open(local_zip_path, "wb") as file:
-        file.write(response.content)
-
-    # Unzip the file
-    with zipfile.ZipFile(local_zip_path, "r") as zip_ref:
-        zip_ref.extractall(extract_path)
-
-    # Clean up the zip file
-    os.remove(local_zip_path)
--- a/poetry.lock
+++ b/poetry.lock
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,25 +1,25 @@
-[tool.poetry]
+[project]
 name = "docling-serve"
 version = "0.2.0"  # DO NOT EDIT, updated automatically
 description = "Running Docling as a service"
-license = "MIT"
+license = {text = "MIT"}
 authors = [
-    "Michele Dolfi <dol@zurich.ibm.com>",
-    "Christoph Auer <cau@zurich.ibm.com>",
-    "Panos Vagenas <pva@zurich.ibm.com>",
-    "Cesar Berrospi Ramis <ceb@zurich.ibm.com>",
-   "Peter Staar <taa@zurich.ibm.com>",
+    {name="Michele Dolfi", email="dol@zurich.ibm.com"},
+    {name="Guillaume Moutier", email="gmoutier@redhat.com"},
+    {name="Anil Vishnoi", email="avishnoi@redhat.com"},
+    {name="Panos Vagenas", email="pva@zurich.ibm.com"},
+    {name="Panos Vagenas", email="pva@zurich.ibm.com"},
+    {name="Christoph Auer", email="cau@zurich.ibm.com"},
+    {name="Peter Staar", email="taa@zurich.ibm.com"},
 ]
 maintainers = [
-    "Peter Staar <taa@zurich.ibm.com>",
-    "Christoph Auer <cau@zurich.ibm.com>",
-    "Michele Dolfi <dol@zurich.ibm.com>",
-    "Cesar Berrospi Ramis <ceb@zurich.ibm.com>",
-    "Panos Vagenas <pva@zurich.ibm.com>",
+    {name="Michele Dolfi", email="dol@zurich.ibm.com"},
+    {name="Anil Vishnoi", email="avishnoi@redhat.com"},
+    {name="Panos Vagenas", email="pva@zurich.ibm.com"},
+    {name="Christoph Auer", email="cau@zurich.ibm.com"},
+    {name="Peter Staar", email="taa@zurich.ibm.com"},
 ]
 readme = "README.md"
-repository = "https://github.com/DS4SD/docling-serve"
-homepage = "https://github.com/DS4SD/docling-serve"
 classifiers = [
    "License :: OSI Approved :: MIT License",
    "Operating System :: OS Independent",
@@ -28,80 +28,88 @@ classifiers = [
    "Typing :: Typed",
    "Programming Language :: Python :: 3"
 ]
-
-[tool.poetry.dependencies]
-python = ">=3.10,<3.13" # 3.10 needed for Gradio, and no torchvision build for 3.13 yet
-docling = "^2.14.0"
-fastapi = {version = "^0.115.6", extras = ["standard"]}
-gradio = { version = "^5.9.1", optional = true }
-uvicorn = "~0.29.0"
-pydantic = "^2.10.3"
-pydantic-settings = "^2.4.0"
-python-multipart = "^0.0.19"
-httpx = "^0.28.1"
-tesserocr = { version = "^2.7.1", 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 = ">=3.10"
+dependencies = [
+    "docling~=2.23",
+    "fastapi[standard]~=0.115",
+    "httpx~=0.28",
+    "pydantic~=2.10",
+    "pydantic-settings~=2.4",
+    "python-multipart>=0.0.14,<0.1.0",
+    "uvicorn[standard]>=0.29.0,<1.0.0",
 ]

+[project.optional-dependencies]
+ui = [
+    "gradio~=5.9"
+]
+tesserocr = [
+    "tesserocr~=2.7"
+]
+rapidocr = [
+    "rapidocr-onnxruntime~=1.4; python_version<'3.13'",
+    "onnxruntime~=1.7",
+]
+cpu = [
+  "torch>=2.6.0",
+  "torchvision>=0.21.0",
+]
+cu124 = [
+  "torch>=2.6.0",
+  "torchvision>=0.21.0",
+]

-[tool.poetry.extras]
-ui = ["gradio"]
-tesserocr = ["tesserocr"]
-rapidocr = ["rapidocr-onnxruntime", "onnxruntime"]
+[dependency-groups]
+dev = [
+    "autoflake~=2.3",
+    "black~=24.8",
+    "flake8~=7.1",
+    "isort~=5.13",
+    "mypy~=1.11",
+    "pre-commit~=3.8",
+    "pytest~=8.3",
+    "pytest-asyncio~=0.24",
+    "pytest-check~=2.4",
+    "python-semantic-release~=7.32",
+]

+[tool.uv]
+conflicts = [
+  [
+    { extra = "cpu" },
+    { extra = "cu124" },
+  ],
+]

-[tool.poetry.group.pypi-torch]
-optional = false
-
-[tool.poetry.group.pypi-torch.dependencies]
+[tool.uv.sources]
 torch = [
-  {version = "!=2.4.1+cpu" },
+  { index = "pytorch-cpu", extra = "cpu" },
+  { index = "pytorch-cu124", extra = "cu124" },
 ]
 torchvision = [
-  {version = "!=0.19.1+cpu" },
+  { index = "pytorch-cpu", extra = "cpu" },
+  { index = "pytorch-cu124", extra = "cu124" },
 ]

-[tool.poetry.group.cpu]
-optional = true
+[[tool.uv.index]]
+name = "pytorch-cpu"
+url = "https://download.pytorch.org/whl/cpu"
+explicit = true

-[tool.poetry.group.cpu.dependencies]
-torch = [
-    {markers = 'platform_machine=="x86_64" and sys_platform=="linux" and python_version == "3.10"', url="https://download.pytorch.org/whl/cpu/torch-2.4.1%2Bcpu-cp310-cp310-linux_x86_64.whl"},
-    {markers = 'platform_machine=="x86_64" and sys_platform=="linux" and python_version == "3.11"', url="https://download.pytorch.org/whl/cpu/torch-2.4.1%2Bcpu-cp311-cp311-linux_x86_64.whl"},
-    {markers = 'platform_machine=="x86_64" and sys_platform=="linux" and python_version == "3.12"', url="https://download.pytorch.org/whl/cpu/torch-2.4.1%2Bcpu-cp312-cp312-linux_x86_64.whl"},
-]
-torchvision = [
-    {markers = 'platform_machine=="x86_64" and sys_platform=="linux" and python_version == "3.10"', url="https://download.pytorch.org/whl/cpu/torchvision-0.19.1%2Bcpu-cp310-cp310-linux_x86_64.whl"},
-    {markers = 'platform_machine=="x86_64" and sys_platform=="linux" and python_version == "3.11"', url="https://download.pytorch.org/whl/cpu/torchvision-0.19.1%2Bcpu-cp311-cp311-linux_x86_64.whl"},
-    {markers = 'platform_machine=="x86_64" and sys_platform=="linux" and python_version == "3.12"', url="https://download.pytorch.org/whl/cpu/torchvision-0.19.1%2Bcpu-cp312-cp312-linux_x86_64.whl"},
-]
+[[tool.uv.index]]
+name = "pytorch-cu124"
+url = "https://download.pytorch.org/whl/cu124"
+explicit = true

-[tool.poetry.group.constraints.dependencies]
-numpy = [
-    { version = "^2.1.0", markers = 'python_version >= "3.13"' },
-    { version = "^1.24.4", markers = 'python_version < "3.13"' },
-]
+[tool.setuptools.packages.find]
+include = ["docling_serve"]

-[tool.poetry.group.dev.dependencies]
-black = "^24.8.0"
-isort = "^5.13.2"
-pre-commit = "^3.8.0"
-autoflake = "^2.3.1"
-flake8 = "^7.1.1"
-pytest = "^8.3.4"
-pytest-asyncio = "^0.24.0"
-pytest-check = "^2.4.1"
-mypy = "^1.11.2"
-python-semantic-release = "^7.32.2"
-
-[build-system]
-requires = ["poetry-core"]
-build-backend = "poetry.core.masonry.api"
+[project.urls]
+Homepage = "https://github.com/DS4SD/docling-serve"
+# Documentation = "https://ds4sd.github.io/docling"
+Repository = "https://github.com/DS4SD/docling-serve"
+Issues = "https://github.com/DS4SD/docling-serve/issues"
+Changelog = "https://github.com/DS4SD/docling-serve/blob/main/CHANGELOG.md"

 [tool.black]
 line-length = 88
--- a/uv.lock
+++ b/uv.lock