feat(docling-serve): add DoclingServeConverter integration

Adds a new `docling-serve-haystack` integration with a `DoclingServeConverter`
component that converts documents via a remote DoclingServe HTTP server instead
of loading heavy ML dependencies locally (no PyTorch required).

- Supports URLs, local file paths, and ByteStream sources
- Export formats: Markdown (default), plain text, JSON
- Both sync `run()` and async `arun()` methods
- Configurable conversion options, timeout, and optional API key auth
- Full unit test suite (mocked httpx) + integration test markers
- CI workflow, labeler, coverage comment, and root README table entry

Closes #2960

Author: SyedShahmeerAli12

.github/labeler.yml

@@ -64,6 +64,11 @@ integration:docling:
       - any-glob-to-any-file: "integrations/docling/**/*"
       - any-glob-to-any-file: ".github/workflows/docling.yml"
 
+integration:docling-serve:
+  - changed-files:
+      - any-glob-to-any-file: "integrations/docling_serve/**/*"
+      - any-glob-to-any-file: ".github/workflows/docling_serve.yml"
+
 integration:elasticsearch:
   - changed-files:
       - any-glob-to-any-file: "integrations/elasticsearch/**/*"

.github/workflows/CI_coverage_comment.yml

@@ -15,6 +15,7 @@ on:
       - "Test / cohere"
       - "Test / cometapi"
       - "Test / deepeval"
+      - "Test / docling_serve"
       - "Test / dspy"
       - "Test / elasticsearch"
       - "Test / faiss"

.github/workflows/docling_serve.yml

@@ -0,0 +1,90 @@
+name: Test / docling_serve
+
+on:
+  schedule:
+    - cron: "0 0 * * *"
+  pull_request:
+    paths:
+      - "integrations/docling_serve/**"
+      - "!integrations/docling_serve/*.md"
+      - ".github/workflows/docling_serve.yml"
+
+defaults:
+  run:
+    working-directory: integrations/docling_serve
+
+concurrency:
+  group: docling_serve-${{ github.head_ref }}
+  cancel-in-progress: true
+
+env:
+  PYTHONUNBUFFERED: "1"
+  FORCE_COLOR: "1"
+
+jobs:
+  run:
+    name: Python ${{ matrix.python-version }} on ${{ startsWith(matrix.os, 'macos-') && 'macOS' || startsWith(matrix.os, 'windows-') && 'Windows' || 'Linux' }}
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu-latest]
+        python-version: ["3.10", "3.14"]
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install Hatch
+        run: pip install hatch
+
+      - name: Lint
+        if: matrix.python-version == '3.10' && runner.os == 'Linux'
+        run: hatch run fmt-check && hatch run test:types
+
+      - name: Run unit tests
+        run: hatch run test:unit-cov-retry
+
+      - name: Store unit tests coverage
+        id: coverage_comment
+        if: matrix.python-version == '3.10' && runner.os == 'Linux'
+        uses: py-cov-action/python-coverage-comment-action@7188638f871f721a365d644f505d1ff3df20d683 # v3.40
+        with:
+          GITHUB_TOKEN: ${{ github.token }}
+          COVERAGE_PATH: integrations/docling_serve
+          SUBPROJECT_ID: docling_serve
+          MINIMUM_GREEN: 90
+          MINIMUM_ORANGE: 60
+
+      - name: Upload coverage comment to be posted
+        if: matrix.python-version == '3.10' && runner.os == 'Linux' && github.event_name == 'pull_request' && steps.coverage_comment.outputs.COMMENT_FILE_WRITTEN == 'true'
+        uses: actions/upload-artifact@v4
+        with:
+          name: coverage-comment-docling_serve
+          path: python-coverage-comment-action-docling_serve.txt
+
+      - name: Run unit tests with lowest direct dependencies
+        run: |
+          hatch run uv pip compile pyproject.toml --resolution lowest-direct --output-file requirements_lowest_direct.txt
+          hatch -e test env run -- uv pip install -r requirements_lowest_direct.txt
+          hatch run test:unit
+
+      - name: Nightly - run unit tests with Haystack main branch
+        if: github.event_name == 'schedule'
+        run: |
+          hatch env prune
+          hatch -e test env run -- uv pip install git+https://github.com/deepset-ai/haystack.git@main
+          hatch run test:unit
+
+  notify-slack-on-failure:
+    needs: run
+    if: failure() && github.event_name == 'schedule'
+    runs-on: ubuntu-latest
+    steps:
+      - uses: deepset-ai/notify-slack-action@3cda73b77a148f16f703274198e7771340cf862b # v1
+        with:
+          slack-webhook-url: ${{ secrets.SLACK_WEBHOOK_URL_NOTIFICATIONS }}

README.md

@@ -38,6 +38,7 @@ Please check out our [Contribution Guidelines](CONTRIBUTING.md) for all the deta
 | [cometapi-haystack](integrations/cometapi/)                             | Generator | [![PyPI - Version](https://img.shields.io/pypi/v/cometapi-haystack.svg)](https://pypi.org/project/cometapi-haystack)                                     | [![Test / cometapi](https://github.com/deepset-ai/haystack-core-integrations/actions/workflows/cometapi.yml/badge.svg)](https://github.com/deepset-ai/haystack-core-integrations/actions/workflows/cometapi.yml)                                           | [![Coverage badge](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/deepset-ai/haystack-core-integrations/python-coverage-comment-action-data-cometapi/endpoint.json&label=)](https://htmlpreview.github.io/?https://github.com/deepset-ai/haystack-core-integrations/blob/python-coverage-comment-action-data-cometapi/htmlcov/index.html) | [![Coverage badge](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/deepset-ai/haystack-core-integrations/python-coverage-comment-action-data-cometapi-combined/endpoint.json&label=)](https://htmlpreview.github.io/?https://github.com/deepset-ai/haystack-core-integrations/blob/python-coverage-comment-action-data-cometapi-combined/htmlcov/index.html) |
 | [deepeval-haystack](integrations/deepeval/)                             | Evaluator                   | [![PyPI - Version](https://img.shields.io/pypi/v/deepeval-haystack.svg)](https://pypi.org/project/deepeval-haystack)                                     | [![Test / deepeval](https://github.com/deepset-ai/haystack-core-integrations/actions/workflows/deepeval.yml/badge.svg)](https://github.com/deepset-ai/haystack-core-integrations/actions/workflows/deepeval.yml)                                           | [![Coverage badge](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/deepset-ai/haystack-core-integrations/python-coverage-comment-action-data-deepeval/endpoint.json&label=)](https://htmlpreview.github.io/?https://github.com/deepset-ai/haystack-core-integrations/blob/python-coverage-comment-action-data-deepeval/htmlcov/index.html) | [![Coverage badge](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/deepset-ai/haystack-core-integrations/python-coverage-comment-action-data-deepeval-combined/endpoint.json&label=)](https://htmlpreview.github.io/?https://github.com/deepset-ai/haystack-core-integrations/blob/python-coverage-comment-action-data-deepeval-combined/htmlcov/index.html) |
 | [docling-haystack](integrations/docling/) | Converter | [![PyPI - Version](https://img.shields.io/pypi/v/docling-haystack.svg)](https://pypi.org/project/docling-haystack) | [![Test / docling](https://github.com/deepset-ai/haystack-core-integrations/actions/workflows/docling.yml/badge.svg)](https://github.com/deepset-ai/haystack-core-integrations/actions/workflows/docling.yml) | [![Coverage badge](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/deepset-ai/haystack-core-integrations/python-coverage-comment-action-data-docling/endpoint.json&label=)](https://htmlpreview.github.io/?https://github.com/deepset-ai/haystack-core-integrations/blob/python-coverage-comment-action-data-docling/htmlcov/index.html) | [![Coverage badge](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/deepset-ai/haystack-core-integrations/python-coverage-comment-action-data-docling-combined/endpoint.json&label=)](https://htmlpreview.github.io/?https://github.com/deepset-ai/haystack-core-integrations/blob/python-coverage-comment-action-data-docling-combined/htmlcov/index.html) |
+| [docling-serve-haystack](integrations/docling_serve/) | Converter | [![PyPI - Version](https://img.shields.io/pypi/v/docling-serve-haystack.svg)](https://pypi.org/project/docling-serve-haystack) | [![Test / docling_serve](https://github.com/deepset-ai/haystack-core-integrations/actions/workflows/docling_serve.yml/badge.svg)](https://github.com/deepset-ai/haystack-core-integrations/actions/workflows/docling_serve.yml) | [![Coverage badge](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/deepset-ai/haystack-core-integrations/python-coverage-comment-action-data-docling_serve/endpoint.json&label=)](https://htmlpreview.github.io/?https://github.com/deepset-ai/haystack-core-integrations/blob/python-coverage-comment-action-data-docling_serve/htmlcov/index.html) | N/A |
 | [dspy-haystack](integrations/dspy/)                                     | Generator                   | [![PyPI - Version](https://img.shields.io/pypi/v/dspy-haystack.svg)](https://pypi.org/project/dspy-haystack)                                             | [![Test / dspy](https://github.com/deepset-ai/haystack-core-integrations/actions/workflows/dspy.yml/badge.svg)](https://github.com/deepset-ai/haystack-core-integrations/actions/workflows/dspy.yml)                                                       | [![Coverage badge](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/deepset-ai/haystack-core-integrations/python-coverage-comment-action-data-dspy/endpoint.json&label=)](https://htmlpreview.github.io/?https://github.com/deepset-ai/haystack-core-integrations/blob/python-coverage-comment-action-data-dspy/htmlcov/index.html) | [![Coverage badge](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/deepset-ai/haystack-core-integrations/python-coverage-comment-action-data-dspy-combined/endpoint.json&label=)](https://htmlpreview.github.io/?https://github.com/deepset-ai/haystack-core-integrations/blob/python-coverage-comment-action-data-dspy-combined/htmlcov/index.html) |
 | [elasticsearch-haystack](integrations/elasticsearch/)                   | Document Store              | [![PyPI - Version](https://img.shields.io/pypi/v/elasticsearch-haystack.svg)](https://pypi.org/project/elasticsearch-haystack)                           | [![Test / elasticsearch](https://github.com/deepset-ai/haystack-core-integrations/actions/workflows/elasticsearch.yml/badge.svg)](https://github.com/deepset-ai/haystack-core-integrations/actions/workflows/elasticsearch.yml)                            | [![Coverage badge](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/deepset-ai/haystack-core-integrations/python-coverage-comment-action-data-elasticsearch/endpoint.json&label=)](https://htmlpreview.github.io/?https://github.com/deepset-ai/haystack-core-integrations/blob/python-coverage-comment-action-data-elasticsearch/htmlcov/index.html) | [![Coverage badge](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/deepset-ai/haystack-core-integrations/python-coverage-comment-action-data-elasticsearch-combined/endpoint.json&label=)](https://htmlpreview.github.io/?https://github.com/deepset-ai/haystack-core-integrations/blob/python-coverage-comment-action-data-elasticsearch-combined/htmlcov/index.html) |
 | [faiss-haystack](integrations/faiss/)                                   | Document Store              | [![PyPI - Version](https://img.shields.io/pypi/v/faiss-haystack.svg)](https://pypi.org/project/faiss-haystack)                                           | [![Test / faiss](https://github.com/deepset-ai/haystack-core-integrations/actions/workflows/faiss.yml/badge.svg)](https://github.com/deepset-ai/haystack-core-integrations/actions/workflows/faiss.yml)                                                     | [![Coverage badge](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/deepset-ai/haystack-core-integrations/python-coverage-comment-action-data-faiss/endpoint.json&label=)](https://htmlpreview.github.io/?https://github.com/deepset-ai/haystack-core-integrations/blob/python-coverage-comment-action-data-faiss/htmlcov/index.html) | [![Coverage badge](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/deepset-ai/haystack-core-integrations/python-coverage-comment-action-data-faiss-combined/endpoint.json&label=)](https://htmlpreview.github.io/?https://github.com/deepset-ai/haystack-core-integrations/blob/python-coverage-comment-action-data-faiss-combined/htmlcov/index.html) |

integrations/docling_serve/README.md

@@ -0,0 +1,10 @@
+# docling-serve-haystack
+
+[![PyPI - Version](https://img.shields.io/pypi/v/docling-serve-haystack.svg)](https://pypi.org/project/docling-serve-haystack)
+[![PyPI - Python Version](https://img.shields.io/pypi/pyversions/docling-serve-haystack.svg)](https://pypi.org/project/docling-serve-haystack)
+
+- [Changelog](https://github.com/deepset-ai/haystack-core-integrations/blob/main/integrations/docling_serve/CHANGELOG.md)
+
+---
+
+Refer to the general [Contribution Guidelines](https://github.com/deepset-ai/haystack-core-integrations/blob/main/CONTRIBUTING.md).

integrations/docling_serve/pyproject.toml

@@ -0,0 +1,162 @@
+[build-system]
+requires = ["hatchling", "hatch-vcs"]
+build-backend = "hatchling.build"
+
+[project]
+name = "docling-serve-haystack"
+dynamic = ["version"]
+description = "Haystack converter component for DoclingServe — document conversion via HTTP"
+readme = "README.md"
+requires-python = ">=3.10"
+license = "Apache-2.0"
+keywords = ["Haystack", "Docling", "DoclingServe", "document conversion", "PDF", "OCR"]
+authors = [{ name = "deepset GmbH", email = "info@deepset.ai" }]
+classifiers = [
+  "License :: OSI Approved :: Apache Software License",
+  "Development Status :: 4 - Beta",
+  "Programming Language :: Python",
+  "Programming Language :: Python :: 3.10",
+  "Programming Language :: Python :: 3.11",
+  "Programming Language :: Python :: 3.12",
+  "Programming Language :: Python :: 3.13",
+  "Programming Language :: Python :: 3.14",
+  "Programming Language :: Python :: Implementation :: CPython",
+  "Programming Language :: Python :: Implementation :: PyPy",
+]
+dependencies = [
+  "haystack-ai>=2.9.0",
+  "httpx>=0.27.0",
+]
+
+[project.urls]
+Documentation = "https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/docling_serve#readme"
+Issues = "https://github.com/deepset-ai/haystack-core-integrations/issues"
+Source = "https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/docling_serve"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/haystack_integrations"]
+
+[tool.hatch.version]
+source = "vcs"
+tag-pattern = 'integrations\/docling_serve-v(?P<version>.*)'
+
+[tool.hatch.version.raw-options]
+root = "../.."
+git_describe_command = 'git describe --tags --match="integrations/docling_serve-v[0-9]*"'
+
+[tool.hatch.envs.default]
+installer = "uv"
+dependencies = ["haystack-pydoc-tools", "ruff"]
+
+[tool.hatch.envs.default.scripts]
+docs = ["haystack-pydoc pydoc/config_docusaurus.yml"]
+fmt = "ruff check --fix {args}; ruff format {args}"
+fmt-check = "ruff check {args} && ruff format --check {args}"
+
+[tool.hatch.envs.test]
+dependencies = [
+    "pytest",
+    "pytest-asyncio",
+    "pytest-cov",
+    "pytest-rerunfailures",
+    "mypy",
+    "pip",
+]
+
+[tool.hatch.envs.test.scripts]
+unit = 'pytest -m "not integration" {args:tests}'
+integration = 'pytest -m "integration" {args:tests}'
+all = 'pytest {args:tests}'
+unit-cov-retry = 'pytest --cov=haystack_integrations --reruns 3 --reruns-delay 30 -x -m "not integration" {args:tests}'
+types = "mypy -p haystack_integrations.components.converters.docling_serve {args}"
+
+[tool.mypy]
+install_types = true
+non_interactive = true
+check_untyped_defs = true
+disallow_incomplete_defs = true
+
+[[tool.mypy.overrides]]
+module = ["httpx"]
+ignore_missing_imports = true
+
+[tool.ruff]
+line-length = 120
+
+[tool.ruff.lint]
+select = [
+    "A",
+    "ANN",
+    "ARG",
+    "B",
+    "C",
+    "D102",
+    "D103",
+    "D205",
+    "D209",
+    "D213",
+    "D417",
+    "D419",
+    "DTZ",
+    "E",
+    "EM",
+    "F",
+    "I",
+    "ICN",
+    "ISC",
+    "N",
+    "PLC",
+    "PLE",
+    "PLR",
+    "PLW",
+    "Q",
+    "RUF",
+    "S",
+    "T",
+    "TID",
+    "UP",
+    "W",
+    "YTT",
+]
+ignore = [
+    "B027",
+    "B008",
+    "S105",
+    "S106",
+    "S107",
+    "C901",
+    "PLR0911",
+    "PLR0912",
+    "PLR0913",
+    "PLR0915",
+    "ANN401",
+]
+
+[tool.ruff.lint.isort]
+known-first-party = ["haystack_integrations"]
+
+[tool.ruff.lint.flake8-tidy-imports]
+ban-relative-imports = "parents"
+
+[tool.ruff.lint.per-file-ignores]
+"tests/**/*" = ["PLR2004", "S101", "TID252", "D", "ANN"]
+
+[tool.coverage.run]
+source = ["haystack_integrations"]
+branch = true
+relative_files = true
+parallel = false
+
+[tool.coverage.report]
+omit = ["*/tests/*", "*/__init__.py"]
+show_missing = true
+exclude_lines = ["no cov", "if __name__ == .__main__.:", "if TYPE_CHECKING:"]
+
+[tool.pytest.ini_options]
+addopts = "--strict-markers"
+markers = [
+  "integration: integration tests",
+]
+log_cli = true
+asyncio_mode = "auto"
+asyncio_default_fixture_loop_scope = "function"

integrations/docling_serve/src/haystack_integrations/components/converters/docling_serve/__init__.py

@@ -0,0 +1,7 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+
+from haystack_integrations.components.converters.docling_serve.converter import DoclingServeConverter, ExportType
+
+__all__ = ["DoclingServeConverter", "ExportType"]