hetzner-haystack 1.0.0__tar.gz

hetzner_haystack-1.0.0/.gitignore

@@ -0,0 +1,146 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+volumes/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# IDEs
+.vscode
+
+# Docs generation artifacts
+_readme_*.md
+.idea
+
+# macOS
+.DS_Store
+
+# http cache (requests-cache)
+**/http_cache.sqlite
+
+# ruff
+.ruff_cache

hetzner_haystack-1.0.0/LICENSE.txt

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2023-present deepset GmbH
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

hetzner_haystack-1.0.0/PKG-INFO

@@ -0,0 +1,40 @@
+Metadata-Version: 2.5
+Name: hetzner-haystack
+Version: 1.0.0
+Summary: An integration between the Hetzner Inference API and Haystack
+Project-URL: Documentation, https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/hetzner#readme
+Project-URL: Issues, https://github.com/deepset-ai/haystack-core-integrations/issues
+Project-URL: Source, https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/hetzner
+Author-email: deepset GmbH <info@deepset.ai>
+License-Expression: Apache-2.0
+License-File: LICENSE.txt
+Keywords: chat generator,haystack,hetzner,inference,llm,qwen
+Classifier: Development Status :: 4 - Beta
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Programming Language :: Python :: Implementation :: CPython
+Classifier: Programming Language :: Python :: Implementation :: PyPy
+Requires-Python: >=3.10
+Requires-Dist: haystack-ai>=2.22.0
+Description-Content-Type: text/markdown
+
+# hetzner-haystack
+
+[![PyPI - Version](https://img.shields.io/pypi/v/hetzner-haystack.svg)](https://pypi.org/project/hetzner-haystack)
+[![PyPI - Python Version](https://img.shields.io/pypi/pyversions/hetzner-haystack.svg)](https://pypi.org/project/hetzner-haystack)
+
+- [Integration page](https://haystack.deepset.ai/integrations/hetzner)
+- [Changelog](https://github.com/deepset-ai/haystack-core-integrations/blob/main/integrations/hetzner/CHANGELOG.md)
+
+---
+
+## Contributing
+
+Refer to the general [Contribution Guidelines](https://github.com/deepset-ai/haystack-core-integrations/blob/main/CONTRIBUTING.md).
+
+To run integration tests locally, you need to export the `HETZNER_API_KEY` environment variable.

hetzner_haystack-1.0.0/README.md

@@ -0,0 +1,15 @@
+# hetzner-haystack
+
+[![PyPI - Version](https://img.shields.io/pypi/v/hetzner-haystack.svg)](https://pypi.org/project/hetzner-haystack)
+[![PyPI - Python Version](https://img.shields.io/pypi/pyversions/hetzner-haystack.svg)](https://pypi.org/project/hetzner-haystack)
+
+- [Integration page](https://haystack.deepset.ai/integrations/hetzner)
+- [Changelog](https://github.com/deepset-ai/haystack-core-integrations/blob/main/integrations/hetzner/CHANGELOG.md)
+
+---
+
+## Contributing
+
+Refer to the general [Contribution Guidelines](https://github.com/deepset-ai/haystack-core-integrations/blob/main/CONTRIBUTING.md).
+
+To run integration tests locally, you need to export the `HETZNER_API_KEY` environment variable.

hetzner_haystack-1.0.0/pydoc/config_docusaurus.yml

@@ -0,0 +1,13 @@
+loaders:
+  - modules:
+      - haystack_integrations.components.generators.hetzner.chat.chat_generator
+    search_path: [../src]
+processors:
+  - type: filter
+    documented_only: true
+    skip_empty_modules: true
+renderer:
+  description: Hetzner integration for Haystack
+  id: integrations-hetzner
+  filename: hetzner.md
+  title: Hetzner

hetzner_haystack-1.0.0/pyproject.toml

@@ -0,0 +1,162 @@
+[build-system]
+requires = ["hatchling", "hatch-vcs"]
+build-backend = "hatchling.build"
+
+[project]
+name = "hetzner-haystack"
+dynamic = ["version"]
+description = 'An integration between the Hetzner Inference API and Haystack'
+readme = "README.md"
+requires-python = ">=3.10"
+license = "Apache-2.0"
+keywords = ["haystack", "hetzner", "inference", "llm", "chat generator", "qwen"]
+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>=2.22.0"]
+
+[project.urls]
+Documentation = "https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/hetzner#readme"
+Issues = "https://github.com/deepset-ai/haystack-core-integrations/issues"
+Source = "https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/hetzner"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/haystack_integrations"]
+
+[tool.hatch.version]
+source = "vcs"
+tag-pattern = 'integrations\/hetzner-v(?P<version>.*)'
+
+[tool.hatch.version.raw-options]
+root = "../.."
+git_describe_command = 'git describe --tags --match="integrations/hetzner-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}'
+integration-cov-append-retry = 'pytest --cov=haystack_integrations --cov-append --reruns 3 --reruns-delay 30 -x -m "integration" {args:tests}'
+types = "mypy -p haystack_integrations.components.generators.hetzner {args}"
+
+[tool.mypy]
+install_types = true
+non_interactive = true
+check_untyped_defs = true
+disallow_incomplete_defs = true
+
+[tool.ruff]
+line-length = 120
+
+[tool.ruff.lint]
+select = [
+    "A",
+    "ANN",
+    "ARG",
+    "B",
+    "C",
+    "D102",   # Missing docstring in public method
+    "D103",   # Missing docstring in public function
+    "D205",   # 1 blank line required between summary line and description
+    "D209",   # Closing triple quotes go to new line
+    "D213",   # summary lines must be positioned on the second physical line of the docstring
+    "D417",   # Missing argument descriptions in the docstring
+    "D419",   # Docstring is empty
+    "DTZ",
+    "E",
+    "EM",
+    "F",
+    "I",
+    "ICN",
+    "ISC",
+    "N",
+    "PLC",
+    "PLE",
+    "PLR",
+    "PLW",
+    "Q",
+    "RUF",
+    "S",
+    "T",
+    "TID",
+    "UP",
+    "W",
+    "YTT",
+]
+ignore = [
+    # Allow non-abstract empty methods in abstract base classes
+    "B027",
+    # Allow function calls in argument defaults (common Haystack pattern for Secret.from_env_var)
+    "B008",
+    # Ignore checks for possible passwords
+    "S105",
+    "S106",
+    "S107",
+    # Ignore complexity
+    "C901",
+    "PLR0911",
+    "PLR0912",
+    "PLR0913",
+    "PLR0915",
+    "PLR0917",
+    # Allow `Any` type - used legitimately for dynamic types and SDK boundaries
+    "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 can use magic values, assertions, relative imports, and don't need type annotations
+"tests/**/*" = ["PLR2004", "S101", "TID252", "D", "ANN"]
+
+[tool.coverage.run]
+source = ["haystack_integrations"]
+branch = true
+parallel = false
+relative_files = true
+
+[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_default_fixture_loop_scope = "function"

hetzner_haystack-1.0.0/src/haystack_integrations/components/generators/hetzner/__init__.py

@@ -0,0 +1,7 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+
+from .chat.chat_generator import HetznerChatGenerator
+
+__all__ = ["HetznerChatGenerator"]

hetzner_haystack-1.0.0/src/haystack_integrations/components/generators/hetzner/chat/__init__.py

@@ -0,0 +1,7 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+
+from .chat_generator import HetznerChatGenerator
+
+__all__ = ["HetznerChatGenerator"]

hetzner_haystack-1.0.0/src/haystack_integrations/components/generators/hetzner/chat/chat_generator.py

@@ -0,0 +1,179 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+
+from typing import Any, ClassVar
+
+from haystack import component, default_to_dict, logging
+from haystack.components.generators.chat import OpenAIChatGenerator
+from haystack.dataclasses import StreamingCallbackT
+from haystack.tools import ToolsType, serialize_tools_or_toolset
+from haystack.utils import serialize_callable
+from haystack.utils.auth import Secret
+from openai.lib._pydantic import to_strict_json_schema
+from pydantic import BaseModel
+
+logger = logging.getLogger(__name__)
+
+
+@component
+class HetznerChatGenerator(OpenAIChatGenerator):
+    """
+    Enables text generation using the models served by the Hetzner Inference API.
+
+    For the list of available models, see the
+    [Hetzner Inference API docs](https://docs.hetzner.com/general/company-and-policy/experiments/inference/) or query
+    the `/v1/models` endpoint of the API, whose response is definitive.
+
+    You can pass any text generation parameters valid for the Hetzner chat completion API directly to this component
+    using the `generation_kwargs` parameter in `__init__` or in the `run` method.
+
+    The served models accept images alongside text, so
+    [`ImageContent`](https://docs.haystack.deepset.ai/docs/imagecontent) parts can be included in the
+    [`ChatMessage`](https://docs.haystack.deepset.ai/docs/chatmessage)s passed to `run`.
+
+    Usage example:
+    ```python
+    from haystack_integrations.components.generators.hetzner import HetznerChatGenerator
+    from haystack.dataclasses import ChatMessage
+
+    messages = [ChatMessage.from_user("What's Natural Language Processing?")]
+
+    client = HetznerChatGenerator()
+    response = client.run(messages)
+    print(response)
+
+    >>{'replies': [ChatMessage(_content='Natural Language Processing (NLP) is a branch of artificial intelligence
+    >>that focuses on enabling computers to understand, interpret, and generate human language in a way that is
+    >>meaningful and useful.', _role=<ChatRole.ASSISTANT: 'assistant'>, _name=None,
+    >>_meta={'model': 'Qwen/Qwen3.6-35B-A3B-FP8', 'index': 0, 'finish_reason': 'stop',
+    >>'usage': {'prompt_tokens': 15, 'completion_tokens': 36, 'total_tokens': 51}})]}
+    ```
+    """
+
+    SUPPORTED_MODELS: ClassVar[list[str]] = [
+        "Qwen/Qwen3.6-35B-A3B-FP8",
+        "Qwen3.8-27B",
+    ]
+    """The models supported by this component while the Hetzner Inference API is in experimental status.
+    The selection changes over time: query the `/v1/models` endpoint of the API for the definitive list.
+    Models outside this list are not rejected and are passed on to the API as-is."""
+
+    def __init__(
+        self,
+        *,
+        api_key: Secret = Secret.from_env_var("HETZNER_API_KEY"),
+        model: str = "Qwen/Qwen3.6-35B-A3B-FP8",
+        streaming_callback: StreamingCallbackT | None = None,
+        api_base_url: str | None = "https://inference.hetzner.com/api/v1",
+        generation_kwargs: dict[str, Any] | None = None,
+        tools: ToolsType | None = None,
+        timeout: float | None = None,
+        max_retries: int | None = None,
+        http_client_kwargs: dict[str, Any] | None = None,
+    ) -> None:
+        """
+        Creates an instance of HetznerChatGenerator.
+
+        :param api_key:
+            The Hetzner Inference API token.
+        :param model:
+            The name of the Hetzner chat completion model to use. See `SUPPORTED_MODELS`.
+        :param streaming_callback:
+            A callback function that is called when a new token is received from the stream.
+            The callback function accepts StreamingChunk as an argument.
+        :param api_base_url:
+            The Hetzner Inference API base url.
+        :param generation_kwargs:
+            Other parameters to use for the model. These parameters are all sent directly to
+            the Hetzner endpoint.
+            Some of the supported parameters:
+            - `max_tokens`: The maximum number of tokens the output text can have.
+            - `temperature`: What sampling temperature to use. Higher values mean the model will take more risks.
+                Try 0.9 for more creative applications and 0 (argmax sampling) for ones with a well-defined answer.
+            - `top_p`: An alternative to sampling with temperature, called nucleus sampling, where the model
+                considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens
+                comprising the top 10% probability mass are considered.
+            - `stream`: Whether to stream back partial progress. If set, tokens will be sent as data-only server-sent
+                events as they become available, with the stream terminated by a data: [DONE] message.
+            - `response_format`: A JSON schema or a Pydantic model that enforces the structure of the model's response.
+                If provided, the output will always be validated against this
+                format (unless the model returns a tool call).
+                For details, see the [OpenAI Structured Outputs documentation](https://platform.openai.com/docs/guides/structured-outputs).
+                Notes:
+                - For structured outputs with streaming,
+                  the `response_format` must be a JSON schema and not a Pydantic model.
+        :param tools:
+            A list of Tool and/or Toolset objects, or a single Toolset for which the model can prepare calls.
+            Each tool should have a unique name.
+        :param timeout:
+            The timeout for the Hetzner API call.
+        :param max_retries:
+            Maximum number of retries to contact Hetzner after an internal error.
+            If not set, it defaults to either the `OPENAI_MAX_RETRIES` environment variable, or set to 5.
+        :param http_client_kwargs:
+            A dictionary of keyword arguments to configure a custom `httpx.Client`or `httpx.AsyncClient`.
+            For more information, see the [HTTPX documentation](https://www.python-httpx.org/api/#client).
+        """
+        if model not in self.SUPPORTED_MODELS:
+            logger.warning(
+                "Model {model} is not in the list of models known to be served by the Hetzner Inference API: "
+                "{supported_models}. The request is sent anyway; check the `/v1/models` endpoint for the "
+                "current selection.",
+                model=model,
+                supported_models=", ".join(self.SUPPORTED_MODELS),
+            )
+
+        # the @component decorator recreates the class, so the zero-argument form of super() cannot be used
+        super(HetznerChatGenerator, self).__init__(  # noqa: UP008
+            api_key=api_key,
+            model=model,
+            streaming_callback=streaming_callback,
+            api_base_url=api_base_url,
+            generation_kwargs=generation_kwargs,
+            tools=tools,
+            timeout=timeout,
+            max_retries=max_retries,
+            http_client_kwargs=http_client_kwargs,
+        )
+
+    def to_dict(self) -> dict[str, Any]:
+        """
+        Serialize this component to a dictionary.
+
+        :returns:
+            The serialized component as a dictionary.
+        """
+        callback_name = serialize_callable(self.streaming_callback) if self.streaming_callback else None
+        generation_kwargs = self.generation_kwargs.copy()
+        response_format = generation_kwargs.get("response_format")
+        # If the response format is a Pydantic model, it's converted to openai's json schema format
+        # If it's already a json schema, it's left as is
+        if response_format and isinstance(response_format, type) and issubclass(response_format, BaseModel):
+            json_schema = {
+                "type": "json_schema",
+                "json_schema": {
+                    "name": response_format.__name__,
+                    "strict": True,
+                    "schema": to_strict_json_schema(response_format),
+                },
+            }
+
+            generation_kwargs["response_format"] = json_schema
+
+        # if we didn't implement the to_dict method here then the to_dict method of the superclass would be used
+        # which would serialize some fields that we don't want to serialize (e.g. the ones we don't have in
+        # the __init__)
+        # it would be hard to maintain the compatibility as superclass changes
+        return default_to_dict(
+            self,
+            model=self.model,
+            streaming_callback=callback_name,
+            api_base_url=self.api_base_url,
+            generation_kwargs=generation_kwargs,
+            api_key=self.api_key.to_dict(),
+            tools=serialize_tools_or_toolset(self.tools),
+            timeout=self.timeout,
+            max_retries=self.max_retries,
+            http_client_kwargs=self.http_client_kwargs,
+        )

hetzner_haystack-1.0.0/tests/__init__.py

@@ -0,0 +1,3 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0

hetzner_haystack-1.0.0/tests/conftest.py

@@ -0,0 +1,44 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+
+import pytest
+from haystack.dataclasses import ChatMessage
+from haystack.tools import Tool
+
+
+@pytest.fixture(autouse=True)
+def allow_deserialization_of_test_modules(monkeypatch):
+    """
+    haystack-ai >= 3.0 refuses to deserialize classes and callables from modules outside its
+    trusted-module allowlist. Tools and callbacks defined in the test modules live outside that
+    allowlist, so trust them explicitly; haystack-ai 2.x ignores this environment variable.
+    """
+    monkeypatch.setenv("HAYSTACK_DESERIALIZATION_ALLOWLIST", "tests,test_*")
+
+
+def weather(city: str):
+    """Get weather for a given city."""
+    return f"The weather in {city} is sunny and 32°C"
+
+
+def _city_tool(name: str, function):
+    return Tool(
+        name=name,
+        description=f"useful to determine the {name} of a given location",
+        parameters={"type": "object", "properties": {"city": {"type": "string"}}, "required": ["city"]},
+        function=function,
+    )
+
+
+@pytest.fixture
+def tools():
+    return [_city_tool("weather", weather)]
+
+
+@pytest.fixture
+def chat_messages():
+    return [
+        ChatMessage.from_system("You are a helpful assistant"),
+        ChatMessage.from_user("What's the capital of France"),
+    ]

hetzner_haystack-1.0.0/tests/test_hetzner_chat_generator.py

@@ -0,0 +1,278 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+
+import json
+import os
+from unittest.mock import patch
+
+import pytest
+from haystack import Pipeline
+from haystack.components.generators.utils import print_streaming_chunk
+from haystack.dataclasses import ChatMessage, ChatRole, ImageContent, StreamingChunk
+from haystack.utils.auth import Secret
+from openai.types.chat import ChatCompletion, ChatCompletionMessage
+from openai.types.chat.chat_completion import Choice
+from openai.types.completion_usage import CompletionUsage
+from pydantic import BaseModel
+
+from haystack_integrations.components.generators.hetzner.chat.chat_generator import HetznerChatGenerator
+
+DEFAULT_MODEL = "Qwen/Qwen3.6-35B-A3B-FP8"
+DEFAULT_API_BASE_URL = "https://inference.hetzner.com/api/v1"
+COMPONENT_TYPE = "haystack_integrations.components.generators.hetzner.chat.chat_generator.HetznerChatGenerator"
+
+requires_api_key = pytest.mark.skipif(
+    not os.environ.get("HETZNER_API_KEY", None),
+    reason="Export an env var called HETZNER_API_KEY containing the Hetzner API token to run this test.",
+)
+
+# an 8x8 red PNG, small enough to inline and enough to exercise the multimodal request path
+RED_SQUARE_PNG = "iVBORw0KGgoAAAANSUhEUgAAAAgAAAAICAIAAABLbSncAAAAEUlEQVR42mO4o6GBFTEMLQkAe3tLAYZNzu4AAAAASUVORK5CYII="
+
+
+class CalendarEvent(BaseModel):
+    event_name: str
+    event_date: str
+
+
+@pytest.fixture
+def mock_chat_completion():
+    """Mock the Hetzner (OpenAI-compatible) chat completion response and reuse it for tests."""
+    with patch("openai.resources.chat.completions.Completions.create") as mock_chat_completion_create:
+        mock_chat_completion_create.return_value = ChatCompletion(
+            id="foo",
+            model=DEFAULT_MODEL,
+            object="chat.completion",
+            choices=[
+                Choice(
+                    finish_reason="stop",
+                    logprobs=None,
+                    index=0,
+                    message=ChatCompletionMessage(content="Hello world!", role="assistant"),
+                )
+            ],
+            created=1750162525,
+            usage=CompletionUsage(prompt_tokens=57, completion_tokens=40, total_tokens=97),
+        )
+        yield mock_chat_completion_create
+
+
+class TestHetznerChatGenerator:
+    def test_init_default(self, monkeypatch):
+        monkeypatch.setenv("HETZNER_API_KEY", "test-api-key")
+        component = HetznerChatGenerator()
+        assert component.api_key.resolve_value() == "test-api-key"
+        assert component.model == DEFAULT_MODEL
+        assert component.api_base_url == DEFAULT_API_BASE_URL
+        assert component.streaming_callback is None
+        assert not component.generation_kwargs
+
+    def test_init_with_unsupported_model_warns(self, caplog, monkeypatch):
+        monkeypatch.setenv("HETZNER_API_KEY", "test-api-key")
+        component = HetznerChatGenerator(model="some-model-not-served-by-hetzner")
+        # unknown models are passed on to the API, the user is only warned
+        assert component.model == "some-model-not-served-by-hetzner"
+        assert "not in the list of models known to be served by the Hetzner Inference API" in caplog.text
+
+    def test_to_dict_default(self, monkeypatch):
+        monkeypatch.setenv("HETZNER_API_KEY", "test-api-key")
+        data = HetznerChatGenerator().to_dict()
+
+        assert data["type"] == COMPONENT_TYPE
+        assert data["init_parameters"] == {
+            "api_key": {"env_vars": ["HETZNER_API_KEY"], "strict": True, "type": "env_var"},
+            "model": DEFAULT_MODEL,
+            "streaming_callback": None,
+            "api_base_url": DEFAULT_API_BASE_URL,
+            "generation_kwargs": {},
+            "timeout": None,
+            "max_retries": None,
+            "tools": None,
+            "http_client_kwargs": None,
+        }
+
+    def test_to_dict_with_parameters(self, monkeypatch):
+        monkeypatch.setenv("ENV_VAR", "test-api-key")
+        component = HetznerChatGenerator(
+            api_key=Secret.from_env_var("ENV_VAR"),
+            model="Qwen3.8-27B",
+            streaming_callback=print_streaming_chunk,
+            api_base_url="test-base-url",
+            generation_kwargs={"max_tokens": 10, "response_format": CalendarEvent},
+            timeout=10,
+            max_retries=10,
+            http_client_kwargs={"proxy": "http://localhost:8080"},
+        )
+        init_parameters = component.to_dict()["init_parameters"]
+
+        assert init_parameters["api_key"] == {"env_vars": ["ENV_VAR"], "strict": True, "type": "env_var"}
+        assert init_parameters["model"] == "Qwen3.8-27B"
+        assert init_parameters["streaming_callback"] == "haystack.components.generators.utils.print_streaming_chunk"
+        assert init_parameters["api_base_url"] == "test-base-url"
+        assert init_parameters["timeout"] == 10
+        assert init_parameters["max_retries"] == 10
+        assert init_parameters["http_client_kwargs"] == {"proxy": "http://localhost:8080"}
+        # a Pydantic response_format is converted to OpenAI's JSON schema format, everything else is passed through
+        assert init_parameters["generation_kwargs"]["max_tokens"] == 10
+        response_format = init_parameters["generation_kwargs"]["response_format"]
+        assert response_format["type"] == "json_schema"
+        assert response_format["json_schema"]["name"] == "CalendarEvent"
+        assert response_format["json_schema"]["strict"] is True
+        assert response_format["json_schema"]["schema"]["required"] == ["event_name", "event_date"]
+        assert response_format["json_schema"]["schema"]["additionalProperties"] is False
+
+    def test_from_dict(self, monkeypatch):
+        monkeypatch.setenv("HETZNER_API_KEY", "fake-api-key")
+        component = HetznerChatGenerator.from_dict(
+            {
+                "type": COMPONENT_TYPE,
+                "init_parameters": {
+                    "api_key": {"env_vars": ["HETZNER_API_KEY"], "strict": True, "type": "env_var"},
+                    "model": DEFAULT_MODEL,
+                    "api_base_url": "test-base-url",
+                    "streaming_callback": "haystack.components.generators.utils.print_streaming_chunk",
+                    "generation_kwargs": {"max_tokens": 10, "some_test_param": "test-params"},
+                    "timeout": 10,
+                    "max_retries": 10,
+                    "tools": None,
+                    "http_client_kwargs": {"proxy": "http://localhost:8080"},
+                },
+            }
+        )
+
+        assert component.api_key == Secret.from_env_var("HETZNER_API_KEY")
+        assert component.model == DEFAULT_MODEL
+        assert component.api_base_url == "test-base-url"
+        assert component.streaming_callback is print_streaming_chunk
+        assert component.generation_kwargs == {"max_tokens": 10, "some_test_param": "test-params"}
+        assert component.timeout == 10
+        assert component.max_retries == 10
+        assert component.tools is None
+        assert component.http_client_kwargs == {"proxy": "http://localhost:8080"}
+
+    def test_run(self, chat_messages, mock_chat_completion, monkeypatch):
+        monkeypatch.setenv("HETZNER_API_KEY", "fake-api-key")
+        component = HetznerChatGenerator(generation_kwargs={"max_tokens": 10, "temperature": 0.5})
+        response = component.run(chat_messages)
+
+        # the generation kwargs are passed on to the Hetzner endpoint
+        _, kwargs = mock_chat_completion.call_args
+        assert kwargs["model"] == DEFAULT_MODEL
+        assert kwargs["max_tokens"] == 10
+        assert kwargs["temperature"] == 0.5
+
+        assert len(response["replies"]) == 1
+        assert isinstance(response["replies"][0], ChatMessage)
+        assert response["replies"][0].text == "Hello world!"
+
+    def test_serde_in_pipeline(self, monkeypatch, tools):
+        monkeypatch.setenv("ENV_VAR", "test-key")
+        generator = HetznerChatGenerator(
+            api_key=Secret.from_env_var("ENV_VAR"),
+            generation_kwargs={"temperature": 0.7},
+            streaming_callback=print_streaming_chunk,
+            tools=tools,
+        )
+        pipeline = Pipeline()
+        pipeline.add_component("generator", generator)
+
+        component_dict = pipeline.to_dict()["components"]["generator"]
+        assert component_dict["type"] == COMPONENT_TYPE
+        assert component_dict["init_parameters"]["generation_kwargs"] == {"temperature": 0.7}
+
+        # the Tool serialization format is owned by haystack-ai and varies across its versions, so
+        # round-trip the tools through YAML instead of pinning their serialized form
+        new_pipeline = Pipeline.loads(pipeline.dumps())
+        assert new_pipeline == pipeline
+        loaded_generator = new_pipeline.get_component("generator")
+        assert loaded_generator.model == generator.model
+        assert loaded_generator.generation_kwargs == generator.generation_kwargs
+        assert loaded_generator.streaming_callback is print_streaming_chunk
+        assert [tool.name for tool in loaded_generator.tools] == [tool.name for tool in tools]
+        assert [tool.parameters for tool in loaded_generator.tools] == [tool.parameters for tool in tools]
+
+    @requires_api_key
+    @pytest.mark.integration
+    def test_live_run(self):
+        results = HetznerChatGenerator().run([ChatMessage.from_user("What's the capital of France")])
+
+        assert len(results["replies"]) == 1
+        message = results["replies"][0]
+        assert "Paris" in message.text
+        assert DEFAULT_MODEL in message.meta["model"]
+        assert message.meta["finish_reason"] == "stop"
+
+    @requires_api_key
+    @pytest.mark.integration
+    def test_live_run_streaming(self):
+        chunks = []
+
+        def callback(chunk: StreamingChunk) -> None:
+            chunks.append(chunk)
+
+        component = HetznerChatGenerator(streaming_callback=callback)
+        results = component.run([ChatMessage.from_user("What's the capital of France?")])
+
+        message = results["replies"][0]
+        assert "Paris" in message.text
+        assert message.meta["finish_reason"] == "stop"
+        assert len(chunks) > 1
+        assert "Paris" in "".join(chunk.content for chunk in chunks if chunk.content)
+
+    @requires_api_key
+    @pytest.mark.integration
+    def test_live_run_with_tools_and_response(self, tools):
+        initial_messages = [ChatMessage.from_user("What's the weather like in Paris and Berlin?")]
+        component = HetznerChatGenerator(tools=tools)
+        results = component.run(messages=initial_messages, generation_kwargs={"tool_choice": "auto"})
+
+        assert len(results["replies"]) == 1
+        tool_message = results["replies"][0]
+        assert ChatMessage.is_from(tool_message, ChatRole.ASSISTANT)
+        assert tool_message.meta["finish_reason"] == "tool_calls"
+
+        # the model requests the tool once per city, in a single reply
+        tool_calls = tool_message.tool_calls
+        assert len(tool_calls) == 2
+        assert all(tool_call.id and tool_call.tool_name == "weather" for tool_call in tool_calls)
+        assert sorted((tool_call.arguments for tool_call in tool_calls), key=lambda args: args["city"]) == [
+            {"city": "Berlin"},
+            {"city": "Paris"},
+        ]
+
+        # pass the tool results back to the model to get the final response
+        results = component.run(
+            [
+                initial_messages[0],
+                tool_message,
+                ChatMessage.from_tool(tool_result="22° C and sunny", origin=tool_calls[0]),
+                ChatMessage.from_tool(tool_result="16° C and windy", origin=tool_calls[1]),
+            ]
+        )
+        final_message = results["replies"][0]
+        assert final_message.is_from(ChatRole.ASSISTANT)
+        assert "paris" in final_message.text.lower()
+        assert "berlin" in final_message.text.lower()
+
+    @requires_api_key
+    @pytest.mark.integration
+    def test_live_run_with_response_format(self):
+        component = HetznerChatGenerator(generation_kwargs={"response_format": CalendarEvent})
+        results = component.run([ChatMessage.from_user("The marketing summit takes place on October 12th.")])
+
+        event = json.loads(results["replies"][0].text)
+        assert "marketing summit" in event["event_name"].lower()
+        assert isinstance(event["event_date"], str)
+
+    @requires_api_key
+    @pytest.mark.integration
+    def test_live_run_with_image(self):
+        image = ImageContent(base64_image=RED_SQUARE_PNG, mime_type="image/png")
+        component = HetznerChatGenerator()
+        results = component.run([ChatMessage.from_user(content_parts=["What color is this image?", image])])
+
+        message = results["replies"][0]
+        # the model names the color in its own words, so accept any reddish description
+        assert any(color in message.text.lower() for color in ("red", "crimson", "scarlet"))
+        assert message.meta["finish_reason"] == "stop"

hetzner_haystack-1.0.0/tests/test_hetzner_chat_generator_async.py

@@ -0,0 +1,99 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+
+import os
+from unittest.mock import AsyncMock, patch
+
+import pytest
+from haystack.dataclasses import ChatMessage, ChatRole, StreamingChunk
+from openai.types.chat import ChatCompletion, ChatCompletionMessage
+from openai.types.chat.chat_completion import Choice
+from openai.types.completion_usage import CompletionUsage
+
+from haystack_integrations.components.generators.hetzner.chat.chat_generator import HetznerChatGenerator
+
+DEFAULT_MODEL = "Qwen/Qwen3.6-35B-A3B-FP8"
+
+requires_api_key = pytest.mark.skipif(
+    not os.environ.get("HETZNER_API_KEY", None),
+    reason="Export an env var called HETZNER_API_KEY containing the Hetzner API token to run this test.",
+)
+
+
+@pytest.fixture
+def mock_async_chat_completion():
+    """Mock the async Hetzner (OpenAI-compatible) chat completion response and reuse it for tests."""
+    with patch(
+        "openai.resources.chat.completions.AsyncCompletions.create", new_callable=AsyncMock
+    ) as mock_chat_completion_create:
+        mock_chat_completion_create.return_value = ChatCompletion(
+            id="foo",
+            model=DEFAULT_MODEL,
+            object="chat.completion",
+            choices=[
+                Choice(
+                    finish_reason="stop",
+                    logprobs=None,
+                    index=0,
+                    message=ChatCompletionMessage(content="Hello world!", role="assistant"),
+                )
+            ],
+            created=1750162525,
+            usage=CompletionUsage(prompt_tokens=57, completion_tokens=40, total_tokens=97),
+        )
+        yield mock_chat_completion_create
+
+
+@pytest.mark.asyncio
+class TestHetznerChatGeneratorAsync:
+    async def test_run_async(self, chat_messages, mock_async_chat_completion, monkeypatch):
+        monkeypatch.setenv("HETZNER_API_KEY", "fake-api-key")
+        component = HetznerChatGenerator(generation_kwargs={"max_tokens": 10, "temperature": 0.5})
+        response = await component.run_async(chat_messages)
+
+        # the generation kwargs are passed on to the Hetzner endpoint
+        _, kwargs = mock_async_chat_completion.call_args
+        assert kwargs["model"] == DEFAULT_MODEL
+        assert kwargs["max_tokens"] == 10
+        assert kwargs["temperature"] == 0.5
+
+        assert len(response["replies"]) == 1
+        assert isinstance(response["replies"][0], ChatMessage)
+        assert response["replies"][0].text == "Hello world!"
+
+    @requires_api_key
+    @pytest.mark.integration
+    async def test_live_run_async(self):
+        results = await HetznerChatGenerator().run_async([ChatMessage.from_user("What's the capital of France")])
+
+        assert len(results["replies"]) == 1
+        message = results["replies"][0]
+        assert "Paris" in message.text
+        assert DEFAULT_MODEL in message.meta["model"]
+        assert message.meta["finish_reason"] == "stop"
+
+    @requires_api_key
+    @pytest.mark.integration
+    async def test_live_run_with_tools_streaming_async(self, tools):
+        chunks = []
+
+        async def callback(chunk: StreamingChunk) -> None:
+            chunks.append(chunk)
+
+        component = HetznerChatGenerator(tools=tools, streaming_callback=callback)
+        results = await component.run_async(
+            [ChatMessage.from_user("What's the weather like in Paris?")],
+            generation_kwargs={"tool_choice": "auto"},
+        )
+
+        assert len(chunks) > 1
+        assert any(chunk.meta.get("tool_calls") for chunk in chunks), "No tool calls received in streaming"
+
+        tool_message = results["replies"][0]
+        assert ChatMessage.is_from(tool_message, ChatRole.ASSISTANT)
+        assert tool_message.meta["finish_reason"] == "tool_calls"
+        tool_call = tool_message.tool_call
+        assert tool_call.id
+        assert tool_call.tool_name == "weather"
+        assert tool_call.arguments == {"city": "Paris"}