spacy-haystack 0.1.0__tar.gz

spacy_haystack-0.1.0/.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

spacy_haystack-0.1.0/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.

spacy_haystack-0.1.0/PKG-INFO

@@ -0,0 +1,39 @@
+Metadata-Version: 2.4
+Name: spacy-haystack
+Version: 0.1.0
+Summary: Haystack integration for spacy
+Project-URL: Documentation, https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/spacy#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/spacy
+Author-email: deepset GmbH <info@deepset.ai>
+License-Expression: Apache-2.0
+License-File: LICENSE.txt
+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: click>=8.0.0
+Requires-Dist: haystack-ai>=2.23.0
+Requires-Dist: spacy<3.9,>=3.8.13
+Description-Content-Type: text/markdown
+
+# spacy-haystack
+
+[![PyPI - Version](https://img.shields.io/pypi/v/spacy-haystack.svg)](https://pypi.org/project/spacy-haystack)
+[![PyPI - Python Version](https://img.shields.io/pypi/pyversions/spacy-haystack.svg)](https://pypi.org/project/spacy-haystack)
+
+- [Integration page](https://haystack.deepset.ai/integrations/spacy)
+- [Changelog](https://github.com/deepset-ai/haystack-core-integrations/blob/main/integrations/spacy/CHANGELOG.md)
+
+---
+
+## Contributing
+
+Refer to the general [Contribution Guidelines](https://github.com/deepset-ai/haystack-core-integrations/blob/main/CONTRIBUTING.md).

spacy_haystack-0.1.0/README.md

@@ -0,0 +1,13 @@
+# spacy-haystack
+
+[![PyPI - Version](https://img.shields.io/pypi/v/spacy-haystack.svg)](https://pypi.org/project/spacy-haystack)
+[![PyPI - Python Version](https://img.shields.io/pypi/pyversions/spacy-haystack.svg)](https://pypi.org/project/spacy-haystack)
+
+- [Integration page](https://haystack.deepset.ai/integrations/spacy)
+- [Changelog](https://github.com/deepset-ai/haystack-core-integrations/blob/main/integrations/spacy/CHANGELOG.md)
+
+---
+
+## Contributing
+
+Refer to the general [Contribution Guidelines](https://github.com/deepset-ai/haystack-core-integrations/blob/main/CONTRIBUTING.md).

spacy_haystack-0.1.0/pydoc/config_docusaurus.yml

@@ -0,0 +1,13 @@
+loaders:
+  - modules:
+      - haystack_integrations.components.extractors.spacy.named_entity_extractor
+    search_path: [../src]
+processors:
+  - type: filter
+    documented_only: true
+    skip_empty_modules: true
+renderer:
+  description: Spacy integration for Haystack
+  id: integrations-spacy
+  filename: spacy.md
+  title: Spacy

spacy_haystack-0.1.0/pyproject.toml

@@ -0,0 +1,165 @@
+[build-system]
+requires = ["hatchling", "hatch-vcs"]
+build-backend = "hatchling.build"
+
+[project]
+name = "spacy-haystack"
+dynamic = ["version"]
+description = "Haystack integration for spacy"
+readme = "README.md"
+requires-python = ">=3.10"
+license = "Apache-2.0"
+keywords = []
+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",
+]
+# `click` is required to make spacy work but not declared by spacy itself.
+# See https://github.com/explosion/spaCy/issues/13971
+dependencies = ["haystack-ai>=2.23.0", "spacy>=3.8.13,<3.9", "click>=8.0.0"]
+
+[project.urls]
+Documentation = "https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/spacy#readme"
+Issues = "https://github.com/deepset-ai/haystack-core-integrations/issues"
+Source = "https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/spacy"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/haystack_integrations"]
+
+[tool.hatch.version]
+source = "vcs"
+tag-pattern = 'integrations\/spacy-v(?P<version>.*)'
+
+[tool.hatch.version.raw-options]
+root = "../.."
+git_describe_command = 'git describe --tags --match="integrations/spacy-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",
+    # spaCy model used by the integration tests
+    "en-core-web-trf @ https://github.com/explosion/spacy-models/releases/download/en_core_web_trf-3.8.0/en_core_web_trf-3.8.0-py3-none-any.whl",
+]
+
+[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.extractors.spacy {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",
+    # 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"

spacy_haystack-0.1.0/src/haystack_integrations/components/extractors/spacy/__init__.py

@@ -0,0 +1,6 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+from .named_entity_extractor import NamedEntityAnnotation, SpacyNamedEntityExtractor
+
+__all__ = ["NamedEntityAnnotation", "SpacyNamedEntityExtractor"]

spacy_haystack-0.1.0/src/haystack_integrations/components/extractors/spacy/named_entity_extractor.py

@@ -0,0 +1,255 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+
+from collections.abc import Iterator
+from contextlib import contextmanager
+from dataclasses import dataclass, replace
+from typing import Any
+
+from haystack import ComponentError, DeserializationError, Document, component, default_from_dict, default_to_dict
+from haystack.utils.device import ComponentDevice
+from thinc.api import get_current_ops, set_current_ops
+
+import spacy
+from spacy import Language as SpacyPipeline
+
+
+@dataclass
+class NamedEntityAnnotation:
+    """
+    Describes a single NER annotation.
+
+    :param entity:
+        Entity label.
+    :param start:
+        Start index of the entity in the document.
+    :param end:
+        End index of the entity in the document.
+    :param score:
+        Score calculated by the model.
+    """
+
+    entity: str
+    start: int
+    end: int
+    score: float | None = None
+
+
+@component
+class SpacyNamedEntityExtractor:
+    """
+    Annotates named entities in a collection of documents.
+
+    The component can be used with any [spaCy model](https://spacy.io/models) that contains
+    an NER component. Annotations are stored as metadata in the documents.
+
+    Usage example:
+    ```python
+    from haystack import Document
+
+    from haystack_integrations.components.extractors.spacy import SpacyNamedEntityExtractor
+
+    documents = [
+        Document(content="I'm Merlin, the happy pig!"),
+        Document(content="My name is Clara and I live in Berkeley, California."),
+    ]
+    extractor = SpacyNamedEntityExtractor(model="en_core_web_sm")
+    results = extractor.run(documents=documents)["documents"]
+    annotations = [SpacyNamedEntityExtractor.get_stored_annotations(doc) for doc in results]
+    print(annotations)
+    ```
+    """
+
+    _METADATA_KEY = "named_entities"
+
+    def __init__(
+        self,
+        *,
+        model: str,
+        pipeline_kwargs: dict[str, Any] | None = None,
+        device: ComponentDevice | None = None,
+    ) -> None:
+        """
+        Create a Named Entity extractor component.
+
+        :param model:
+            Name of the spaCy model or a path to the model on
+            the local disk.
+        :param pipeline_kwargs:
+            Keyword arguments passed to the pipeline. The
+            pipeline can override these arguments.
+        :param device:
+            The device on which the model is loaded. If `None`,
+            the default device is automatically selected.
+        :raises ValueError:
+            If the device represents multiple devices, which the
+            spaCy backend does not support.
+        """
+        self.model_name_or_path = model
+        self.pipeline_kwargs = pipeline_kwargs or {}
+        self.device = ComponentDevice.resolve_device(device)
+
+        if self.device.has_multiple_devices:
+            msg = "spaCy backend for named entity extractor only supports inference on single devices"
+            raise ValueError(msg)
+
+        self.pipeline: SpacyPipeline | None = None
+        self._warmed_up: bool = False
+
+    def warm_up(self) -> None:
+        """
+        Initialize the component.
+
+        :raises ComponentError:
+            If the component fails to initialize successfully.
+        """
+        if self._warmed_up:
+            return
+
+        try:
+            # We need to initialize the model on the GPU if needed.
+            with self._select_device():
+                self.pipeline = spacy.load(self.model_name_or_path)
+
+            if not self.pipeline.has_pipe("ner"):
+                msg = f"spaCy pipeline '{self.model_name_or_path}' does not contain an NER component"
+                raise ComponentError(msg)
+
+            # Disable unnecessary pipes.
+            pipes_to_keep = ("ner", "tok2vec", "transformer", "curated_transformer")
+            for name in self.pipeline.pipe_names:
+                if name not in pipes_to_keep:
+                    self.pipeline.disable_pipe(name)
+
+            self.pipeline_kwargs = {k: v for k, v in self.pipeline_kwargs.items() if k not in ("texts", "batch_size")}
+            self._warmed_up = True
+        except Exception as e:
+            msg = f"{self.__class__.__name__} failed to initialize."
+            raise ComponentError(msg) from e
+
+    @component.output_types(documents=list[Document])
+    def run(self, documents: list[Document], batch_size: int = 1) -> dict[str, Any]:
+        """
+        Annotate named entities in each document and store the annotations in the document's metadata.
+
+        :param documents:
+            Documents to process.
+        :param batch_size:
+            Batch size used for processing the documents.
+        :returns:
+            Processed documents.
+        :raises ComponentError:
+            If the model fails to process a document.
+        """
+        if not self._warmed_up:
+            self.warm_up()
+
+        texts = [doc.content if doc.content is not None else "" for doc in documents]
+        annotations = self._annotate(texts, batch_size=batch_size)
+
+        if len(annotations) != len(documents):
+            msg = (
+                "NER model did not return the correct number of annotations; "
+                f"got {len(annotations)} but expected {len(documents)}"
+            )
+            raise ComponentError(msg)
+
+        new_documents = []
+        for doc, doc_annotations in zip(documents, annotations, strict=True):
+            new_meta = {**doc.meta, self._METADATA_KEY: doc_annotations}
+            new_documents.append(replace(doc, meta=new_meta))
+
+        return {"documents": new_documents}
+
+    def _annotate(self, texts: list[str], *, batch_size: int = 1) -> list[list[NamedEntityAnnotation]]:
+        """
+        Predict annotations for a collection of documents.
+
+        :param texts:
+            Raw texts to be annotated.
+        :param batch_size:
+            Size of text batches that are
+            passed to the model.
+        :returns:
+            NER annotations.
+        """
+        if not self.initialized:
+            msg = "NER model was not initialized - Did you call `warm_up()`?"
+            raise ComponentError(msg)
+
+        assert self.pipeline is not None  # noqa: S101
+        with self._select_device():
+            outputs = list(self.pipeline.pipe(texts=texts, batch_size=batch_size, **self.pipeline_kwargs))
+
+        return [
+            [
+                NamedEntityAnnotation(entity=entity.label_, start=entity.start_char, end=entity.end_char)
+                for entity in doc.ents
+            ]
+            for doc in outputs
+        ]
+
+    def to_dict(self) -> dict[str, Any]:
+        """
+        Serializes the component to a dictionary.
+
+        :returns:
+            Dictionary with serialized data.
+        """
+        return default_to_dict(
+            self,
+            model=self.model_name_or_path,
+            device=self.device,
+            pipeline_kwargs=self.pipeline_kwargs,
+        )
+
+    @classmethod
+    def from_dict(cls, data: dict[str, Any]) -> "SpacyNamedEntityExtractor":
+        """
+        Deserializes the component from a dictionary.
+
+        :param data:
+            Dictionary to deserialize from.
+        :returns:
+            Deserialized component.
+        """
+        try:
+            return default_from_dict(cls, data)
+        except Exception as e:
+            msg = f"Couldn't deserialize {cls.__name__} instance"
+            raise DeserializationError(msg) from e
+
+    @property
+    def initialized(self) -> bool:
+        """
+        Returns if the extractor is ready to annotate text.
+        """
+        return self.pipeline is not None
+
+    @classmethod
+    def get_stored_annotations(cls, document: Document) -> list[NamedEntityAnnotation] | None:
+        """
+        Returns the document's named entity annotations stored in its metadata, if any.
+
+        :param document:
+            Document whose annotations are to be fetched.
+        :returns:
+            The stored annotations.
+        """
+
+        return document.meta.get(cls._METADATA_KEY)
+
+    @contextmanager
+    def _select_device(self) -> Iterator[None]:
+        """
+        Context manager used to run spaCy models on a specific GPU in a scoped manner.
+        """
+        device_id = self.device.to_spacy()
+        previous_ops = get_current_ops()
+        try:
+            if device_id >= 0:
+                spacy.require_gpu(device_id)
+            yield
+        finally:
+            set_current_ops(previous_ops)

spacy_haystack-0.1.0/tests/__init__.py

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

spacy_haystack-0.1.0/tests/test_named_entity_extractor.py

@@ -0,0 +1,339 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+
+from unittest.mock import patch
+
+import pytest
+from haystack import ComponentError, DeserializationError, Document, Pipeline
+from haystack.utils.device import ComponentDevice, DeviceMap
+from thinc.api import NumpyOps, get_current_ops, set_current_ops
+
+from haystack_integrations.components.extractors.spacy import (
+    NamedEntityAnnotation,
+    SpacyNamedEntityExtractor,
+)
+
+MODULE = "haystack_integrations.components.extractors.spacy.named_entity_extractor"
+COMPONENT_TYPE = f"{MODULE}.SpacyNamedEntityExtractor"
+
+
+@pytest.fixture
+def raw_texts() -> list:
+    return [
+        "My name is Clara and I live in Berkeley, California.",
+        "I'm Merlin, the happy pig!",
+        "New York State declared a state of emergency after the announcement of the end of the world.",
+        "",  # Intentionally empty.
+    ]
+
+
+@pytest.fixture
+def spacy_annotations() -> list:
+    return [
+        [
+            NamedEntityAnnotation(entity="PERSON", start=11, end=16),
+            NamedEntityAnnotation(entity="GPE", start=31, end=39),
+            NamedEntityAnnotation(entity="GPE", start=41, end=51),
+        ],
+        [NamedEntityAnnotation(entity="PERSON", start=4, end=10)],
+        [NamedEntityAnnotation(entity="GPE", start=0, end=14)],
+        [],
+    ]
+
+
+def test_named_entity_extractor_init():
+    extractor = SpacyNamedEntityExtractor(model="en_core_web_trf")
+    assert extractor.model_name_or_path == "en_core_web_trf"
+    assert extractor.pipeline_kwargs == {}
+    assert not extractor.initialized
+
+
+def test_init_raises_with_multiple_devices():
+    device = ComponentDevice.from_multiple(DeviceMap.from_dict({"layer1": "cpu", "layer2": "cuda:0"}))
+    with pytest.raises(ValueError, match="only supports inference on single devices"):
+        SpacyNamedEntityExtractor(model="en_core_web_trf", device=device)
+
+
+def test_named_entity_extractor_to_dict():
+    extractor = SpacyNamedEntityExtractor(
+        model="en_core_web_trf",
+        device=ComponentDevice.from_str("cuda:1"),
+    )
+
+    serde_data = extractor.to_dict()
+    assert serde_data == {
+        "type": COMPONENT_TYPE,
+        "init_parameters": {
+            "model": "en_core_web_trf",
+            "device": {"type": "single", "device": "cuda:1"},
+            "pipeline_kwargs": {},
+        },
+    }
+
+
+def test_named_entity_extractor_to_dict_with_parameters():
+    extractor = SpacyNamedEntityExtractor(
+        model="en_core_web_trf",
+        device=ComponentDevice.from_str("cuda:1"),
+        pipeline_kwargs={"n_process": 2},
+    )
+
+    serde_data = extractor.to_dict()
+    assert serde_data == {
+        "type": COMPONENT_TYPE,
+        "init_parameters": {
+            "model": "en_core_web_trf",
+            "device": {"type": "single", "device": "cuda:1"},
+            "pipeline_kwargs": {"n_process": 2},
+        },
+    }
+
+
+def test_named_entity_extractor_from_dict():
+    data = {
+        "type": COMPONENT_TYPE,
+        "init_parameters": {
+            "model": "en_core_web_trf",
+            "device": None,
+            "pipeline_kwargs": None,
+        },
+    }
+    extractor = SpacyNamedEntityExtractor.from_dict(data)
+
+    assert extractor.model_name_or_path == "en_core_web_trf"
+    assert extractor.pipeline_kwargs == {}
+
+
+def test_named_entity_extractor_from_dict_no_default_parameters():
+    data = {
+        "type": COMPONENT_TYPE,
+        "init_parameters": {"model": "en_core_web_trf"},
+    }
+    extractor = SpacyNamedEntityExtractor.from_dict(data)
+
+    assert extractor.model_name_or_path == "en_core_web_trf"
+    assert extractor.device == ComponentDevice.resolve_device(None)
+
+
+def test_named_entity_extractor_serde():
+    extractor = SpacyNamedEntityExtractor(
+        model="en_core_web_trf",
+        device=ComponentDevice.from_str("cuda:1"),
+    )
+
+    serde_data = extractor.to_dict()
+    new_extractor = SpacyNamedEntityExtractor.from_dict(serde_data)
+
+    assert new_extractor.model_name_or_path == extractor.model_name_or_path
+    assert new_extractor.device == extractor.device
+
+    with pytest.raises(DeserializationError, match=r"Couldn't deserialize"):
+        serde_data["init_parameters"].pop("model")
+        _ = SpacyNamedEntityExtractor.from_dict(serde_data)
+
+
+def test_named_entity_extractor_serde_none_device():
+    extractor = SpacyNamedEntityExtractor(model="en_core_web_trf", device=None)
+
+    serde_data = extractor.to_dict()
+    new_extractor = SpacyNamedEntityExtractor.from_dict(serde_data)
+
+    assert new_extractor.model_name_or_path == extractor.model_name_or_path
+    assert new_extractor.device == extractor.device
+
+
+# tests for SpacyNamedEntityExtractor serialization/deserialization in a pipeline
+def test_named_entity_extractor_pipeline_serde(tmp_path):
+    extractor = SpacyNamedEntityExtractor(model="en_core_web_trf")
+    p = Pipeline()
+    p.add_component(instance=extractor, name="extractor")
+
+    with open(tmp_path / "test_pipeline.yaml", "w") as f:
+        p.dump(f)
+    with open(tmp_path / "test_pipeline.yaml") as f:
+        q = Pipeline.load(f)
+
+    assert p.to_dict() == q.to_dict(), "Pipeline serialization/deserialization with SpacyNamedEntityExtractor failed."
+
+
+def test_warm_up_skips_when_already_warmed_up():
+    extractor = SpacyNamedEntityExtractor(model="en_core_web_trf")
+    extractor._warmed_up = True
+
+    with patch(f"{MODULE}.spacy.load") as mock_load:
+        extractor.warm_up()
+        mock_load.assert_not_called()
+
+
+def test_warm_up_fails_when_model_load_raises():
+    extractor = SpacyNamedEntityExtractor(model="en_core_web_trf")
+
+    with patch(f"{MODULE}.spacy") as mock_spacy:
+        mock_spacy.load.side_effect = RuntimeError("boom")
+
+        with pytest.raises(ComponentError, match="failed to initialize"):
+            extractor.warm_up()
+
+
+def test_warm_up_fails_when_model_has_no_ner_component():
+    extractor = SpacyNamedEntityExtractor(model="en_core_web_trf")
+
+    with patch(f"{MODULE}.spacy") as mock_spacy:
+        mock_spacy.load.return_value.has_pipe.return_value = False
+
+        with pytest.raises(ComponentError, match="failed to initialize"):
+            extractor.warm_up()
+
+
+def test_named_entity_extractor_run():
+    """Test the SpacyNamedEntityExtractor.run method with mocked model interaction."""
+    documents = [Document(content="My name is Clara and I live in Berkeley, California.")]
+
+    expected_annotations = [
+        [
+            NamedEntityAnnotation(entity="PERSON", start=11, end=16),
+            NamedEntityAnnotation(entity="GPE", start=31, end=39),
+            NamedEntityAnnotation(entity="GPE", start=41, end=51),
+        ]
+    ]
+
+    extractor = SpacyNamedEntityExtractor(model="en_core_web_trf")
+
+    with patch.object(extractor, "_annotate", return_value=expected_annotations) as mock_annotate:
+        extractor.pipeline = "mocked_pipeline"
+        extractor._warmed_up = True
+
+        result = extractor.run(documents=documents, batch_size=2)
+
+        mock_annotate.assert_called_once_with(["My name is Clara and I live in Berkeley, California."], batch_size=2)
+
+        assert "documents" in result
+        assert len(result["documents"]) == 1
+
+        assert isinstance(result["documents"][0], Document)
+        assert result["documents"][0].content == documents[0].content
+        assert "named_entities" in result["documents"][0].meta
+        assert result["documents"][0].meta["named_entities"] == expected_annotations[0]
+        assert "named_entities" not in documents[0].meta
+
+
+def test_named_entity_extractor_run_fails_with_wrong_number_of_annotations():
+    documents = [Document(content="My name is Clara."), Document(content="I'm Merlin, the happy pig!")]
+
+    extractor = SpacyNamedEntityExtractor(model="en_core_web_trf")
+
+    with patch.object(extractor, "_annotate", return_value=[[]]):
+        extractor._warmed_up = True
+
+        with pytest.raises(ComponentError, match="did not return the correct number of annotations"):
+            extractor.run(documents=documents)
+
+
+def test_run_triggers_warm_up_when_not_warmed_up():
+    documents = [Document(content="My name is Clara and I live in Berkeley, California.")]
+    expected_annotations = [[NamedEntityAnnotation(entity="PERSON", start=11, end=16)]]
+
+    extractor = SpacyNamedEntityExtractor(model="en_core_web_trf")
+
+    with (
+        patch.object(extractor, "warm_up") as mock_warm_up,
+        patch.object(extractor, "_annotate", return_value=expected_annotations),
+    ):
+        result = extractor.run(documents=documents)
+
+        mock_warm_up.assert_called_once()
+        assert result["documents"][0].meta["named_entities"] == expected_annotations[0]
+
+
+def test_annotate_raises_when_not_initialized():
+    extractor = SpacyNamedEntityExtractor(model="en_core_web_trf")
+
+    with pytest.raises(ComponentError, match="was not initialized"):
+        extractor._annotate(["My name is Clara."])
+
+
+def test_spacy_backend_restores_device_state():
+    """
+    Verify that SpacyNamedEntityExtractor restores the previous Thinc Ops state after the context manager exits.
+    """
+    # 1. Setup a custom state
+    custom_ops = NumpyOps()
+    custom_ops.owner = "test_marker"
+    set_current_ops(custom_ops)
+
+    try:
+        # 2. Initialize and enter the device-selection context manager
+        extractor = SpacyNamedEntityExtractor(model="en_core_web_sm")
+
+        with extractor._select_device():
+            # Inside the context, the state might change
+            pass
+
+        # 3. Verify state is restored
+        final_ops = get_current_ops()
+        assert getattr(final_ops, "owner", None) == "test_marker"
+
+    finally:
+        # Clean up global state
+        set_current_ops(NumpyOps())
+
+
+@pytest.mark.integration
+def test_ner_extractor_init():
+    extractor = SpacyNamedEntityExtractor(model="en_core_web_trf")
+    extractor.warm_up()
+    assert extractor.initialized
+
+
+@pytest.mark.integration
+@pytest.mark.parametrize("batch_size", [1, 3])
+def test_ner_extractor(raw_texts, spacy_annotations, batch_size):
+    extractor = SpacyNamedEntityExtractor(model="en_core_web_trf")
+    extractor.warm_up()
+
+    _extract_and_check_predictions(extractor, raw_texts, spacy_annotations, batch_size)
+
+
+@pytest.mark.integration
+@pytest.mark.parametrize("batch_size", [1, 3])
+def test_ner_extractor_in_pipeline(raw_texts, spacy_annotations, batch_size):
+    pipeline = Pipeline()
+    pipeline.add_component(
+        name="ner_extractor",
+        instance=SpacyNamedEntityExtractor(model="en_core_web_trf"),
+    )
+
+    outputs = pipeline.run(
+        {"ner_extractor": {"documents": [Document(content=text) for text in raw_texts], "batch_size": batch_size}}
+    )["ner_extractor"]["documents"]
+    predicted = [SpacyNamedEntityExtractor.get_stored_annotations(doc) for doc in outputs]
+    _check_predictions(predicted, spacy_annotations)
+
+
+def _extract_and_check_predictions(extractor, texts, expected, batch_size):
+    docs = [Document(content=text) for text in texts]
+    outputs = extractor.run(documents=docs, batch_size=batch_size)["documents"]
+    for original_doc, output_doc in zip(docs, outputs, strict=True):
+        # we don't modify documents in place
+        assert original_doc is not output_doc
+
+        # apart from meta, the documents should be identical
+        output_doc_dict = output_doc.to_dict(flatten=False)
+        output_doc_dict.pop("meta", None)
+        assert original_doc.to_dict() == output_doc_dict
+
+    predicted = [SpacyNamedEntityExtractor.get_stored_annotations(doc) for doc in outputs]
+
+    _check_predictions(predicted, expected)
+
+
+def _check_predictions(predicted, expected):
+    assert len(predicted) == len(expected)
+    for pred, exp in zip(predicted, expected, strict=True):
+        assert len(pred) == len(exp)
+
+        for a, b in zip(pred, exp, strict=True):
+            assert a.entity == b.entity
+            assert a.start == b.start
+            assert a.end == b.end