whisper-haystack 1.0.0__py3-none-any.whl

haystack_integrations/components/audio/whisper/__init__.py

@@ -0,0 +1,8 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+
+from haystack_integrations.components.audio.whisper.whisper_local import LocalWhisperTranscriber
+from haystack_integrations.components.audio.whisper.whisper_remote import RemoteWhisperTranscriber
+
+__all__ = ["LocalWhisperTranscriber", "RemoteWhisperTranscriber"]

haystack_integrations/components/audio/whisper/whisper_local.py

@@ -0,0 +1,199 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+
+import tempfile
+from pathlib import Path
+from typing import Any, Literal, get_args
+
+from haystack import Document, component, default_from_dict, default_to_dict
+from haystack.dataclasses import ByteStream
+from haystack.lazy_imports import LazyImport
+from haystack.utils import ComponentDevice
+
+with LazyImport("Run 'pip install \"openai-whisper>=20231106\"' to install whisper.") as whisper_import:
+    import whisper
+
+WhisperLocalModel = Literal[
+    "base",
+    "base.en",
+    "large",
+    "large-v1",
+    "large-v2",
+    "large-v3",
+    "medium",
+    "medium.en",
+    "small",
+    "small.en",
+    "tiny",
+    "tiny.en",
+]
+
+
+@component
+class LocalWhisperTranscriber:
+    """
+    Transcribes audio files using OpenAI's Whisper model on your local machine.
+
+    For the supported audio formats, languages, and other parameters, see the
+    [Whisper API documentation](https://platform.openai.com/docs/guides/speech-to-text) and the official Whisper
+    [GitHub repository](https://github.com/openai/whisper).
+
+    ### Usage example
+
+    ```python
+    from haystack_integrations.components.audio.whisper import LocalWhisperTranscriber
+
+    whisper = LocalWhisperTranscriber(model="small")
+    whisper.warm_up()
+    transcription = whisper.run(sources=["path/to/audio/file"])
+    ```
+    """
+
+    def __init__(
+        self,
+        model: WhisperLocalModel = "large",
+        device: ComponentDevice | None = None,
+        whisper_params: dict[str, Any] | None = None,
+    ) -> None:
+        """
+        Creates an instance of the LocalWhisperTranscriber component.
+
+        :param model:
+            The name of the model to use. Set to one of the following models:
+            "tiny", "base", "small", "medium", "large" (default).
+            For details on the models and their modifications, see the
+            [Whisper documentation](https://github.com/openai/whisper?tab=readme-ov-file#available-models-and-languages).
+        :param device:
+            The device for loading the model. If `None`, automatically selects the default device.
+        """
+        whisper_import.check()
+        if model not in get_args(WhisperLocalModel):
+            msg = f"Model name '{model}' not recognized. Choose one among: {', '.join(get_args(WhisperLocalModel))}."
+            raise ValueError(msg)
+        self.model = model
+        self.whisper_params = whisper_params or {}
+        self.device = ComponentDevice.resolve_device(device)
+        self._model = None
+
+    def warm_up(self) -> None:
+        """
+        Loads the model in memory.
+        """
+        if not self._model:
+            self._model = whisper.load_model(self.model, device=self.device.to_torch())
+
+    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, device=self.device, whisper_params=self.whisper_params)
+
+    @classmethod
+    def from_dict(cls, data: dict[str, Any]) -> "LocalWhisperTranscriber":
+        """
+        Deserializes the component from a dictionary.
+
+        :param data:
+            The dictionary to deserialize from.
+        :returns:
+            The deserialized component.
+        """
+        return default_from_dict(cls, data)
+
+    @component.output_types(documents=list[Document])
+    def run(
+        self, sources: list[str | Path | ByteStream], whisper_params: dict[str, Any] | None = None
+    ) -> dict[str, Any]:
+        """
+        Transcribes a list of audio files into a list of documents.
+
+        :param sources:
+            A list of paths or binary streams to transcribe.
+        :param whisper_params:
+            For the supported audio formats, languages, and other parameters, see the
+            [Whisper API documentation](https://platform.openai.com/docs/guides/speech-to-text) and the official Whisper
+            [GitHup repo](https://github.com/openai/whisper).
+
+        :returns: A dictionary with the following keys:
+            - `documents`: A list of documents where each document is a transcribed audio file. The content of
+                the document is the transcription text, and the document's metadata contains the values returned by
+                the Whisper model, such as the alignment data and the path to the audio file used
+                for the transcription.
+        """
+        if self._model is None:
+            self.warm_up()
+
+        if whisper_params is None:
+            whisper_params = self.whisper_params
+
+        documents = self._transcribe(sources, **whisper_params)
+        return {"documents": documents}
+
+    def _transcribe(self, sources: list[str | Path | ByteStream], **kwargs: Any) -> list[Document]:
+        """
+        Transcribes the audio files into a list of Documents, one for each input file.
+
+        For the supported audio formats, languages, and other parameters, see the
+        [Whisper API documentation](https://platform.openai.com/docs/guides/speech-to-text) and the official Whisper
+        [github repo](https://github.com/openai/whisper).
+
+        :param sources:
+            A list of paths or binary streams to transcribe.
+        :returns:
+            A list of Documents, one for each file.
+        """
+        transcriptions = self._raw_transcribe(sources, **kwargs)
+        documents = []
+        for path, transcript in transcriptions.items():
+            content = transcript.pop("text")
+            doc = Document(content=content, meta={"audio_file": path, **transcript})
+            documents.append(doc)
+        return documents
+
+    def _get_path(self, source: str | Path | ByteStream) -> Path:
+        if isinstance(source, (Path, str)):
+            return Path(source)
+
+        potential_path = source.meta.get("file_path")
+        if potential_path is not None:
+            return Path(potential_path)
+        with tempfile.NamedTemporaryFile(delete=False) as fp:
+            path = Path(fp.name)
+            source.to_file(path)
+        return path
+
+    def _raw_transcribe(self, sources: list[str | Path | ByteStream], **kwargs: Any) -> dict[Path, Any]:
+        """
+        Transcribes the given audio files. Returns the output of the model, a dictionary, for each input file.
+
+        For the supported audio formats, languages, and other parameters, see the
+        [Whisper API documentation](https://platform.openai.com/docs/guides/speech-to-text) and the official Whisper
+        [github repo](https://github.com/openai/whisper).
+
+        :param sources:
+            A list of paths or binary streams to transcribe.
+        :returns:
+            A dictionary mapping 'file_path' to 'transcription'.
+        """
+        if self._model is None:
+            self.warm_up()
+
+        return_segments = kwargs.pop("return_segments", False)
+        transcriptions = {}
+
+        for source in sources:
+            path = self._get_path(source)
+
+            # mypy doesn't know this is set in warm_up
+            transcription = self._model.transcribe(str(path), **kwargs)  # type: ignore[attr-defined]
+
+            if not return_segments:
+                transcription.pop("segments", None)
+
+            transcriptions[path] = transcription
+
+        return transcriptions

haystack_integrations/components/audio/whisper/whisper_remote.py

@@ -0,0 +1,205 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+
+import io
+from pathlib import Path
+from typing import Any
+
+from haystack import Document, component, default_from_dict, default_to_dict, logging
+from haystack.dataclasses import ByteStream
+from haystack.utils import Secret
+from haystack.utils.http_client import init_http_client
+from openai import AsyncOpenAI, OpenAI
+
+logger = logging.getLogger(__name__)
+
+
+@component
+class RemoteWhisperTranscriber:
+    """
+    Transcribes audio files using the OpenAI's Whisper API.
+
+    The component requires an OpenAI API key, see the
+    [OpenAI documentation](https://platform.openai.com/docs/api-reference/authentication) for more details.
+    For the supported audio formats, languages, and other parameters, see the
+    [Whisper API documentation](https://platform.openai.com/docs/guides/speech-to-text).
+
+    ### Usage example
+
+    ```python
+    from haystack_integrations.components.audio.whisper import RemoteWhisperTranscriber
+
+    whisper = RemoteWhisperTranscriber(model="whisper-1")
+    transcription = whisper.run(sources=["path/to/audio/file"])
+    ```
+    """
+
+    def __init__(
+        self,
+        api_key: Secret = Secret.from_env_var("OPENAI_API_KEY"),
+        model: str = "whisper-1",
+        api_base_url: str | None = None,
+        organization: str | None = None,
+        http_client_kwargs: dict[str, Any] | None = None,
+        **kwargs: Any,
+    ) -> None:
+        """
+        Creates an instance of the RemoteWhisperTranscriber component.
+
+        :param api_key:
+            OpenAI API key.
+            You can set it with an environment variable `OPENAI_API_KEY`, or pass with this parameter
+            during initialization.
+        :param model:
+            Name of the model to use. Currently accepts only `whisper-1`.
+        :param organization:
+            Your OpenAI organization ID. See OpenAI's documentation on
+            [Setting Up Your Organization](https://platform.openai.com/docs/guides/production-best-practices/setting-up-your-organization).
+        :param api_base_url:
+            An optional URL to use as the API base. For details, see the
+            OpenAI [documentation](https://platform.openai.com/docs/api-reference/audio).
+        :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).
+        :param kwargs:
+            Other optional parameters for the model. These are sent directly to the OpenAI
+            endpoint. See OpenAI [documentation](https://platform.openai.com/docs/api-reference/audio) for more details.
+            Some of the supported parameters are:
+            - `language`: The language of the input audio.
+              Provide the input language in ISO-639-1 format
+              to improve transcription accuracy and latency.
+            - `prompt`: An optional text to guide the model's
+              style or continue a previous audio segment.
+              The prompt should match the audio language.
+            - `response_format`: The format of the transcript
+              output. This component only supports `json`.
+            - `temperature`: The sampling temperature, between 0
+            and 1. Higher values like 0.8 make the output more
+            random, while lower values like 0.2 make it more
+            focused and deterministic. If set to 0, the model
+            uses log probability to automatically increase the
+            temperature until certain thresholds are hit.
+        """
+
+        self.organization = organization
+        self.model = model
+        self.api_base_url = api_base_url
+        self.api_key = api_key
+        self.http_client_kwargs = http_client_kwargs
+
+        # Only response_format = "json" is supported
+        whisper_params = kwargs
+        response_format = whisper_params.get("response_format", "json")
+        if response_format != "json":
+            logger.warning(
+                "RemoteWhisperTranscriber only supports 'response_format: json'. This parameter will be overwritten."
+            )
+        whisper_params["response_format"] = "json"
+        self.whisper_params = whisper_params
+        self.client = OpenAI(
+            api_key=api_key.resolve_value(),
+            organization=organization,
+            base_url=api_base_url,
+            http_client=init_http_client(self.http_client_kwargs, async_client=False),
+        )
+        self.async_client = AsyncOpenAI(
+            api_key=api_key.resolve_value(),
+            organization=organization,
+            base_url=api_base_url,
+            http_client=init_http_client(self.http_client_kwargs, async_client=True),
+        )
+
+    def to_dict(self) -> dict[str, Any]:
+        """
+        Serializes the component to a dictionary.
+
+        :returns:
+            Dictionary with serialized data.
+        """
+        return default_to_dict(
+            self,
+            api_key=self.api_key,
+            model=self.model,
+            organization=self.organization,
+            api_base_url=self.api_base_url,
+            http_client_kwargs=self.http_client_kwargs,
+            **self.whisper_params,
+        )
+
+    @classmethod
+    def from_dict(cls, data: dict[str, Any]) -> "RemoteWhisperTranscriber":
+        """
+        Deserializes the component from a dictionary.
+
+        :param data:
+            The dictionary to deserialize from.
+        :returns:
+            The deserialized component.
+        """
+        return default_from_dict(cls, data)
+
+    @component.output_types(documents=list[Document])
+    def run(self, sources: list[str | Path | ByteStream]) -> dict[str, Any]:
+        """
+        Transcribes the list of audio files into a list of documents.
+
+        :param sources:
+            A list of file paths or `ByteStream` objects containing the audio files to transcribe.
+
+        :returns: A dictionary with the following keys:
+            - `documents`: A list of documents, one document for each file.
+                The content of each document is the transcribed text.
+        """
+        documents = []
+
+        for source in sources:
+            if isinstance(source, ByteStream):
+                byte_stream = source
+            else:
+                byte_stream = ByteStream.from_file_path(Path(source))
+                byte_stream.meta["file_path"] = source
+
+            file = io.BytesIO(byte_stream.data)
+            file.name = str(byte_stream.meta["file_path"]) if "file_path" in byte_stream.meta else "__fallback__.wav"
+
+            content = self.client.audio.transcriptions.create(file=file, model=self.model, **self.whisper_params)
+            doc = Document(content=content.text, meta=byte_stream.meta)
+            documents.append(doc)
+
+        return {"documents": documents}
+
+    @component.output_types(documents=list[Document])
+    async def run_async(self, sources: list[str | Path | ByteStream]) -> dict[str, Any]:
+        """
+        Asynchronously transcribes the list of audio files into a list of documents.
+
+        This is the asynchronous version of the `run` method. It has the same parameters and return values
+        but can be used with `await` in an async code.
+
+        :param sources:
+            A list of file paths or `ByteStream` objects containing the audio files to transcribe.
+
+        :returns: A dictionary with the following keys:
+            - `documents`: A list of documents, one document for each file.
+                The content of each document is the transcribed text.
+        """
+        documents = []
+
+        for source in sources:
+            if isinstance(source, ByteStream):
+                byte_stream = source
+            else:
+                byte_stream = ByteStream.from_file_path(Path(source))
+                byte_stream.meta["file_path"] = source
+
+            file = io.BytesIO(byte_stream.data)
+            file.name = str(byte_stream.meta["file_path"]) if "file_path" in byte_stream.meta else "__fallback__.wav"
+
+            content = await self.async_client.audio.transcriptions.create(
+                file=file, model=self.model, **self.whisper_params
+            )
+            doc = Document(content=content.text, meta=byte_stream.meta)
+            documents.append(doc)
+
+        return {"documents": documents}

whisper_haystack-1.0.0.dist-info/METADATA

@@ -0,0 +1,39 @@
+Metadata-Version: 2.4
+Name: whisper-haystack
+Version: 1.0.0
+Summary: Haystack integration for whisper
+Project-URL: Documentation, https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/whisper#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/whisper
+Author-email: deepset GmbH <info@deepset.ai>
+License-Expression: Apache-2.0
+License-File: LICENSE.txt
+Keywords: Haystack,OpenAI,Whisper,audio,speech-to-text,transcription
+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>=2.24.1
+Description-Content-Type: text/markdown
+
+# whisper-haystack
+
+[![PyPI - Version](https://img.shields.io/pypi/v/whisper-haystack.svg)](https://pypi.org/project/whisper-haystack)
+[![PyPI - Python Version](https://img.shields.io/pypi/pyversions/whisper-haystack.svg)](https://pypi.org/project/whisper-haystack)
+
+- [Integration page](https://haystack.deepset.ai/integrations/whisper)
+- [Changelog](https://github.com/deepset-ai/haystack-core-integrations/blob/main/integrations/whisper/CHANGELOG.md)
+
+## Contributing
+
+Refer to the general [Contribution Guidelines](https://github.com/deepset-ai/haystack-core-integrations/blob/main/CONTRIBUTING.md).
+
+To run the integration tests locally, export an `OPENAI_API_KEY` environment variable (for `RemoteWhisperTranscriber`)
+and install `openai-whisper` and `ffmpeg` (for `LocalWhisperTranscriber`).

whisper_haystack-1.0.0.dist-info/RECORD

@@ -0,0 +1,8 @@
+haystack_integrations/components/audio/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+haystack_integrations/components/audio/whisper/__init__.py,sha256=8iAHgNTTtg9xBjBuUmboTETce64bydKbRtBGDaKqXCA,374
+haystack_integrations/components/audio/whisper/whisper_local.py,sha256=2DO3gV-MeaS_weL2P6KsDQRR00tChB-AFD5q3xqGU7U,7358
+haystack_integrations/components/audio/whisper/whisper_remote.py,sha256=5MA_iqeN0UITna2g8Ph3HqnDUpgygdmx5zXZjUih2eE,8418
+whisper_haystack-1.0.0.dist-info/METADATA,sha256=lY9ncsAVz-q2XQBvmjUgHejU11EqrmzzJ60kMNOqoE0,2034
+whisper_haystack-1.0.0.dist-info/WHEEL,sha256=mffPy8wBnZQn2VnJUU5jE99KsxaSfiyMHV9Yt0aLVxs,87
+whisper_haystack-1.0.0.dist-info/licenses/LICENSE.txt,sha256=OrAtTu4aPmrTjKDSTzkSPgo_ji6NOMWO2N9JOTFyAzM,11350
+whisper_haystack-1.0.0.dist-info/RECORD,,

whisper_haystack-1.0.0.dist-info/WHEEL

@@ -0,0 +1,4 @@
+Wheel-Version: 1.0
+Generator: hatchling 1.30.1
+Root-Is-Purelib: true
+Tag: py3-none-any

whisper_haystack-1.0.0.dist-info/licenses/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.