google-drive-haystack 1.0.0__py3-none-any.whl

google_drive_haystack-1.0.0.dist-info/METADATA

@@ -0,0 +1,39 @@
+Metadata-Version: 2.4
+Name: google-drive-haystack
+Version: 1.0.0
+Summary: Haystack integration for google_drive
+Project-URL: Documentation, https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/google_drive#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/google_drive
+Author-email: deepset GmbH <info@deepset.ai>
+License-Expression: Apache-2.0
+License-File: LICENSE.txt
+Keywords: drive,google,haystack,retriever
+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
+Requires-Dist: httpx>=0.28.0
+Requires-Dist: tenacity>=8.2.3
+Description-Content-Type: text/markdown
+
+# google-drive-haystack
+
+[![PyPI - Version](https://img.shields.io/pypi/v/google-drive-haystack.svg)](https://pypi.org/project/google-drive-haystack)
+[![PyPI - Python Version](https://img.shields.io/pypi/pyversions/google-drive-haystack.svg)](https://pypi.org/project/google-drive-haystack)
+
+- [Changelog](https://github.com/deepset-ai/haystack-core-integrations/blob/main/integrations/google_drive/CHANGELOG.md)
+
+---
+
+## Contributing
+
+Refer to the general [Contribution Guidelines](https://github.com/deepset-ai/haystack-core-integrations/blob/main/CONTRIBUTING.md).

google_drive_haystack-1.0.0.dist-info/RECORD

@@ -0,0 +1,8 @@
+haystack_integrations/components/retrievers/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+haystack_integrations/components/retrievers/google_drive/__init__.py,sha256=xRiZoC0xfhhuMJCy9P8tz55E_Ou0VGOnhFnckI5rw5I,368
+haystack_integrations/components/retrievers/google_drive/errors.py,sha256=hWMYJTnuer1la1_Vw792qqypjHTm8WEujA_7Shibj1k,595
+haystack_integrations/components/retrievers/google_drive/retriever.py,sha256=8VkVcIdHc0x136GZieZx1hDDA1mGNDrcVLCiFOSS1tQ,22637
+google_drive_haystack-1.0.0.dist-info/METADATA,sha256=XDjA8N1JOcdTG13Kv7fjA55tQFubA6MvRS--Hd37iiA,1848
+google_drive_haystack-1.0.0.dist-info/WHEEL,sha256=mffPy8wBnZQn2VnJUU5jE99KsxaSfiyMHV9Yt0aLVxs,87
+google_drive_haystack-1.0.0.dist-info/licenses/LICENSE.txt,sha256=OrAtTu4aPmrTjKDSTzkSPgo_ji6NOMWO2N9JOTFyAzM,11350
+google_drive_haystack-1.0.0.dist-info/RECORD,,

google_drive_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

google_drive_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.

haystack_integrations/components/retrievers/google_drive/__init__.py

@@ -0,0 +1,12 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+from .errors import GoogleDriveConfigError, GoogleDriveError, GoogleDriveRequestError
+from .retriever import GoogleDriveRetriever
+
+__all__ = [
+    "GoogleDriveConfigError",
+    "GoogleDriveError",
+    "GoogleDriveRequestError",
+    "GoogleDriveRetriever",
+]

haystack_integrations/components/retrievers/google_drive/errors.py

@@ -0,0 +1,19 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+
+
+class GoogleDriveError(Exception):
+    """Base class for errors raised by the Google Drive integration."""
+
+
+class GoogleDriveConfigError(GoogleDriveError):
+    """Raised when the Google Drive retriever is misconfigured."""
+
+
+class GoogleDriveRequestError(GoogleDriveError):
+    """Raised when a Google Drive API request fails."""
+
+    def __init__(self, message: str, status_code: int | None = None) -> None:
+        super().__init__(message)
+        self.status_code = status_code

haystack_integrations/components/retrievers/google_drive/retriever.py

@@ -0,0 +1,499 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+
+import os
+from typing import Any
+
+import httpx
+from haystack import Document, component, default_from_dict, default_to_dict, logging
+from haystack.utils import Secret
+from tenacity import AsyncRetrying, RetryCallState, Retrying, retry_if_result, stop_after_attempt, wait_exponential
+
+from .errors import GoogleDriveConfigError, GoogleDriveRequestError
+
+logger = logging.getLogger(__name__)
+
+_DEFAULT_API_BASE_URL = "https://www.googleapis.com/drive/v3"
+# The Drive `files.list` endpoint caps a single page at 1000 results; larger `top_k` values are paginated.
+_MAX_PAGE_SIZE = 1000
+_RETRYABLE_STATUS = frozenset({429, 500, 502, 503, 504})
+# Fallback backoff when a throttled response carries no `Retry-After` header: 1s, 2s, 4s, ...
+_EXPONENTIAL_BACKOFF = wait_exponential()
+
+# The file properties requested via the Drive `fields` selection.
+_DEFAULT_FILE_FIELDS = (
+    "id",
+    "name",
+    "mimeType",
+    "webViewLink",
+    "description",
+    "fileExtension",
+    "createdTime",
+    "modifiedTime",
+    "owners(displayName)",
+    "lastModifyingUser(displayName)",
+)
+
+# The mime types that support content exporting: application/vnd.google-apps.*
+_EXPORT_MIME_TYPES = {
+    "application/vnd.google-apps.document": "text/plain",
+    "application/vnd.google-apps.spreadsheet": "text/csv",
+    "application/vnd.google-apps.presentation": "text/plain",
+}
+
+
+def _retry_response(retry_state: RetryCallState) -> httpx.Response | None:
+    """Return the `httpx.Response` recorded for a retry attempt, or `None` if the attempt raised."""
+    outcome = retry_state.outcome
+    if outcome is None or outcome.failed:
+        return None
+    return outcome.result()
+
+
+def _is_retryable_response(response: httpx.Response) -> bool:
+    """Return whether a Google Drive API response should trigger a retry."""
+    return response.status_code in _RETRYABLE_STATUS
+
+
+def _wait_with_retry_after(retry_state: RetryCallState) -> float:
+    """Wait strategy honoring a numeric `Retry-After` header, falling back to exponential backoff."""
+    response = _retry_response(retry_state)
+    if response is not None:
+        retry_after = response.headers.get("Retry-After")
+        if retry_after:
+            try:
+                return float(retry_after)
+            except ValueError:
+                pass
+
+    return _EXPONENTIAL_BACKOFF(retry_state)
+
+
+def _last_response(retry_state: RetryCallState) -> httpx.Response:
+    """Return the final response once retries are exhausted, so the caller can raise a typed error."""
+    response = _retry_response(retry_state)
+    if response is None:
+        msg = "Google Drive API retries were exhausted without a recorded response."
+        raise GoogleDriveRequestError(msg)
+    return response
+
+
+def _log_retry(retry_state: RetryCallState) -> None:
+    """Log a warning before sleeping between Google Drive API retries."""
+    response = _retry_response(retry_state)
+    next_action = retry_state.next_action
+    if response is None or next_action is None:
+        return
+    logger.warning(
+        "Google Drive API returned status {status}; retrying in {delay}s (attempt {attempt}).",
+        status=response.status_code,
+        delay=next_action.sleep,
+        attempt=retry_state.attempt_number,
+    )
+
+
+@component
+class GoogleDriveRetriever:
+    """
+    Retrieves files from Google Drive via the Drive API v3 search (`files.list`) endpoint.
+
+    Given a query, the retriever runs a full-text search over the user's Drive (and optionally shared
+    drives) and maps each matching file to a Haystack `Document`. By default, each `Document` carries
+    resource metadata (`file_name`, `file_id`, `web_url`, `mime_type`, `file_extension`, author, and
+    timestamps) and uses the file `description` or `name` as `content`, because the Drive search API does
+    not return a text snippet. Set `include_content=True` to additionally export native Google
+    Docs/Sheets/Slides to text and use that as the `Document` content. Binary files (PDF, DOCX, ...) are
+    never downloaded. Compose a downstream fetcher/converter on the returned `web_url`/`file_id` when full
+    file content is needed.
+
+    The retriever takes a per-user `access_token` as a run input, typically wired from an upstream
+    `OAuthResolver`. The token must carry a delegated Google OAuth scope that allows search
+    (for example `https://www.googleapis.com/auth/drive.readonly`). The metadata-only
+    `drive.metadata.readonly` scope cannot search file content or export documents.
+
+    ### Usage example
+    ```python
+    from haystack import Pipeline
+    from haystack.utils import Secret
+    from haystack_integrations.components.connectors.oauth import OAuthResolver
+    from haystack_integrations.utils.oauth import RefreshTokenSource
+    from haystack_integrations.components.retrievers.google_drive import GoogleDriveRetriever
+
+    pipeline = Pipeline()
+    pipeline.add_component(
+        "resolver",
+        OAuthResolver(
+            token_source=RefreshTokenSource(
+                token_url="https://oauth2.googleapis.com/token",
+                client_id="aaa-bbb-ccc",
+                refresh_token=Secret.from_env_var("GOOGLE_REFRESH_TOKEN"),
+                scopes=["https://www.googleapis.com/auth/drive.readonly"],
+            ),
+        ),
+    )
+    pipeline.add_component("retriever", GoogleDriveRetriever(top_k=5))
+    pipeline.connect("resolver.access_token", "retriever.access_token")
+
+    result = pipeline.run({"retriever": {"query": "quarterly roadmap"}})
+    documents = result["retriever"]["documents"]
+    ```
+    """
+
+    def __init__(
+        self,
+        *,
+        include_content: bool = False,
+        top_k: int = 10,
+        query_filter: str | None = None,
+        include_shared_drives: bool = False,
+        order_by: str | None = None,
+        fields: list[str] | None = None,
+        api_base_url: str = _DEFAULT_API_BASE_URL,
+        timeout: float = 30.0,
+        max_retries: int = 3,
+    ) -> None:
+        """
+        Initialize the retriever.
+
+        :param include_content: When `True`, native Google Docs/Sheets/Slides are exported to text and the
+            result becomes the `Document` content. Binary files are never downloaded. When `False` (the
+            default), `content` is the file `description` or `name` and no export request is made.
+        :param top_k: The maximum number of documents to return. Maps to the Drive `pageSize` and is
+            paginated when it exceeds a single page.
+        :param query_filter: Optional Drive query clause AND-ed with the full-text search term, for example
+            `"mimeType != 'application/vnd.google-apps.folder'"` or `"'<folderId>' in parents"`.
+        :param include_shared_drives: When `True`, the search spans shared drives as well as the user's My
+            Drive (sets `includeItemsFromAllDrives`, `supportsAllDrives`, and `corpora=allDrives`).
+        :param order_by: Optional Drive `orderBy` expression, for example `"modifiedTime desc"`.
+        :param fields: Optional list of file properties to request via the Drive `fields` selection.
+            Defaults to a standard set covering the returned metadata.
+        :param api_base_url: The Drive API base URL. Defaults to `https://www.googleapis.com/drive/v3`.
+        :param timeout: The HTTP timeout in seconds for each request to the Drive API.
+        :param max_retries: The maximum number of retries on HTTP 429 (rate limit), 500, 502, 503,
+            or 504 responses. Set to 0 to disable retries.
+        :raises GoogleDriveConfigError: If `top_k` is not positive or `max_retries` is negative.
+        """
+        if top_k <= 0:
+            msg = "top_k must be a positive integer."
+            raise GoogleDriveConfigError(msg)
+        if max_retries < 0:
+            msg = "max_retries must be zero or a positive integer."
+            raise GoogleDriveConfigError(msg)
+
+        self.include_content = include_content
+        self.top_k = top_k
+        self.query_filter = query_filter
+        self.include_shared_drives = include_shared_drives
+        self.order_by = order_by
+        self.fields = fields
+        self.api_base_url = api_base_url.rstrip("/")
+        self.timeout = timeout
+        self.max_retries = max_retries
+
+    @component.output_types(documents=list[Document])
+    def run(self, query: str, access_token: str | Secret, top_k: int | None = None) -> dict[str, list[Document]]:
+        """
+        Search Google Drive and return the matching documents.
+
+        :param query: The search query string, matched against the full text of files via
+            `fullText contains`.
+        :param access_token: A delegated Google OAuth bearer token for the user whose Drive is searched,
+            typically wired from an upstream `OAuthResolver` (which emits a plain `str`). A `Secret` is also
+            accepted and resolved internally.
+        :param top_k: Overrides the `top_k` configured at initialization for this run.
+        :returns: A dictionary with a `documents` key holding the list of retrieved `Document` objects.
+        :raises GoogleDriveConfigError: If `access_token` is a `Secret` that does not resolve to a string.
+        :raises GoogleDriveRequestError: If the Drive API returns an error response.
+        :raises httpx.HTTPError: If a network-level error occurs (for example a timeout or connection failure).
+        """
+        token = self._resolve_access_token(access_token)
+        limit = top_k or self.top_k
+        documents: list[Document] = []
+        page_token: str | None = None
+        with httpx.Client(timeout=self.timeout) as client:
+            while len(documents) < limit:
+                size = min(_MAX_PAGE_SIZE, limit - len(documents))
+                params = self._build_params(query, page_token, size)
+                payload = self._get(client, token, params)
+                files = payload.get("files") or []
+                for file in files:
+                    content = self._content_for(client, token, file)
+                    documents.append(self._file_to_document(file, content))
+                page_token = payload.get("nextPageToken")
+                if not files or not page_token:
+                    break
+
+        return {"documents": documents[:limit]}
+
+    @component.output_types(documents=list[Document])
+    async def run_async(
+        self, query: str, access_token: str | Secret, top_k: int | None = None
+    ) -> dict[str, list[Document]]:
+        """
+        Asynchronously search Google Drive and return the matching documents.
+
+        :param query: The search query string, matched against the full text of files via
+            `fullText contains`.
+        :param access_token: A delegated Google OAuth bearer token for the user whose Drive is searched,
+            typically wired from an upstream `OAuthResolver` (which emits a plain `str`). A `Secret` is also
+            accepted and resolved internally.
+        :param top_k: Overrides the `top_k` configured at initialization for this run.
+        :returns: A dictionary with a `documents` key holding the list of retrieved `Document` objects.
+        :raises GoogleDriveConfigError: If `access_token` is a `Secret` that does not resolve to a string.
+        :raises GoogleDriveRequestError: If the Drive API returns an error response.
+        :raises httpx.HTTPError: If a network-level error occurs (for example a timeout or connection failure).
+        """
+        token = self._resolve_access_token(access_token)
+        limit = top_k or self.top_k
+        documents: list[Document] = []
+        page_token: str | None = None
+        async with httpx.AsyncClient(timeout=self.timeout) as client:
+            while len(documents) < limit:
+                size = min(_MAX_PAGE_SIZE, limit - len(documents))
+                params = self._build_params(query, page_token, size)
+                payload = await self._get_async(client, token, params)
+                files = payload.get("files") or []
+                for file in files:
+                    content = await self._content_for_async(client, token, file)
+                    documents.append(self._file_to_document(file, content))
+                page_token = payload.get("nextPageToken")
+                if not files or not page_token:
+                    break
+
+        return {"documents": documents[:limit]}
+
+    @staticmethod
+    def _resolve_access_token(access_token: str | Secret) -> str:
+        """Return the bearer token string, resolving it if a `Secret` was passed."""
+        if not isinstance(access_token, Secret):
+            return access_token
+        resolved = access_token.resolve_value()
+        if not isinstance(resolved, str):
+            msg = "The access_token Secret did not resolve to a string value."
+            raise GoogleDriveConfigError(msg)
+        return resolved
+
+    def _build_params(self, query: str, page_token: str | None, size: int) -> dict[str, Any]:
+        """Build the Drive `files.list` query parameters for one page."""
+        q = f"fullText contains '{self._escape_query(query)}'"
+        if self.query_filter:
+            q = f"{q} and ({self.query_filter})"
+        fields = tuple(self.fields) if self.fields else _DEFAULT_FILE_FIELDS
+        params: dict[str, Any] = {
+            "q": q,
+            "pageSize": size,
+            "fields": f"nextPageToken, files({', '.join(fields)})",
+        }
+        if page_token:
+            params["pageToken"] = page_token
+        if self.order_by:
+            params["orderBy"] = self.order_by
+        if self.include_shared_drives:
+            params["includeItemsFromAllDrives"] = True
+            params["supportsAllDrives"] = True
+            params["corpora"] = "allDrives"
+
+        return params
+
+    @staticmethod
+    def _escape_query(query: str) -> str:
+        """Escape backslashes and single quotes so the query is safe inside a Drive `q` string literal."""
+        return query.replace("\\", "\\\\").replace("'", "\\'")
+
+    def _content_for(self, client: httpx.Client, access_token: str, file: dict[str, Any]) -> str | None:
+        """Return the exported text for a native Google file when `include_content` is set, else `None`."""
+        if not self.include_content:
+            return None
+        mime_type = file.get("mimeType")
+        file_id = file.get("id")
+        if not mime_type or not file_id:
+            return None
+        export_mime = _EXPORT_MIME_TYPES.get(mime_type)
+        if not export_mime:
+            return None
+        return self._export_content(client, access_token, file_id, export_mime)
+
+    async def _content_for_async(
+        self, client: httpx.AsyncClient, access_token: str, file: dict[str, Any]
+    ) -> str | None:
+        """Async variant of `_content_for`."""
+        if not self.include_content:
+            return None
+        mime_type = file.get("mimeType")
+        file_id = file.get("id")
+        if not mime_type or not file_id:
+            return None
+        export_mime = _EXPORT_MIME_TYPES.get(mime_type)
+        if not export_mime:
+            return None
+        return await self._export_content_async(client, access_token, file_id, export_mime)
+
+    def _export_content(self, client: httpx.Client, access_token: str, file_id: str, export_mime: str) -> str | None:
+        """Export a native Google file to text. On any failure, log a warning and return `None`."""
+        url = f"{self.api_base_url}/files/{file_id}/export"
+        headers = {"Authorization": f"Bearer {access_token}"}
+        try:
+            response = client.get(url, headers=headers, params={"mimeType": export_mime})
+        except httpx.HTTPError as error:
+            logger.warning(
+                "Could not export Google Drive file {file_id} as {export_mime}: {error}. "
+                "Falling back to metadata content.",
+                file_id=file_id,
+                export_mime=export_mime,
+                error=str(error),
+            )
+            return None
+        if response.is_error:
+            logger.warning(
+                "Could not export Google Drive file {file_id} as {export_mime} (status {status}). "
+                "Falling back to metadata content.",
+                file_id=file_id,
+                export_mime=export_mime,
+                status=response.status_code,
+            )
+            return None
+
+        return response.text
+
+    async def _export_content_async(
+        self, client: httpx.AsyncClient, access_token: str, file_id: str, export_mime: str
+    ) -> str | None:
+        """Async variant of `_export_content`."""
+        url = f"{self.api_base_url}/files/{file_id}/export"
+        headers = {"Authorization": f"Bearer {access_token}"}
+        try:
+            response = await client.get(url, headers=headers, params={"mimeType": export_mime})
+        except httpx.HTTPError as error:
+            logger.warning(
+                "Could not export Google Drive file {file_id} as {export_mime}: {error}. "
+                "Falling back to metadata content.",
+                file_id=file_id,
+                export_mime=export_mime,
+                error=str(error),
+            )
+            return None
+        if response.is_error:
+            logger.warning(
+                "Could not export Google Drive file {file_id} as {export_mime} (status {status}). "
+                "Falling back to metadata content.",
+                file_id=file_id,
+                export_mime=export_mime,
+                status=response.status_code,
+            )
+            return None
+
+        return response.text
+
+    def _get(self, client: httpx.Client, access_token: str, params: dict[str, Any]) -> dict[str, Any]:
+        """Send a `files.list` request, retrying on throttling/transient errors, and return the parsed JSON."""
+        url = f"{self.api_base_url}/files"
+        headers = {"Authorization": f"Bearer {access_token}"}
+        retrying = Retrying(
+            stop=stop_after_attempt(self.max_retries + 1),
+            wait=_wait_with_retry_after,
+            retry=retry_if_result(_is_retryable_response),
+            before_sleep=_log_retry,
+            retry_error_callback=_last_response,
+        )
+        response: httpx.Response = retrying(client.get, url, headers=headers, params=params)
+
+        return self._parse_response(response)
+
+    async def _get_async(self, client: httpx.AsyncClient, access_token: str, params: dict[str, Any]) -> dict[str, Any]:
+        """Async variant of `_get`."""
+        url = f"{self.api_base_url}/files"
+        headers = {"Authorization": f"Bearer {access_token}"}
+        retrying = AsyncRetrying(
+            stop=stop_after_attempt(self.max_retries + 1),
+            wait=_wait_with_retry_after,
+            retry=retry_if_result(_is_retryable_response),
+            before_sleep=_log_retry,
+            retry_error_callback=_last_response,
+        )
+        response: httpx.Response = await retrying(client.get, url, headers=headers, params=params)
+
+        return self._parse_response(response)
+
+    @staticmethod
+    def _parse_response(response: httpx.Response) -> dict[str, Any]:
+        """Return the parsed JSON for a successful response, or raise a descriptive error."""
+        if not response.is_error:
+            return response.json()
+
+        status = response.status_code
+        if status == httpx.codes.UNAUTHORIZED:
+            msg = (
+                "Google Drive rejected the access token (401 Unauthorized). The token may be expired, invalid, "
+                "or missing a required scope (for example https://www.googleapis.com/auth/drive.readonly). The "
+                "metadata-only drive.metadata.readonly scope cannot search file content or export documents."
+            )
+        elif status == httpx.codes.FORBIDDEN:
+            msg = f"Google Drive denied the request (403 Forbidden): {response.text}"
+        else:
+            msg = f"Google Drive API request failed with status {status}: {response.text}"
+
+        raise GoogleDriveRequestError(msg, status_code=status)
+
+    @staticmethod
+    def _display_name(identity: dict[str, Any] | None) -> str | None:
+        """Extract the display name from a Drive user object (`owners[i]` / `lastModifyingUser`), if present."""
+        if not identity:
+            return None
+        return identity.get("displayName")
+
+    @staticmethod
+    def _file_to_document(file: dict[str, Any], content: str | None = None) -> Document:
+        """Map a single Drive file resource to a Haystack Document (content + resource metadata)."""
+        name = file.get("name")
+        text = content or file.get("description") or name or ""
+
+        # Drive usually returns `fileExtension`; derive it from the name when absent (e.g. native Google docs).
+        extension = file.get("fileExtension")
+        if not extension and name:
+            extension = os.path.splitext(name)[1].lstrip(".").lower() or None
+
+        owners = file.get("owners") or []
+        created_by = GoogleDriveRetriever._display_name(owners[0]) if owners else None
+
+        meta = {
+            "file_name": name,
+            "file_id": file.get("id"),
+            "web_url": file.get("webViewLink"),
+            "mime_type": file.get("mimeType"),
+            "file_extension": extension,
+            "created_date_time": file.get("createdTime"),
+            "last_modified_date_time": file.get("modifiedTime"),
+            "created_by": created_by,
+            "last_modified_by": GoogleDriveRetriever._display_name(file.get("lastModifyingUser")),
+        }
+        return Document(content=text, meta={key: value for key, value in meta.items() if value is not None})
+
+    def to_dict(self) -> dict[str, Any]:
+        """
+        Serialize this component to a dictionary.
+
+        :returns: The serialized component as a dictionary.
+        """
+        return default_to_dict(
+            self,
+            include_content=self.include_content,
+            top_k=self.top_k,
+            query_filter=self.query_filter,
+            include_shared_drives=self.include_shared_drives,
+            order_by=self.order_by,
+            fields=self.fields,
+            api_base_url=self.api_base_url,
+            timeout=self.timeout,
+            max_retries=self.max_retries,
+        )
+
+    @classmethod
+    def from_dict(cls, data: dict[str, Any]) -> "GoogleDriveRetriever":
+        """
+        Deserialize this component from a dictionary.
+
+        :param data: The dictionary representation of this component.
+        :returns: The deserialized component instance.
+        """
+        return default_from_dict(cls, data)