google-drive-haystack 1.0.0__tar.gz → 2.0.0__tar.gz

google_drive_haystack-2.0.0/CHANGELOG.md

@@ -0,0 +1,16 @@
+# Changelog
+
+## [integrations/google_drive-v1.1.0] - 2026-06-25
+
+### 🚀 Features
+
+- *(google_drive)* Add Google Drive fetcher (#3488)
+
+
+## [integrations/google_drive-v1.0.0] - 2026-06-23
+
+### 🚀 Features
+
+- *(google_drive)* Add integration for Google Drive retriever (#3456)
+
+<!-- generated by git-cliff -->

{google_drive_haystack-1.0.0 → google_drive_haystack-2.0.0}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.4
+Metadata-Version: 2.5
 Name: google-drive-haystack
-Version: 1.0.0
+Version: 2.0.0
 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
@@ -8,19 +8,19 @@ Project-URL: Source, https://github.com/deepset-ai/haystack-core-integrations/tr
 Author-email: deepset GmbH <info@deepset.ai>
 License-Expression: Apache-2.0
 License-File: LICENSE.txt
-Keywords: drive,google,haystack,retriever
+Keywords: drive,fetcher,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 :: 3.15
 Classifier: Programming Language :: Python :: Implementation :: CPython
 Classifier: Programming Language :: Python :: Implementation :: PyPy
-Requires-Python: >=3.10
-Requires-Dist: haystack-ai
+Requires-Python: >=3.11
+Requires-Dist: haystack-ai>=2.17.0
 Requires-Dist: httpx>=0.28.0
 Requires-Dist: tenacity>=8.2.3
 Description-Content-Type: text/markdown
@@ -30,6 +30,7 @@ Description-Content-Type: text/markdown
 [![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)
 
+- [Integration page](https://haystack.deepset.ai/integrations/google-drive)
 - [Changelog](https://github.com/deepset-ai/haystack-core-integrations/blob/main/integrations/google_drive/CHANGELOG.md)
 
 ---
@@ -37,3 +38,5 @@ Description-Content-Type: text/markdown
 ## Contributing
 
 Refer to the general [Contribution Guidelines](https://github.com/deepset-ai/haystack-core-integrations/blob/main/CONTRIBUTING.md).
+
+To run integration tests locally, you need to export the `GOOGLE_DRIVE_ACCESS_TOKEN` environment variable.

{google_drive_haystack-1.0.0 → google_drive_haystack-2.0.0}/README.md

@@ -3,6 +3,7 @@
 [![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)
 
+- [Integration page](https://haystack.deepset.ai/integrations/google-drive)
 - [Changelog](https://github.com/deepset-ai/haystack-core-integrations/blob/main/integrations/google_drive/CHANGELOG.md)
 
 ---
@@ -10,3 +11,5 @@
 ## Contributing
 
 Refer to the general [Contribution Guidelines](https://github.com/deepset-ai/haystack-core-integrations/blob/main/CONTRIBUTING.md).
+
+To run integration tests locally, you need to export the `GOOGLE_DRIVE_ACCESS_TOKEN` environment variable.

{google_drive_haystack-1.0.0 → google_drive_haystack-2.0.0}/pydoc/config_docusaurus.yml

@@ -1,6 +1,7 @@
 loaders:
   - modules:
       - haystack_integrations.components.retrievers.google_drive.retriever
+      - haystack_integrations.components.fetchers.google_drive.fetcher
     search_path: [../src]
 processors:
   - type: filter

{google_drive_haystack-1.0.0 → google_drive_haystack-2.0.0}/pyproject.toml

@@ -7,28 +7,29 @@ name = "google-drive-haystack"
 dynamic = ["version"]
 description = "Haystack integration for google_drive"
 readme = "README.md"
-requires-python = ">=3.10"
+requires-python = ">=3.11"
 license = "Apache-2.0"
 keywords = [
   "haystack",
   "google",
   "drive",
   "retriever",
+  "fetcher",
 ]
 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 :: 3.15",
   "Programming Language :: Python :: Implementation :: CPython",
   "Programming Language :: Python :: Implementation :: PyPy",
 ]
-dependencies = ["haystack-ai", "httpx>=0.28.0", "tenacity>=8.2.3"]
+dependencies = ["haystack-ai>=2.17.0", "httpx>=0.28.0", "tenacity>=8.2.3"]
 
 [project.urls]
 Documentation = "https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/google_drive#readme"
@@ -71,7 +72,7 @@ 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.retrievers.google_drive {args}"
+types = "mypy -p haystack_integrations.common.google_drive -p haystack_integrations.components.retrievers.google_drive -p haystack_integrations.components.fetchers.google_drive {args}"
 
 [tool.mypy]
 install_types = true
@@ -132,6 +133,7 @@ ignore = [
     "PLR0912",
     "PLR0913",
     "PLR0915",
+    "PLR0917",
     # Allow `Any` type - used legitimately for dynamic types and SDK boundaries
     "ANN401",
 ]

{google_drive_haystack-1.0.0/src/haystack_integrations/components/retrievers → google_drive_haystack-2.0.0/src/haystack_integrations/common}/google_drive/__init__.py

@@ -2,11 +2,9 @@
 #
 # SPDX-License-Identifier: Apache-2.0
 from .errors import GoogleDriveConfigError, GoogleDriveError, GoogleDriveRequestError
-from .retriever import GoogleDriveRetriever
 
 __all__ = [
     "GoogleDriveConfigError",
     "GoogleDriveError",
     "GoogleDriveRequestError",
-    "GoogleDriveRetriever",
 ]

{google_drive_haystack-1.0.0/src/haystack_integrations/components/retrievers → google_drive_haystack-2.0.0/src/haystack_integrations/common}/google_drive/errors.py

@@ -8,7 +8,7 @@ class GoogleDriveError(Exception):
 
 
 class GoogleDriveConfigError(GoogleDriveError):
-    """Raised when the Google Drive retriever is misconfigured."""
+    """Raised when a Google Drive component is misconfigured."""
 
 
 class GoogleDriveRequestError(GoogleDriveError):

google_drive_haystack-2.0.0/src/haystack_integrations/common/google_drive/utils.py

@@ -0,0 +1,129 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+
+import asyncio
+from typing import TypeVar
+
+import httpx
+from haystack import 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__)
+
+T = TypeVar("T")
+
+DEFAULT_API_BASE_URL = "https://www.googleapis.com/drive/v3"
+_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()
+
+
+async def _gather_tasks_with_cancel(tasks: list[asyncio.Task[T]]) -> list[T]:
+    """
+    Wait for all tasks, cancelling and draining unfinished siblings if one fails.
+
+    :param tasks: Tasks to wait for.
+    :returns:
+        The task results in input order.
+    """
+    try:
+        return await asyncio.gather(*tasks)
+    except BaseException:
+        for task in tasks:
+            task.cancel()
+        await asyncio.gather(*tasks, return_exceptions=True)
+        raise
+
+
+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 _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,
+    )
+
+
+def build_retrying(max_retries: int) -> Retrying:
+    """Build a tenacity `Retrying` that retries Google Drive API requests on throttling/transient errors."""
+    return Retrying(
+        stop=stop_after_attempt(max_retries + 1),
+        wait=_wait_with_retry_after,
+        retry=retry_if_result(_is_retryable_response),
+        before_sleep=_log_retry,
+        retry_error_callback=_last_response,
+    )
+
+
+def build_async_retrying(max_retries: int) -> AsyncRetrying:
+    """Async variant of `build_retrying`."""
+    return AsyncRetrying(
+        stop=stop_after_attempt(max_retries + 1),
+        wait=_wait_with_retry_after,
+        retry=retry_if_result(_is_retryable_response),
+        before_sleep=_log_retry,
+        retry_error_callback=_last_response,
+    )

google_drive_haystack-2.0.0/src/haystack_integrations/components/fetchers/google_drive/__init__.py

@@ -0,0 +1,17 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+from haystack_integrations.common.google_drive.errors import (
+    GoogleDriveConfigError,
+    GoogleDriveError,
+    GoogleDriveRequestError,
+)
+
+from .fetcher import GoogleDriveFetcher
+
+__all__ = [
+    "GoogleDriveConfigError",
+    "GoogleDriveError",
+    "GoogleDriveFetcher",
+    "GoogleDriveRequestError",
+]