microsoft-sharepoint-haystack 1.0.0__tar.gz → 1.1.0__tar.gz

microsoft_sharepoint_haystack-1.1.0/CHANGELOG.md

@@ -0,0 +1,9 @@
+# Changelog
+
+## [integrations/microsoft_sharepoint-v1.0.0] - 2026-06-22
+
+### 🚀 Features
+
+- *(microsoft_sharepoint)* Add Microsoft SharePoint retriever integration (#3429)
+
+<!-- generated by git-cliff -->

{microsoft_sharepoint_haystack-1.0.0 → microsoft_sharepoint_haystack-1.1.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: microsoft-sharepoint-haystack
-Version: 1.0.0
+Version: 1.1.0
 Summary: Haystack integration for microsoft_sharepoint
 Project-URL: Documentation, https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/microsoft_sharepoint#readme
 Project-URL: Issues, https://github.com/deepset-ai/haystack-core-integrations/issues
@@ -8,7 +8,7 @@ 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: haystack,microsoft,retriever,sharepoint
+Keywords: fetcher,haystack,microsoft,retriever,sharepoint
 Classifier: Development Status :: 4 - Beta
 Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Programming Language :: Python
@@ -20,7 +20,7 @@ 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: haystack-ai>=2.17.0
 Requires-Dist: httpx>=0.28.0
 Requires-Dist: tenacity>=8.2.3
 Description-Content-Type: text/markdown
@@ -31,3 +31,14 @@ Description-Content-Type: text/markdown
 [![PyPI - Python Version](https://img.shields.io/pypi/pyversions/microsoft-sharepoint-haystack.svg)](https://pypi.org/project/microsoft-sharepoint-haystack)
 
 - [Changelog](https://github.com/deepset-ai/haystack-core-integrations/blob/main/integrations/microsoft_sharepoint/CHANGELOG.md)
+
+## Running the tests
+
+```bash
+hatch run test:unit          # offline, no credentials needed
+hatch run test:integration   # hits live Microsoft Graph (see below)
+```
+
+The integration tests (the `TestLive` classes in `tests/`) exercise the retriever and the fetcher
+against live Microsoft Graph. They **skip themselves** when their inputs are not set, so the default
+local and CI runs stay offline. To run them you need a delegated Microsoft Graph access token.

{microsoft_sharepoint_haystack-1.0.0 → microsoft_sharepoint_haystack-1.1.0}/README.md

@@ -4,3 +4,14 @@
 [![PyPI - Python Version](https://img.shields.io/pypi/pyversions/microsoft-sharepoint-haystack.svg)](https://pypi.org/project/microsoft-sharepoint-haystack)
 
 - [Changelog](https://github.com/deepset-ai/haystack-core-integrations/blob/main/integrations/microsoft_sharepoint/CHANGELOG.md)
+
+## Running the tests
+
+```bash
+hatch run test:unit          # offline, no credentials needed
+hatch run test:integration   # hits live Microsoft Graph (see below)
+```
+
+The integration tests (the `TestLive` classes in `tests/`) exercise the retriever and the fetcher
+against live Microsoft Graph. They **skip themselves** when their inputs are not set, so the default
+local and CI runs stay offline. To run them you need a delegated Microsoft Graph access token.

{microsoft_sharepoint_haystack-1.0.0 → microsoft_sharepoint_haystack-1.1.0}/pydoc/config_docusaurus.yml

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

{microsoft_sharepoint_haystack-1.0.0 → microsoft_sharepoint_haystack-1.1.0}/pyproject.toml

@@ -14,6 +14,7 @@ keywords = [
   "microsoft",
   "sharepoint",
   "retriever",
+  "fetcher",
 ]
 authors = [{ name = "deepset GmbH", email = "info@deepset.ai" }]
 classifiers = [
@@ -28,7 +29,7 @@ classifiers = [
   "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/microsoft_sharepoint#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.microsoft_sharepoint {args}"
+types = "mypy -p haystack_integrations.common.microsoft_sharepoint -p haystack_integrations.components.retrievers.microsoft_sharepoint -p haystack_integrations.components.fetchers.microsoft_sharepoint {args}"
 
 [tool.mypy]
 install_types = true

{microsoft_sharepoint_haystack-1.0.0/src/haystack_integrations/components/retrievers → microsoft_sharepoint_haystack-1.1.0/src/haystack_integrations/common}/microsoft_sharepoint/__init__.py

@@ -2,10 +2,8 @@
 #
 # SPDX-License-Identifier: Apache-2.0
 from .errors import SharePointConfigError, SharePointError, SharePointRequestError
-from .retriever import MSSharePointRetriever
 
 __all__ = [
-    "MSSharePointRetriever",
     "SharePointConfigError",
     "SharePointError",
     "SharePointRequestError",

{microsoft_sharepoint_haystack-1.0.0/src/haystack_integrations/components/retrievers → microsoft_sharepoint_haystack-1.1.0/src/haystack_integrations/common}/microsoft_sharepoint/errors.py

@@ -8,11 +8,11 @@ class SharePointError(Exception):
 
 
 class SharePointConfigError(SharePointError):
-    """Raised when the SharePoint retriever is misconfigured."""
+    """Raised when a Microsoft SharePoint component is misconfigured."""
 
 
 class SharePointRequestError(SharePointError):
-    """Raised when a Microsoft Graph search request fails."""
+    """Raised when a Microsoft Graph request fails."""
 
     def __init__(self, message: str, status_code: int | None = None) -> None:
         super().__init__(message)

microsoft_sharepoint_haystack-1.1.0/src/haystack_integrations/common/microsoft_sharepoint/utils.py

@@ -0,0 +1,107 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+
+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 SharePointConfigError, SharePointRequestError
+
+logger = logging.getLogger(__name__)
+
+DEFAULT_GRAPH_URL = "https://graph.microsoft.com/v1.0"
+_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()
+
+
+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 SharePointConfigError(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 Microsoft Graph 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 = "Microsoft Graph retries were exhausted without a recorded response."
+        raise SharePointRequestError(msg)
+    return response
+
+
+def _log_retry(retry_state: RetryCallState) -> None:
+    """Log a warning before sleeping between Microsoft Graph retries."""
+    response = _retry_response(retry_state)
+    next_action = retry_state.next_action
+    if response is None or next_action is None:
+        return
+    logger.warning(
+        "Microsoft Graph 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 Microsoft Graph 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,
+    )

microsoft_sharepoint_haystack-1.1.0/src/haystack_integrations/components/fetchers/microsoft_sharepoint/__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.microsoft_sharepoint.errors import (
+    SharePointConfigError,
+    SharePointError,
+    SharePointRequestError,
+)
+
+from .fetcher import MSSharePointFetcher
+
+__all__ = [
+    "MSSharePointFetcher",
+    "SharePointConfigError",
+    "SharePointError",
+    "SharePointRequestError",
+]