Merge branch 'dev' into feature-remote-ocr-2

[ci skip]

docs/administration.md

@@ -179,14 +179,10 @@ following:
 
 ### Database Upgrades
 
-In general, Paperless-ngx supports current version of PostgreSQL and MariaDB and it is generally
+In general, paperless does not require a specific version of PostgreSQL or MariaDB and it is
 safe to update them to newer versions. However, you should always take a backup and follow
 the instructions from your database's documentation for how to upgrade between major versions.
 
-!!! note
-
-    As of Paperless-ngx v2.18, the minimum supported version of PostgreSQL is 13.
-
 For PostgreSQL, refer to [Upgrading a PostgreSQL Cluster](https://www.postgresql.org/docs/current/upgrading.html).
 
 For MariaDB, refer to [Upgrading MariaDB](https://mariadb.com/kb/en/upgrading/)

docs/configuration.md

@@ -1776,3 +1776,23 @@ password. All of these options come from their similarly-named [Django settings]
 #### [`PAPERLESS_EMAIL_USE_SSL=<bool>`](#PAPERLESS_EMAIL_USE_SSL) {#PAPERLESS_EMAIL_USE_SSL}
 
 : Defaults to false.
+
+## Remote OCR
+
+#### [`PAPERLESS_REMOTE_OCR_ENGINE=<str>`](#PAPERLESS_REMOTE_OCR_ENGINE) {#PAPERLESS_REMOTE_OCR_ENGINE}
+
+: The remote OCR engine to use. Currently only Azure AI is supported as "azureai".
+
+    Defaults to None, which disables remote OCR.
+
+#### [`PAPERLESS_REMOTE_OCR_API_KEY=<str>`](#PAPERLESS_REMOTE_OCR_API_KEY) {#PAPERLESS_REMOTE_OCR_API_KEY}
+
+: The API key to use for the remote OCR engine.
+
+    Defaults to None.
+
+#### [`PAPERLESS_REMOTE_OCR_ENDPOINT=<str>`](#PAPERLESS_REMOTE_OCR_ENDPOINT) {#PAPERLESS_REMOTE_OCR_ENDPOINT}
+
+: The endpoint to use for the remote OCR engine. This is required for Azure AI.
+
+    Defaults to None.

docs/index.md

@@ -25,9 +25,10 @@ physical documents into a searchable online archive so you can keep, well, _less
 ## Features
 
 -   **Organize and index** your scanned documents with tags, correspondents, types, and more.
--   _Your_ data is stored locally on _your_ server and is never transmitted or shared in any way.
+-   _Your_ data is stored locally on _your_ server and is never transmitted or shared in any way, unless you explicitly choose to do so.
 -   Performs **OCR** on your documents, adding searchable and selectable text, even to documents scanned with only images.
--   Utilizes the open-source Tesseract engine to recognize more than 100 languages.
+    -   Utilizes the open-source Tesseract engine to recognize more than 100 languages.
+    -   _New!_ Supports remote OCR with Azure AI (opt-in).
 -   Documents are saved as PDF/A format which is designed for long term storage, alongside the unaltered originals.
 -   Uses machine-learning to automatically add tags, correspondents and document types to your documents.
 -   Supports PDF documents, images, plain text files, Office documents (Word, Excel, PowerPoint, and LibreOffice equivalents)[^1] and more.

docs/usage.md

@@ -844,6 +844,18 @@ how regularly you intend to scan documents and use paperless.
     performed the task associated with the document, move it to the
     inbox.
 
+## Remote OCR
+
+!!! important
+
+    This feature is disabled by default and will always remain strictly "opt-in".
+
+Paperless-ngx supports performing OCR on documents using remote services. At the moment, this is limited to
+[Microsoft's Azure "Document Intelligence" service](https://azure.microsoft.com/en-us/products/ai-services/ai-document-intelligence).
+This is of course a paid service (with a free tier) which requires an Azure account and subscription. Azure AI is not affiliated with
+Paperless-ngx in any way. When enabled, Paperless-ngx will automatically send appropriate documents to Azure for OCR processing, bypassing
+the local OCR engine. See the [configuration](configuration.md#PAPERLESS_REMOTE_OCR_ENGINE) options for more details.
+
 ## Architecture
 
 Paperless-ngx consists of the following components:

pyproject.toml

@@ -15,6 +15,7 @@ classifiers = [
 # This will allow testing to not install a webserver, mysql, etc
 
 dependencies = [
+  "azure-ai-documentintelligence>=1.0.2",
   "bleach~=6.2.0",
   "celery[redis]~=5.5.1",
   "channels~=4.2",
@@ -23,22 +24,22 @@ dependencies = [
   "dateparser~=1.2",
   # WARNING: django does not use semver.
   #          Only patch versions are guaranteed to not introduce breaking changes.
-  "django~=5.2.5",
+  "django~=5.1.7",
   "django-allauth[socialaccount,mfa]~=65.4.0",
-  "django-auditlog~=3.2.1",
+  "django-auditlog~=3.1.2",
   "django-cachalot~=2.8.0",
   "django-celery-results~=2.6.0",
   "django-compression-middleware~=0.5.0",
   "django-cors-headers~=4.7.0",
   "django-extensions~=4.1",
   "django-filter~=25.1",
-  "django-guardian~=3.0.3",
-  "django-multiselectfield~=1.0.1",
+  "django-guardian~=2.4.0",
+  "django-multiselectfield~=0.1.13",
   "django-soft-delete~=1.0.18",
   "djangorestframework~=3.15",
-  "djangorestframework-guardian~=0.4.0",
+  "djangorestframework-guardian~=0.3.0",
   "drf-spectacular~=0.28",
-  "drf-spectacular-sidecar~=2025.8.1",
+  "drf-spectacular-sidecar~=2025.4.1",
   "drf-writable-nested~=0.7.1",
   "filelock~=3.18.0",
   "flower~=2.0.1",
@@ -103,7 +104,7 @@ testing = [
   "imagehash",
   "pytest~=8.4.1",
   "pytest-cov~=6.2.1",
-  "pytest-django~=4.11.1",
+  "pytest-django~=4.10.0",
   "pytest-env",
   "pytest-httpx",
   "pytest-mock",
@@ -233,6 +234,7 @@ testpaths = [
   "src/paperless_tesseract/tests/",
   "src/paperless_tika/tests",
   "src/paperless_text/tests/",
+  "src/paperless_remote/tests/",
 ]
 addopts = [
   "--pythonwarnings=all",

src/documents/management/commands/document_fuzzy_match.py

@@ -125,14 +125,14 @@ class Command(MultiProcessMixin, ProgressBarMixin, BaseCommand):
                 messages.append(
                     self.style.NOTICE(
                         f"Document {result.doc_one_pk} fuzzy match"
-                        f" to {result.doc_two_pk} (confidence {result.ratio:.3f})\n",
+                        f" to {result.doc_two_pk} (confidence {result.ratio:.3f})",
                     ),
                 )
                 maybe_delete_ids.append(result.doc_two_pk)
 
         if len(messages) == 0:
             messages.append(
-                self.style.SUCCESS("No matches found\n"),
+                self.style.SUCCESS("No matches found"),
             )
         self.stdout.writelines(
             messages,

src/documents/serialisers.py

@@ -2038,24 +2038,6 @@ class WorkflowTriggerSerializer(serializers.ModelSerializer):
 
         return attrs
 
-    @staticmethod
-    def normalize_workflow_trigger_sources(trigger):
-        """
-        Convert sources to strings to handle django-multiselectfield v1.0 changes
-        """
-        if trigger and "sources" in trigger:
-            trigger["sources"] = [
-                str(s.value if hasattr(s, "value") else s) for s in trigger["sources"]
-            ]
-
-    def create(self, validated_data):
-        WorkflowTriggerSerializer.normalize_workflow_trigger_sources(validated_data)
-        return super().create(validated_data)
-
-    def update(self, instance, validated_data):
-        WorkflowTriggerSerializer.normalize_workflow_trigger_sources(validated_data)
-        return super().update(instance, validated_data)
-
 
 class WorkflowActionEmailSerializer(serializers.ModelSerializer):
     id = serializers.IntegerField(allow_null=True, required=False)
@@ -2220,8 +2202,6 @@ class WorkflowSerializer(serializers.ModelSerializer):
         if triggers is not None and triggers is not serializers.empty:
             for trigger in triggers:
                 filter_has_tags = trigger.pop("filter_has_tags", None)
-                # Convert sources to strings to handle django-multiselectfield v1.0 changes
-                WorkflowTriggerSerializer.normalize_workflow_trigger_sources(trigger)
                 trigger_instance, _ = WorkflowTrigger.objects.update_or_create(
                     id=trigger.get("id"),
                     defaults=trigger,

src/documents/tests/test_management_exporter.py

@@ -123,7 +123,7 @@ class TestExportImport(
 
         self.trigger = WorkflowTrigger.objects.create(
             type=WorkflowTrigger.WorkflowTriggerType.CONSUMPTION,
-            sources=[str(WorkflowTrigger.DocumentSourceChoices.CONSUME_FOLDER.value)],
+            sources=[1],
             filter_filename="*",
         )
         self.action = WorkflowAction.objects.create(assign_title="new title")

src/documents/tests/test_management_fuzzy.py

@@ -87,7 +87,7 @@ class TestFuzzyMatchCommand(TestCase):
             filename="other_test.pdf",
         )
         stdout, _ = self.call_command()
-        self.assertIn("No matches found", stdout)
+        self.assertEqual(stdout, "No matches found\n")
 
     def test_with_matches(self):
         """
@@ -116,7 +116,7 @@ class TestFuzzyMatchCommand(TestCase):
             filename="other_test.pdf",
         )
         stdout, _ = self.call_command("--processes", "1")
-        self.assertRegex(stdout, self.MSG_REGEX)
+        self.assertRegex(stdout, self.MSG_REGEX + "\n")
 
     def test_with_3_matches(self):
         """
@@ -152,10 +152,11 @@ class TestFuzzyMatchCommand(TestCase):
             filename="final_test.pdf",
         )
         stdout, _ = self.call_command()
-        lines = [x.strip() for x in stdout.splitlines() if x.strip()]
+        lines = [x.strip() for x in stdout.split("\n") if len(x.strip())]
         self.assertEqual(len(lines), 3)
-        for line in lines:
-            self.assertRegex(line, self.MSG_REGEX)
+        self.assertRegex(lines[0], self.MSG_REGEX)
+        self.assertRegex(lines[1], self.MSG_REGEX)
+        self.assertRegex(lines[2], self.MSG_REGEX)
 
     def test_document_deletion(self):
         """
@@ -196,12 +197,14 @@ class TestFuzzyMatchCommand(TestCase):
 
         stdout, _ = self.call_command("--delete")
 
-        self.assertIn(
+        lines = [x.strip() for x in stdout.split("\n") if len(x.strip())]
+        self.assertEqual(len(lines), 3)
+        self.assertEqual(
+            lines[0],
             "The command is configured to delete documents.  Use with caution",
-            stdout,
         )
-        self.assertRegex(stdout, self.MSG_REGEX)
-        self.assertIn("Deleting 1 documents based on ratio matches", stdout)
+        self.assertRegex(lines[1], self.MSG_REGEX)
+        self.assertEqual(lines[2], "Deleting 1 documents based on ratio matches")
 
         self.assertEqual(Document.objects.count(), 2)
         self.assertIsNotNone(Document.objects.get(pk=1))

src/documents/tests/test_migration_workflows.py

@@ -104,7 +104,7 @@ class TestReverseMigrateWorkflow(TestMigrations):
 
         trigger = WorkflowTrigger.objects.create(
             type=0,
-            sources=[str(DocumentSource.ConsumeFolder)],
+            sources=[DocumentSource.ConsumeFolder],
             filter_path="*/path/*",
             filter_filename="*file*",
         )

src/paperless/auth.py

@@ -54,7 +54,7 @@ class HttpRemoteUserMiddleware(PersistentRemoteUserMiddleware):
 
     header = settings.HTTP_REMOTE_USER_HEADER_NAME
 
-    def __call__(self, request: HttpRequest) -> None:
+    def process_request(self, request: HttpRequest) -> None:
         # If remote user auth is enabled only for the frontend, not the API,
         # then we need dont want to authenticate the user for API requests.
         if (
@@ -62,8 +62,8 @@ class HttpRemoteUserMiddleware(PersistentRemoteUserMiddleware):
             and "paperless.auth.PaperlessRemoteUserAuthentication"
             not in settings.REST_FRAMEWORK["DEFAULT_AUTHENTICATION_CLASSES"]
         ):
-            return self.get_response(request)
-        return super().__call__(request)
+            return
+        return super().process_request(request)
 
 
 class PaperlessRemoteUserAuthentication(authentication.RemoteUserAuthentication):

src/paperless/checks.py

@@ -214,3 +214,31 @@ def audit_log_check(app_configs, **kwargs):
         )
 
     return result
+
+
+@register()
+def check_postgres_version(app_configs, **kwargs):
+    """
+    Django 5.2 removed PostgreSQL 13 support and thus it will be removed in
+    a future Paperless-ngx version. This check can be removed eventually.
+    See https://docs.djangoproject.com/en/5.2/releases/5.2/#dropped-support-for-postgresql-13
+    """
+    db_conn = connections["default"]
+    result = []
+    if db_conn.vendor == "postgresql":
+        try:
+            with db_conn.cursor() as cursor:
+                cursor.execute("SHOW server_version;")
+                version = cursor.fetchone()[0]
+                if version.startswith("13"):
+                    return [
+                        Warning(
+                            "PostgreSQL 13 is deprecated and will not be supported in a future Paperless-ngx release.",
+                            hint="Upgrade to PostgreSQL 14 or newer.",
+                        ),
+                    ]
+        except Exception:  # pragma: no cover
+            # Don't block checks on version query failure
+            pass
+
+    return result

src/paperless/settings.py

@@ -324,6 +324,7 @@ INSTALLED_APPS = [
     "paperless_tesseract.apps.PaperlessTesseractConfig",
     "paperless_text.apps.PaperlessTextConfig",
     "paperless_mail.apps.PaperlessMailConfig",
+    "paperless_remote.apps.PaperlessRemoteParserConfig",
     "django.contrib.admin",
     "rest_framework",
     "rest_framework.authtoken",
@@ -1421,3 +1422,11 @@ OUTLOOK_OAUTH_ENABLED = bool(
     and OUTLOOK_OAUTH_CLIENT_ID
     and OUTLOOK_OAUTH_CLIENT_SECRET,
 )
+
+###############################################################################
+# Remote Parser                                                               #
+###############################################################################
+
+REMOTE_OCR_ENGINE = os.getenv("PAPERLESS_REMOTE_OCR_ENGINE")
+REMOTE_OCR_API_KEY = os.getenv("PAPERLESS_REMOTE_OCR_API_KEY")
+REMOTE_OCR_ENDPOINT = os.getenv("PAPERLESS_REMOTE_OCR_ENDPOINT")

src/paperless/tests/test_checks.py

@@ -9,6 +9,7 @@ from documents.tests.utils import DirectoriesMixin
 from documents.tests.utils import FileSystemAssertsMixin
 from paperless.checks import audit_log_check
 from paperless.checks import binaries_check
+from paperless.checks import check_postgres_version
 from paperless.checks import debug_mode_check
 from paperless.checks import paths_check
 from paperless.checks import settings_values_check
@@ -262,3 +263,39 @@ class TestAuditLogChecks(TestCase):
                     ("auditlog table was found but audit log is disabled."),
                     msg.msg,
                 )
+
+
+class TestPostgresVersionCheck(TestCase):
+    @mock.patch("paperless.checks.connections")
+    def test_postgres_13_warns(self, mock_connections):
+        mock_connection = mock.MagicMock()
+        mock_connection.vendor = "postgresql"
+        mock_cursor = mock.MagicMock()
+        mock_cursor.__enter__.return_value.fetchone.return_value = ["13.11"]
+        mock_connection.cursor.return_value = mock_cursor
+        mock_connections.__getitem__.return_value = mock_connection
+
+        warnings = check_postgres_version(None)
+        self.assertEqual(len(warnings), 1)
+        self.assertIn("PostgreSQL 13 is deprecated", warnings[0].msg)
+
+    @mock.patch("paperless.checks.connections")
+    def test_postgres_14_passes(self, mock_connections):
+        mock_connection = mock.MagicMock()
+        mock_connection.vendor = "postgresql"
+        mock_cursor = mock.MagicMock()
+        mock_cursor.__enter__.return_value.fetchone.return_value = ["14.10"]
+        mock_connection.cursor.return_value = mock_cursor
+        mock_connections.__getitem__.return_value = mock_connection
+
+        warnings = check_postgres_version(None)
+        self.assertEqual(warnings, [])
+
+    @mock.patch("paperless.checks.connections")
+    def test_non_postgres_skipped(self, mock_connections):
+        mock_connection = mock.MagicMock()
+        mock_connection.vendor = "sqlite"
+        mock_connections.__getitem__.return_value = mock_connection
+
+        warnings = check_postgres_version(None)
+        self.assertEqual(warnings, [])

src/paperless/tests/test_remote_user.py

@@ -1,7 +1,6 @@
 import os
 from unittest import mock
 
-from django.conf import settings
 from django.contrib.auth.models import User
 from django.test import override_settings
 from rest_framework import status
@@ -92,7 +91,6 @@ class TestRemoteUser(DirectoriesMixin, APITestCase):
 
     @override_settings(
         REST_FRAMEWORK={
-            **settings.REST_FRAMEWORK,
             "DEFAULT_AUTHENTICATION_CLASSES": [
                 "rest_framework.authentication.BasicAuthentication",
                 "rest_framework.authentication.TokenAuthentication",

src/paperless_remote/__init__.py

@@ -0,0 +1,4 @@
+# this is here so that django finds the checks.
+from paperless_remote.checks import check_remote_parser_configured
+
+__all__ = ["check_remote_parser_configured"]

src/paperless_remote/apps.py

@@ -0,0 +1,14 @@
+from django.apps import AppConfig
+
+from paperless_remote.signals import remote_consumer_declaration
+
+
+class PaperlessRemoteParserConfig(AppConfig):
+    name = "paperless_remote"
+
+    def ready(self):
+        from documents.signals import document_consumer_declaration
+
+        document_consumer_declaration.connect(remote_consumer_declaration)
+
+        AppConfig.ready(self)

src/paperless_remote/checks.py

@@ -0,0 +1,15 @@
+from django.conf import settings
+from django.core.checks import Error
+from django.core.checks import register
+
+
+@register()
+def check_remote_parser_configured(app_configs, **kwargs):
+    if settings.REMOTE_OCR_ENGINE == "azureai" and not settings.REMOTE_OCR_ENDPOINT:
+        return [
+            Error(
+                "Azure AI remote parser requires endpoint to be configured.",
+            ),
+        ]
+
+    return []

src/paperless_remote/parsers.py

@@ -0,0 +1,113 @@
+from pathlib import Path
+
+from django.conf import settings
+
+from paperless_tesseract.parsers import RasterisedDocumentParser
+
+
+class RemoteEngineConfig:
+    def __init__(
+        self,
+        engine: str,
+        api_key: str | None = None,
+        endpoint: str | None = None,
+    ):
+        self.engine = engine
+        self.api_key = api_key
+        self.endpoint = endpoint
+
+    def engine_is_valid(self):
+        valid = self.engine in ["azureai"] and self.api_key is not None
+        if self.engine == "azureai":
+            valid = valid and self.endpoint is not None
+        return valid
+
+
+class RemoteDocumentParser(RasterisedDocumentParser):
+    """
+    This parser uses a remote OCR engine to parse documents. Currently, it supports Azure AI Vision
+    as this is the only service that provides a remote OCR API with text-embedded PDF output.
+    """
+
+    logging_name = "paperless.parsing.remote"
+
+    def get_settings(self) -> RemoteEngineConfig:
+        """
+        Returns the configuration for the remote OCR engine, loaded from Django settings.
+        """
+        return RemoteEngineConfig(
+            engine=settings.REMOTE_OCR_ENGINE,
+            api_key=settings.REMOTE_OCR_API_KEY,
+            endpoint=settings.REMOTE_OCR_ENDPOINT,
+        )
+
+    def supported_mime_types(self):
+        if self.settings.engine_is_valid():
+            return [
+                "application/pdf",
+                "image/png",
+                "image/jpeg",
+                "image/tiff",
+                "image/bmp",
+                "image/gif",
+                "image/webp",
+            ]
+        else:
+            return []
+
+    def azure_ai_vision_parse(
+        self,
+        file: Path,
+    ) -> str | None:
+        """
+        Uses Azure AI Vision to parse the document and return the text content.
+        It requests a searchable PDF output with embedded text.
+        The PDF is saved to the archive_path attribute.
+        Returns the text content extracted from the document.
+        If the parsing fails, it returns None.
+        """
+        from azure.ai.documentintelligence import DocumentIntelligenceClient
+        from azure.ai.documentintelligence.models import AnalyzeDocumentRequest
+        from azure.ai.documentintelligence.models import AnalyzeOutputOption
+        from azure.ai.documentintelligence.models import DocumentContentFormat
+        from azure.core.credentials import AzureKeyCredential
+
+        client = DocumentIntelligenceClient(
+            endpoint=self.settings.endpoint,
+            credential=AzureKeyCredential(self.settings.api_key),
+        )
+
+        with file.open("rb") as f:
+            analyze_request = AnalyzeDocumentRequest(bytes_source=f.read())
+            poller = client.begin_analyze_document(
+                model_id="prebuilt-read",
+                body=analyze_request,
+                output_content_format=DocumentContentFormat.TEXT,
+                output=[AnalyzeOutputOption.PDF],  # request searchable PDF output
+                content_type="application/json",
+            )
+
+        poller.wait()
+        result_id = poller.details["operation_id"]
+        result = poller.result()
+
+        # Download the PDF with embedded text
+        self.archive_path = Path(self.tempdir) / "archive.pdf"
+        with self.archive_path.open("wb") as f:
+            for chunk in client.get_analyze_result_pdf(
+                model_id="prebuilt-read",
+                result_id=result_id,
+            ):
+                f.write(chunk)
+
+        return result.content
+
+    def parse(self, document_path: Path, mime_type, file_name=None):
+        if not self.settings.engine_is_valid():
+            self.log.warning(
+                "No valid remote parser engine is configured, content will be empty.",
+            )
+            self.text = ""
+            return
+        elif self.settings.engine == "azureai":
+            self.text = self.azure_ai_vision_parse(document_path)

src/paperless_remote/signals.py

@@ -0,0 +1,18 @@
+def get_parser(*args, **kwargs):
+    from paperless_remote.parsers import RemoteDocumentParser
+
+    return RemoteDocumentParser(*args, **kwargs)
+
+
+def get_supported_mime_types():
+    from paperless_remote.parsers import RemoteDocumentParser
+
+    return RemoteDocumentParser(None).supported_mime_types()
+
+
+def remote_consumer_declaration(sender, **kwargs):
+    return {
+        "parser": get_parser,
+        "weight": 5,
+        "mime_types": get_supported_mime_types(),
+    }

src/paperless_remote/tests/test_checks.py

@@ -0,0 +1,29 @@
+from django.test import TestCase
+from django.test import override_settings
+
+from paperless_remote import check_remote_parser_configured
+
+
+class TestChecks(TestCase):
+    @override_settings(REMOTE_OCR_ENGINE=None)
+    def test_no_engine(self):
+        msgs = check_remote_parser_configured(None)
+        self.assertEqual(len(msgs), 0)
+
+    @override_settings(REMOTE_OCR_ENGINE="azureai")
+    @override_settings(REMOTE_OCR_API_KEY="somekey")
+    @override_settings(REMOTE_OCR_ENDPOINT=None)
+    def test_azure_no_endpoint(self):
+        msgs = check_remote_parser_configured(None)
+        self.assertEqual(len(msgs), 1)
+        self.assertTrue(
+            msgs[0].msg.startswith(
+                "Azure AI remote parser requires endpoint to be configured.",
+            ),
+        )
+
+    @override_settings(REMOTE_OCR_ENGINE="something")
+    @override_settings(REMOTE_OCR_API_KEY="somekey")
+    def test_valid_configuration(self):
+        msgs = check_remote_parser_configured(None)
+        self.assertEqual(len(msgs), 0)

src/paperless_remote/tests/test_parser.py

@@ -0,0 +1,101 @@
+import uuid
+from pathlib import Path
+from unittest import mock
+
+from django.test import TestCase
+from django.test import override_settings
+
+from documents.tests.utils import DirectoriesMixin
+from documents.tests.utils import FileSystemAssertsMixin
+from paperless_remote.parsers import RemoteDocumentParser
+from paperless_remote.signals import get_parser
+
+
+class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
+    SAMPLE_FILES = Path(__file__).resolve().parent / "samples"
+
+    def assertContainsStrings(self, content, strings):
+        # Asserts that all strings appear in content, in the given order.
+        indices = []
+        for s in strings:
+            if s in content:
+                indices.append(content.index(s))
+            else:
+                self.fail(f"'{s}' is not in '{content}'")
+        self.assertListEqual(indices, sorted(indices))
+
+    @mock.patch("paperless_tesseract.parsers.run_subprocess")
+    @mock.patch("azure.ai.documentintelligence.DocumentIntelligenceClient")
+    def test_get_text_with_azure(self, mock_client_cls, mock_subprocess):
+        # Arrange mock Azure client
+        mock_client = mock.Mock()
+        mock_client_cls.return_value = mock_client
+
+        # Simulate poller result and its `.details`
+        mock_poller = mock.Mock()
+        mock_poller.wait.return_value = None
+        mock_poller.details = {"operation_id": "fake-op-id"}
+        mock_client.begin_analyze_document.return_value = mock_poller
+        mock_poller.result.return_value.content = "This is a test document."
+
+        # Return dummy PDF bytes
+        mock_client.get_analyze_result_pdf.return_value = [
+            b"%PDF-",
+            b"1.7 ",
+            b"FAKEPDF",
+        ]
+
+        # Simulate pdftotext by writing dummy text to sidecar file
+        def fake_run(cmd, *args, **kwargs):
+            with Path(cmd[-1]).open("w", encoding="utf-8") as f:
+                f.write("This is a test document.")
+
+        mock_subprocess.side_effect = fake_run
+
+        with override_settings(
+            REMOTE_OCR_ENGINE="azureai",
+            REMOTE_OCR_API_KEY="somekey",
+            REMOTE_OCR_ENDPOINT="https://endpoint.cognitiveservices.azure.com",
+        ):
+            parser = get_parser(uuid.uuid4())
+            parser.parse(
+                self.SAMPLE_FILES / "simple-digital.pdf",
+                "application/pdf",
+            )
+
+            self.assertContainsStrings(
+                parser.text.strip(),
+                ["This is a test document."],
+            )
+
+    @override_settings(
+        REMOTE_OCR_ENGINE="azureai",
+        REMOTE_OCR_API_KEY="key",
+        REMOTE_OCR_ENDPOINT="https://endpoint.cognitiveservices.azure.com",
+    )
+    def test_supported_mime_types_valid_config(self):
+        parser = RemoteDocumentParser(uuid.uuid4())
+        expected_types = [
+            "application/pdf",
+            "image/png",
+            "image/jpeg",
+            "image/tiff",
+            "image/bmp",
+            "image/gif",
+            "image/webp",
+        ]
+        self.assertEqual(parser.supported_mime_types(), expected_types)
+
+    def test_supported_mime_types_invalid_config(self):
+        parser = get_parser(uuid.uuid4())
+        self.assertEqual(parser.supported_mime_types(), [])
+
+    @override_settings(
+        REMOTE_OCR_ENGINE=None,
+        REMOTE_OCR_API_KEY=None,
+        REMOTE_OCR_ENDPOINT=None,
+    )
+    def test_parse_with_invalid_config(self):
+        parser = get_parser(uuid.uuid4())
+        parser.parse(self.SAMPLE_FILES / "simple-digital.pdf", "application/pdf")
+        self.assertEqual(parser.text, "")

uv.lock

@@ -93,6 +93,34 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/af/cc/55a32a2c98022d88812b5986d2a92c4ff3ee087e83b712ebc703bba452bf/Automat-24.8.1-py3-none-any.whl", hash = "sha256:bf029a7bc3da1e2c24da2343e7598affaa9f10bf0ab63ff808566ce90551e02a", size = 42585, upload-time = "2024-08-19T17:31:56.729Z" },
 ]
 
+[[package]]
+name = "azure-ai-documentintelligence"
+version = "1.0.2"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "azure-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+    { name = "isodate", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+    { name = "typing-extensions", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/44/7b/8115cd713e2caa5e44def85f2b7ebd02a74ae74d7113ba20bdd41fd6dd80/azure_ai_documentintelligence-1.0.2.tar.gz", hash = "sha256:4d75a2513f2839365ebabc0e0e1772f5601b3a8c9a71e75da12440da13b63484", size = 170940 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/d9/75/c9ec040f23082f54ffb1977ff8f364c2d21c79a640a13d1c1809e7fd6b1a/azure_ai_documentintelligence-1.0.2-py3-none-any.whl", hash = "sha256:e1fb446abbdeccc9759d897898a0fe13141ed29f9ad11fc705f951925822ed59", size = 106005 },
+]
+
+[[package]]
+name = "azure-core"
+version = "1.33.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "requests", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+    { name = "six", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+    { name = "typing-extensions", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/75/aa/7c9db8edd626f1a7d99d09ef7926f6f4fb34d5f9fa00dc394afdfe8e2a80/azure_core-1.33.0.tar.gz", hash = "sha256:f367aa07b5e3005fec2c1e184b882b0b039910733907d001c20fb08ebb8c0eb9", size = 295633 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/07/b7/76b7e144aa53bd206bf1ce34fa75350472c3f69bf30e5c8c18bc9881035d/azure_core-1.33.0-py3-none-any.whl", hash = "sha256:9b5b6d0223a1d38c37500e6971118c1e0f13f54951e6893968b38910bc9cda8f", size = 207071 },
+]
+
 [[package]]
 name = "babel"
 version = "2.17.0"
@@ -626,15 +654,15 @@ wheels = [
 
 [[package]]
 name = "django"
-version = "5.2.5"
+version = "5.1.8"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "asgiref", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "sqlparse", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/62/9b/779f853c3d2d58b9e08346061ff3e331cdec3fe3f53aae509e256412a593/django-5.2.5.tar.gz", hash = "sha256:0745b25681b129a77aae3d4f6549b62d3913d74407831abaa0d9021a03954bae", size = 10859748, upload-time = "2025-08-06T08:26:29.978Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/00/40/45adc1b93435d1b418654a734b68351bb6ce0a0e5e37b2f0e9aeb1a2e233/Django-5.1.8.tar.gz", hash = "sha256:42e92a1dd2810072bcc40a39a212b693f94406d0ba0749e68eb642f31dc770b4", size = 10723602, upload-time = "2025-04-02T11:19:56.028Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/9d/6e/98a1d23648e0085bb5825326af17612ecd8fc76be0ce96ea4dc35e17b926/django-5.2.5-py3-none-any.whl", hash = "sha256:2b2ada0ee8a5ff743a40e2b9820d1f8e24c11bac9ae6469cd548f0057ea6ddcd", size = 8302999, upload-time = "2025-08-06T08:26:23.562Z" },
+    { url = "https://files.pythonhosted.org/packages/ec/0d/e6dd0ed898b920fec35c6eeeb9acbeb831fff19ad21c5e684744df1d4a36/Django-5.1.8-py3-none-any.whl", hash = "sha256:11b28fa4b00e59d0def004e9ee012fefbb1065a5beb39ee838983fd24493ad4f", size = 8277130, upload-time = "2025-04-02T11:19:51.591Z" },
 ]
 
 [[package]]
@@ -660,15 +688,15 @@ socialaccount = [
 
 [[package]]
 name = "django-auditlog"
-version = "3.2.1"
+version = "3.1.2"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "django", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "python-dateutil", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/e1/46/9da1d94493832fa18d2f6324a76d387fa232001593866987a96047709f4e/django_auditlog-3.2.1.tar.gz", hash = "sha256:63a4c9f7793e94eed804bc31a04d9b0b58244b1d280e2ed273c8b406bff1f779", size = 72926, upload-time = "2025-07-03T20:08:17.734Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/0e/3a/61bfb180019d08db3f7a2e4097bda14ee32bd57f5dffda0c84b2d4c26304/django_auditlog-3.1.2.tar.gz", hash = "sha256:435345b4055d16abfb4ada4bf11320f9e2f6d343874464471fa0041f13f3a474", size = 69359, upload-time = "2025-04-26T11:01:56.553Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/a7/06/67296d050a72dcd76f57f220df621cb27e5b9282ba7ad0f5f74870dce241/django_auditlog-3.2.1-py3-none-any.whl", hash = "sha256:99603ca9d015f7e9b062b1c34f3e0826a3ce6ae6e5950c81bb7e663f7802a899", size = 38330, upload-time = "2025-07-03T20:07:51.735Z" },
+    { url = "https://files.pythonhosted.org/packages/af/34/47edd758abcb4426953b5ff2fa4dd9956c2304e96160ab1b95c3a1ab6e61/django_auditlog-3.1.2-py3-none-any.whl", hash = "sha256:6432a83fdf4397a726488d101fedcb62daafd6d4b825a0fc4c50e3657f5883cd", size = 37312, upload-time = "2025-04-26T11:01:16.776Z" },
 ]
 
 [[package]]
@@ -764,38 +792,38 @@ wheels = [
 
 [[package]]
 name = "django-guardian"
-version = "3.0.3"
+version = "2.4.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "django", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/30/c2/3ed43813dd7313f729dbaa829b4f9ed4a647530151f672cfb5f843c12edf/django_guardian-3.0.3.tar.gz", hash = "sha256:4e59eab4d836da5a027cf0c176d14bc2a4e22cbbdf753159a03946c08c8a196d", size = 85410, upload-time = "2025-06-25T20:42:17.475Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/6f/4c/d1f6923a0ad7f16c403a54c09e94acb76ac6c3765e02523fb09b2b03e1a8/django-guardian-2.4.0.tar.gz", hash = "sha256:c58a68ae76922d33e6bdc0e69af1892097838de56e93e78a8361090bcd9f89a0", size = 159008, upload-time = "2021-05-23T22:11:26.23Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/8b/13/e6f629a978ef5fab8b8d2760cacc3e451016cef952cf4c049d672c5c6b07/django_guardian-3.0.3-py3-none-any.whl", hash = "sha256:d2164cea9f03c369d7ade21802710f3ab23ca6734bcc7dfcfb385906783916c7", size = 118198, upload-time = "2025-06-25T20:42:15.377Z" },
+    { url = "https://files.pythonhosted.org/packages/a2/25/869df12e544b51f583254aadbba6c1a95e11d2d08edeb9e58dd715112db5/django_guardian-2.4.0-py3-none-any.whl", hash = "sha256:440ca61358427e575323648b25f8384739e54c38b3d655c81d75e0cd0d61b697", size = 106107, upload-time = "2021-05-23T22:11:22.75Z" },
 ]
 
 [[package]]
 name = "django-multiselectfield"
-version = "1.0.1"
+version = "0.1.13"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "django", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/04/9a/27060e8aa491ff2d286054df2e89df481a8dfe0e5e459fa36c0f48e3c10c/django_multiselectfield-1.0.1.tar.gz", hash = "sha256:3f8b4fff3e07d4a91c8bb4b809bc35caeb22b41769b606f4c9edc53b8d72a667", size = 22025, upload-time = "2025-06-12T14:41:21.599Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/dd/c3/1a326cc669fea63f22e63f6e2b2b014534a15966506e8d7fa3c232aced42/django_multiselectfield-0.1.13.tar.gz", hash = "sha256:437d72632f4c0ca416951917632529c3d1d42b62bb6c3c03e3396fa50265be94", size = 11704, upload-time = "2024-07-01T05:40:39.456Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/6d/10/23c0644cf67567bbe4e3a2eeeec0e9c79b701990c0e07c5ee4a4f8897f91/django_multiselectfield-1.0.1-py3-none-any.whl", hash = "sha256:18dc14801f7eca844a48e21cba6d8ec35b9b581f2373bbb2cb75e6994518259a", size = 20481, upload-time = "2025-06-12T14:41:20.107Z" },
+    { url = "https://files.pythonhosted.org/packages/be/9e/3ed6f072f1e806516dbc8c95e4ecae7b87af6757eb5d428857ea0a097e76/django_multiselectfield-0.1.13-py3-none-any.whl", hash = "sha256:f146ef568c823a409f4021b98781666ec2debabfceca9176116d749dc39cb8b3", size = 14804, upload-time = "2024-07-01T05:40:37.549Z" },
 ]
 
 [[package]]
 name = "django-soft-delete"
-version = "1.0.19"
+version = "1.0.18"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "django", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/ce/77/44a6615a7da3ca0ddc624039d399d17d6c3503e1c2dad08b443f8d4a3570/django_soft_delete-1.0.19.tar.gz", hash = "sha256:c67ee8920e1456eca84cc59b3304ef27fa9d476b516be726ce7e1fc558502908", size = 11993, upload-time = "2025-06-19T20:32:20.373Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/ec/7e/89cba723dd5d34ccb6003f4812de7f5c69ba32bd73ab37f2bb21ff344c6c/django_soft_delete-1.0.18.tar.gz", hash = "sha256:d2f9db449a4f008e9786f82fa4bafbe4075f7a0b3284844735007e988b2a4df6", size = 11979, upload-time = "2025-02-01T13:43:53.804Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/96/9e/f8b5a02cdcba606eb40fbe30fe0c9c7493a2c18f83ec3b4620e4e86a34d3/django_soft_delete-1.0.19-py3-none-any.whl", hash = "sha256:46aa5fab513db566d3d7a832529ed27245b5900eaaa705535bc7674055801a46", size = 10889, upload-time = "2025-06-19T20:32:19.083Z" },
+    { url = "https://files.pythonhosted.org/packages/f7/d0/6dcca209e48081213854088fc7014e9dbdcd24f4ec2118f8ee29d11c8623/django_soft_delete-1.0.18-py3-none-any.whl", hash = "sha256:603a29e82bbb7a5bada69f2754fad225ccd8cd7f485320ec06d0fc4e9dfddcf0", size = 10876, upload-time = "2025-02-01T13:43:52.109Z" },
 ]
 
 [[package]]
@@ -835,28 +863,28 @@ wheels = [
 
 [[package]]
 name = "djangorestframework"
-version = "3.16.1"
+version = "3.16.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "django", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/8a/95/5376fe618646fde6899b3cdc85fd959716bb67542e273a76a80d9f326f27/djangorestframework-3.16.1.tar.gz", hash = "sha256:166809528b1aced0a17dc66c24492af18049f2c9420dbd0be29422029cfc3ff7", size = 1089735, upload-time = "2025-08-06T17:50:53.251Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/7d/97/112c5a72e6917949b6d8a18ad6c6e72c46da4290c8f36ee5f1c1dcbc9901/djangorestframework-3.16.0.tar.gz", hash = "sha256:f022ff46613584de994c0c6a4aebbace5fd700555fbe9d33b865ebf173eba6c9", size = 1068408, upload-time = "2025-03-28T14:18:42.065Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/b0/ce/bf8b9d3f415be4ac5588545b5fcdbbb841977db1c1d923f7568eeabe1689/djangorestframework-3.16.1-py3-none-any.whl", hash = "sha256:33a59f47fb9c85ede792cbf88bde71893bcda0667bc573f784649521f1102cec", size = 1080442, upload-time = "2025-08-06T17:50:50.667Z" },
+    { url = "https://files.pythonhosted.org/packages/eb/3e/2448e93f4f87fc9a9f35e73e3c05669e0edd0c2526834686e949bb1fd303/djangorestframework-3.16.0-py3-none-any.whl", hash = "sha256:bea7e9f6b96a8584c5224bfb2e4348dfb3f8b5e34edbecb98da258e892089361", size = 1067305, upload-time = "2025-03-28T14:18:39.489Z" },
 ]
 
 [[package]]
 name = "djangorestframework-guardian"
-version = "0.4.0"
+version = "0.3.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "django", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "django-guardian", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "djangorestframework", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/c1/c4/67df9963395e9dddd4e16cbf75098953798e5135f73fb8f4855895505e39/djangorestframework_guardian-0.4.0.tar.gz", hash = "sha256:a8113659e062f65b74cc31af6982420c382642e782d38581b3fdc748a179756c", size = 8239, upload-time = "2025-07-01T07:22:10.809Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/e5/80/0f2190bacfe7c7b2e22d0e1e695882ec3123f9e58817c8392a258cd46442/djangorestframework-guardian-0.3.0.tar.gz", hash = "sha256:1883756452d9bfcc2a51fb4e039a6837a8f6697c756447aa83af085749b59330", size = 8647, upload-time = "2019-10-14T04:24:25.531Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/59/81/3d62f7ff71f7c45ec6664ebf03a4c736bf77f49481604361d40f8f4471e4/djangorestframework_guardian-0.4.0-py3-none-any.whl", hash = "sha256:30c2a349318c1cd603d6953d50d58159f9a0c833f5f8f5a811407d5984a39e14", size = 6064, upload-time = "2025-07-01T07:22:09.661Z" },
+    { url = "https://files.pythonhosted.org/packages/9b/cc/35c1d8fb99172b2646f29e270e9ec443ffe09e0b63e61cd528d4fb4b8b07/djangorestframework_guardian-0.3.0-py2.py3-none-any.whl", hash = "sha256:3bd3dd6ea58e1bceca5048faf6f8b1a93bb5dcff30ba5eb91b9a0e190a48a0c7", size = 6931, upload-time = "2019-08-02T01:00:39.543Z" },
 ]
 
 [[package]]
@@ -900,14 +928,14 @@ wheels = [
 
 [[package]]
 name = "drf-spectacular-sidecar"
-version = "2025.8.1"
+version = "2025.4.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "django", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/a9/f7/0cb2f520723f1823ef7b6651d447927f61ba92d152a5d68132599b90624f/drf_spectacular_sidecar-2025.8.1.tar.gz", hash = "sha256:1944ae0eb5136cff5aa135211bec31084cef1af03a04de9b7f2f912b3c59c251", size = 2407787, upload-time = "2025-08-01T11:28:01.319Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/5d/b6/ce857d73b65b86a9034d0604b5dc1a002f7fa218e32c4dba479a197acd70/drf_spectacular_sidecar-2025.4.1.tar.gz", hash = "sha256:ea7dc4e674174616589d258b5c9676f3c451ec422e62b79e31234d39db53922d", size = 2402076, upload-time = "2025-04-01T11:23:30.627Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/1f/3b/0fcdc6eb294a11ed6e3ddc02fc29968bf403d3ce31645764eedfc91f87a6/drf_spectacular_sidecar-2025.8.1-py3-none-any.whl", hash = "sha256:c65a2a423000cc067395150b4dc28e7398a762d66ee101c4c38a4fb0d29a42a2", size = 2427849, upload-time = "2025-08-01T11:27:59.648Z" },
+    { url = "https://files.pythonhosted.org/packages/cf/c3/d2f31ef748f89d68121aa3d4a71f7dfd44ea54957b84602d70cda2491c43/drf_spectacular_sidecar-2025.4.1-py3-none-any.whl", hash = "sha256:343a24b0d03125fa76d07685072f55779c5c4124d90c10b14e315fdc143ad9b9", size = 2422415, upload-time = "2025-04-01T11:23:28.797Z" },
 ]
 
 [[package]]
@@ -1383,6 +1411,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/c7/fc/4e5a141c3f7c7bed550ac1f69e599e92b6be449dd4677ec09f325cad0955/inotifyrecursive-0.3.5-py3-none-any.whl", hash = "sha256:7e5f4a2e1dc2bef0efa3b5f6b339c41fb4599055a2b54909d020e9e932cc8d2f", size = 8009, upload-time = "2020-11-20T12:38:46.981Z" },
 ]
 
+[[package]]
+name = "isodate"
+version = "0.7.2"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/54/4d/e940025e2ce31a8ce1202635910747e5a87cc3a6a6bb2d00973375014749/isodate-0.7.2.tar.gz", hash = "sha256:4cd1aa0f43ca76f4a6c6c0292a85f40b35ec2e43e315b59f06e6d32171a953e6", size = 29705 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/15/aa/0aca39a37d3c7eb941ba736ede56d689e7be91cab5d9ca846bde3999eba6/isodate-0.7.2-py3-none-any.whl", hash = "sha256:28009937d8031054830160fce6d409ed342816b543597cece116d966c6d99e15", size = 22320 },
+]
+
 [[package]]
 name = "jinja2"
 version = "3.1.6"
@@ -1911,6 +1948,7 @@ name = "paperless-ngx"
 version = "2.17.1"
 source = { virtual = "." }
 dependencies = [
+    { name = "azure-ai-documentintelligence", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "bleach", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "celery", extra = ["redis"], marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "channels", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
@@ -2044,28 +2082,29 @@ typing = [
 
 [package.metadata]
 requires-dist = [
+    { name = "azure-ai-documentintelligence", specifier = ">=1.0.2" },
     { name = "bleach", specifier = "~=6.2.0" },
     { name = "celery", extras = ["redis"], specifier = "~=5.5.1" },
     { name = "channels", specifier = "~=4.2" },
     { name = "channels-redis", specifier = "~=4.2" },
     { name = "concurrent-log-handler", specifier = "~=0.9.25" },
     { name = "dateparser", specifier = "~=1.2" },
-    { name = "django", specifier = "~=5.2.5" },
+    { name = "django", specifier = "~=5.1.7" },
     { name = "django-allauth", extras = ["socialaccount", "mfa"], specifier = "~=65.4.0" },
-    { name = "django-auditlog", specifier = "~=3.2.1" },
+    { name = "django-auditlog", specifier = "~=3.1.2" },
     { name = "django-cachalot", specifier = "~=2.8.0" },
     { name = "django-celery-results", specifier = "~=2.6.0" },
     { name = "django-compression-middleware", specifier = "~=0.5.0" },
     { name = "django-cors-headers", specifier = "~=4.7.0" },
     { name = "django-extensions", specifier = "~=4.1" },
     { name = "django-filter", specifier = "~=25.1" },
-    { name = "django-guardian", specifier = "~=3.0.3" },
-    { name = "django-multiselectfield", specifier = "~=1.0.1" },
+    { name = "django-guardian", specifier = "~=2.4.0" },
+    { name = "django-multiselectfield", specifier = "~=0.1.13" },
     { name = "django-soft-delete", specifier = "~=1.0.18" },
     { name = "djangorestframework", specifier = "~=3.15" },
-    { name = "djangorestframework-guardian", specifier = "~=0.4.0" },
+    { name = "djangorestframework-guardian", specifier = "~=0.3.0" },
     { name = "drf-spectacular", specifier = "~=0.28" },
-    { name = "drf-spectacular-sidecar", specifier = "~=2025.8.1" },
+    { name = "drf-spectacular-sidecar", specifier = "~=2025.4.1" },
     { name = "drf-writable-nested", specifier = "~=0.7.1" },
     { name = "filelock", specifier = "~=3.18.0" },
     { name = "flower", specifier = "~=2.0.1" },
@@ -2119,7 +2158,7 @@ dev = [
     { name = "pre-commit-uv", specifier = "~=4.1.3" },
     { name = "pytest", specifier = "~=8.4.1" },
     { name = "pytest-cov", specifier = "~=6.2.1" },
-    { name = "pytest-django", specifier = "~=4.11.1" },
+    { name = "pytest-django", specifier = "~=4.10.0" },
     { name = "pytest-env" },
     { name = "pytest-httpx" },
     { name = "pytest-mock" },
@@ -2143,7 +2182,7 @@ testing = [
     { name = "imagehash" },
     { name = "pytest", specifier = "~=8.4.1" },
     { name = "pytest-cov", specifier = "~=6.2.1" },
-    { name = "pytest-django", specifier = "~=4.11.1" },
+    { name = "pytest-django", specifier = "~=4.10.0" },
     { name = "pytest-env" },
     { name = "pytest-httpx" },
     { name = "pytest-mock" },
@@ -2597,14 +2636,14 @@ wheels = [
 
 [[package]]
 name = "pytest-django"
-version = "4.11.1"
+version = "4.10.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "pytest", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/b1/fb/55d580352db26eb3d59ad50c64321ddfe228d3d8ac107db05387a2fadf3a/pytest_django-4.11.1.tar.gz", hash = "sha256:a949141a1ee103cb0e7a20f1451d355f83f5e4a5d07bdd4dcfdd1fd0ff227991", size = 86202, upload-time = "2025-04-03T18:56:09.338Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/a5/10/a096573b4b896f18a8390d9dafaffc054c1f613c60bf838300732e538890/pytest_django-4.10.0.tar.gz", hash = "sha256:1091b20ea1491fd04a310fc9aaff4c01b4e8450e3b157687625e16a6b5f3a366", size = 84710, upload-time = "2025-02-10T14:52:57.337Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/be/ac/bd0608d229ec808e51a21044f3f2f27b9a37e7a0ebaca7247882e67876af/pytest_django-4.11.1-py3-none-any.whl", hash = "sha256:1b63773f648aa3d8541000c26929c1ea63934be1cfa674c76436966d73fe6a10", size = 25281, upload-time = "2025-04-03T18:56:07.678Z" },
+    { url = "https://files.pythonhosted.org/packages/58/4c/a4fe18205926216e1aebe1f125cba5bce444f91b6e4de4f49fa87e322775/pytest_django-4.10.0-py3-none-any.whl", hash = "sha256:57c74ef3aa9d89cae5a5d73fbb69a720a62673ade7ff13b9491872409a3f5918", size = 23975, upload-time = "2025-02-10T14:52:55.325Z" },
 ]
 
 [[package]]