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

[ci skip]

docs/configuration.md

@@ -1805,3 +1805,23 @@ 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

@@ -882,6 +882,21 @@ 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.
+
+Additionally, when using a commercial service with this feature, consider both potential costs as well as any associated file size
+or page limitations (e.g. with a free tier).
+
 ## 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",
   "babel>=2.17",
   "bleach~=6.2.0",
   "celery[redis]~=5.5.1",
@@ -33,7 +34,7 @@ dependencies = [
   "django-cors-headers~=4.9.0",
   "django-extensions~=4.1",
   "django-filter~=25.1",
-  "django-guardian~=3.2.0",
+  "django-guardian~=3.1.2",
   "django-multiselectfield~=1.0.1",
   "django-soft-delete~=1.0.18",
   "django-treenode>=0.23.2",
@@ -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/paperless/settings.py

@@ -322,6 +322,7 @@ 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",
@@ -1389,3 +1390,10 @@ WEBHOOKS_ALLOW_INTERNAL_REQUESTS = __get_boolean(
     "PAPERLESS_WEBHOOKS_ALLOW_INTERNAL_REQUESTS",
     "true",
 )
+
+###############################################################################
+# 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_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 +1,17 @@
+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 and settings.REMOTE_OCR_API_KEY
+    ):
+        return [
+            Error(
+                "Azure AI remote parser requires endpoint and API key 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": ".pdf",
+                "image/png": ".png",
+                "image/jpeg": ".jpg",
+                "image/tiff": ".tiff",
+                "image/bmp": ".bmp",
+                "image/gif": ".gif",
+                "image/webp": ".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 = 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)
+
+        client.close()
+        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 = ""
+        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 +1,24 @@
+from unittest 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 and API key to be configured.",
+            ),
+        )

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: str, strings: list[str]):
+        # 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": ".pdf",
+            "image/png": ".png",
+            "image/jpeg": ".jpg",
+            "image/tiff": ".tiff",
+            "image/bmp": ".bmp",
+            "image/gif": ".gif",
+            "image/webp": ".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

@@ -95,6 +95,34 @@ 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"
@@ -782,15 +810,15 @@ wheels = [
 
 [[package]]
 name = "django-guardian"
-version = "3.2.0"
+version = "3.1.3"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "django", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "typing-extensions", marker = "(python_full_version < '3.13' and sys_platform == 'darwin') or (python_full_version < '3.13' and sys_platform == 'linux')" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/e2/f9/bcff6a931298b9eb55e1550b55ab964fab747f594ba6d2d81cbe19736c5f/django_guardian-3.2.0.tar.gz", hash = "sha256:9e18ecd2e211b665972690c2d03d27bce0ea4932b5efac24a4bb9d526950a69e", size = 99940, upload-time = "2025-09-16T10:35:53.609Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/81/d3/436a44c7688fce1a978224c349ba66c95bf9103d548596b7a2694fd58c03/django_guardian-3.1.3.tar.gz", hash = "sha256:12b5e66c18c97088b0adfa033ab14be68c321c170fd3ec438898271f00a71699", size = 93571, upload-time = "2025-09-10T08:36:23.928Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/2f/23/63a7d868373a73d25c4a5c2dd3cce3aaeb22fbee82560d42b6e93ba01403/django_guardian-3.2.0-py3-none-any.whl", hash = "sha256:0768565a057988a93fc4a1d93649c4a794abfd7473a8408a079cfbf83c559d77", size = 134674, upload-time = "2025-09-16T10:35:51.69Z" },
+    { url = "https://files.pythonhosted.org/packages/83/fc/6fd7b8bc7c52cbbfd1714673cfd28ff0b3fae32265c52d492ec0dee22cb8/django_guardian-3.1.3-py3-none-any.whl", hash = "sha256:90e28b40eea65c326a3a961908cc300f9e1cd69b74e88d38317a9befa167b71c", size = 127687, upload-time = "2025-09-10T08:36:22.533Z" },
 ]
 
 [[package]]
@@ -807,14 +835,14 @@ wheels = [
 
 [[package]]
 name = "django-soft-delete"
-version = "1.0.21"
+version = "1.0.19"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "django", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/da/bf/13996c18bffee3bbcf294830c1737bfb5564164b8319c51e6714b6bdf783/django_soft_delete-1.0.21.tar.gz", hash = "sha256:542bd4650d2769105a4363ea7bb7fbdb3c28429dbaa66417160f8f4b5dc689d5", size = 21153, upload-time = "2025-09-17T08:46:30.476Z" }
+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" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/fa/e6/8f4fed14499c63e35ca33cf9f424ad2e14e963ec5545594d7c7dc2f710f4/django_soft_delete-1.0.21-py3-none-any.whl", hash = "sha256:dd91e671d9d431ff96f4db727ce03e7fbb4008ae4541b1d162d5d06cc9becd2a", size = 18681, upload-time = "2025-09-17T08:46:29.272Z" },
+    { 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" },
 ]
 
 [[package]]
@@ -1412,6 +1440,15 @@ 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"
@@ -2032,6 +2069,7 @@ name = "paperless-ngx"
 version = "2.18.4"
 source = { virtual = "." }
 dependencies = [
+    { name = "azure-ai-documentintelligence", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "babel", 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'" },
@@ -2169,6 +2207,7 @@ typing = [
 
 [package.metadata]
 requires-dist = [
+    { name = "azure-ai-documentintelligence", specifier = ">=1.0.2" },
     { name = "babel", specifier = ">=2.17" },
     { name = "bleach", specifier = "~=6.2.0" },
     { name = "celery", extras = ["redis"], specifier = "~=5.5.1" },
@@ -2185,7 +2224,7 @@ requires-dist = [
     { name = "django-cors-headers", specifier = "~=4.9.0" },
     { name = "django-extensions", specifier = "~=4.1" },
     { name = "django-filter", specifier = "~=25.1" },
-    { name = "django-guardian", specifier = "~=3.2.0" },
+    { name = "django-guardian", specifier = "~=3.1.2" },
     { name = "django-multiselectfield", specifier = "~=1.0.1" },
     { name = "django-soft-delete", specifier = "~=1.0.18" },
     { name = "django-treenode", specifier = ">=0.23.2" },
@@ -2794,14 +2833,14 @@ wheels = [
 
 [[package]]
 name = "pytest-mock"
-version = "3.15.1"
+version = "3.14.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "pytest", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/68/14/eb014d26be205d38ad5ad20d9a80f7d201472e08167f0bb4361e251084a9/pytest_mock-3.15.1.tar.gz", hash = "sha256:1849a238f6f396da19762269de72cb1814ab44416fa73a8686deac10b0d87a0f", size = 34036, upload-time = "2025-09-16T16:37:27.081Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/71/28/67172c96ba684058a4d24ffe144d64783d2a270d0af0d9e792737bddc75c/pytest_mock-3.14.1.tar.gz", hash = "sha256:159e9edac4c451ce77a5cdb9fc5d1100708d2dd4ba3c3df572f14097351af80e", size = 33241, upload-time = "2025-05-26T13:58:45.167Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/5a/cc/06253936f4a7fa2e0f48dfe6d851d9c56df896a9ab09ac019d70b760619c/pytest_mock-3.15.1-py3-none-any.whl", hash = "sha256:0a25e2eb88fe5168d535041d09a4529a188176ae608a6d249ee65abc0949630d", size = 10095, upload-time = "2025-09-16T16:37:25.734Z" },
+    { url = "https://files.pythonhosted.org/packages/b2/05/77b60e520511c53d1c1ca75f1930c7dd8e971d0c4379b7f4b3f9644685ba/pytest_mock-3.14.1-py3-none-any.whl", hash = "sha256:178aefcd11307d874b4cd3100344e7e2d888d9791a6a1d9bfe90fbc1b74fd1d0", size = 9923, upload-time = "2025-05-26T13:58:43.487Z" },
 ]
 
 [[package]]
@@ -2819,15 +2858,16 @@ wheels = [
 
 [[package]]
 name = "pytest-sugar"
-version = "1.1.1"
+version = "1.0.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
+    { name = "packaging", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "pytest", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "termcolor", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/0b/4e/60fed105549297ba1a700e1ea7b828044842ea27d72c898990510b79b0e2/pytest-sugar-1.1.1.tar.gz", hash = "sha256:73b8b65163ebf10f9f671efab9eed3d56f20d2ca68bda83fa64740a92c08f65d", size = 16533, upload-time = "2025-08-23T12:19:35.737Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/f5/ac/5754f5edd6d508bc6493bc37d74b928f102a5fff82d9a80347e180998f08/pytest-sugar-1.0.0.tar.gz", hash = "sha256:6422e83258f5b0c04ce7c632176c7732cab5fdb909cb39cca5c9139f81276c0a", size = 14992, upload-time = "2024-02-01T18:30:36.735Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/87/d5/81d38a91c1fdafb6711f053f5a9b92ff788013b19821257c2c38c1e132df/pytest_sugar-1.1.1-py3-none-any.whl", hash = "sha256:2f8319b907548d5b9d03a171515c1d43d2e38e32bd8182a1781eb20b43344cc8", size = 11440, upload-time = "2025-08-23T12:19:34.894Z" },
+    { url = "https://files.pythonhosted.org/packages/92/fb/889f1b69da2f13691de09a111c16c4766a433382d44aa0ecf221deded44a/pytest_sugar-1.0.0-py3-none-any.whl", hash = "sha256:70ebcd8fc5795dc457ff8b69d266a4e2e8a74ae0c3edc749381c64b5246c8dfd", size = 10171, upload-time = "2024-02-01T18:30:29.395Z" },
 ]
 
 [[package]]
@@ -3789,11 +3829,11 @@ wheels = [
 
 [[package]]
 name = "types-dateparser"
-version = "1.2.2.20250809"
+version = "1.2.0.20250208"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/63/54/2d2b77d1beba5bdb7faeabc7d7f0b9b2f8e428f79f45a144ad7ab87d1a29/types_dateparser-1.2.2.20250809.tar.gz", hash = "sha256:a898f5527e6c34d213bc5d85254b8246d8b1e76239ed9243711198add0c8a29c", size = 15804, upload-time = "2025-08-09T03:15:11.298Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/da/9e/06305e20da13e1014398dac11c346089294f933a1e9e18c80b752b97a795/types_dateparser-1.2.0.20250208.tar.gz", hash = "sha256:11ad024b43a655bcab564f21b172a117e6a09d0fc2e8a8131f52e5b68a59a2a6", size = 15078, upload-time = "2025-02-08T02:37:31.738Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/5d/5a/a5cf930804f639f5f1c58434613a1bbc1bd4641e29aec07444f316b41dff/types_dateparser-1.2.2.20250809-py3-none-any.whl", hash = "sha256:f12ae46abc3085e60e16fbe55730c5acbce980cbe3b176b17b08b4cef85850ef", size = 22140, upload-time = "2025-08-09T03:15:10.234Z" },
+    { url = "https://files.pythonhosted.org/packages/eb/c3/7bbc3d907eaa5cf604207f19b60be5773e12065c621e1bb61f7f9f5159ec/types_dateparser-1.2.0.20250208-py3-none-any.whl", hash = "sha256:bfe9d2f36fca22900797bfdd240e3175d885b9541237447ddd7161ea1be2ff77", size = 21033, upload-time = "2025-02-08T02:37:30.335Z" },
 ]
 
 [[package]]
@@ -3816,11 +3856,11 @@ wheels = [
 
 [[package]]
 name = "types-markdown"
-version = "3.9.0.20250906"
+version = "3.7.0.20241204"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/fb/dd/8a91a5f4dce705eff6862e01e8fd9984cdc55e6d6c3cfcadc68410c43abf/types_markdown-3.9.0.20250906.tar.gz", hash = "sha256:f02dc1a2d130b093de4910c64b2d0a811ae7020f03624df41c667818d2fee050", size = 19439, upload-time = "2025-09-06T02:45:23.617Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/d4/3c/874ac6ce93f4e6bd0283a5df2c8065f4e623c6c3bc0b2fb98c098313cb73/types_markdown-3.7.0.20241204.tar.gz", hash = "sha256:ecca2b25cd23163fd28ed5ba34d183d731da03e8a5ed3a20b60daded304c5410", size = 17820, upload-time = "2024-12-04T02:57:29.117Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/29/17/b0b9d315422eae106af1d30e51afe4b59c18b42311605fed9068ac6aa065/types_markdown-3.9.0.20250906-py3-none-any.whl", hash = "sha256:afac4297e4e75f00b4043f9b3a989dc5924230d065996a233b9bce894c438cc2", size = 25830, upload-time = "2025-09-06T02:45:22.211Z" },
+    { url = "https://files.pythonhosted.org/packages/04/26/3c9730e845cfd0d587e0dfa9c1975f02f9f49407afbf30800094bdac0286/types_Markdown-3.7.0.20241204-py3-none-any.whl", hash = "sha256:f96146c367ea9c82bfe9903559d72706555cc2a1a3474c58ebba03b418ab18da", size = 23572, upload-time = "2024-12-04T02:57:28.217Z" },
 ]
 
 [[package]]
@@ -4094,11 +4134,11 @@ wheels = [
 
 [[package]]
 name = "whitenoise"
-version = "6.11.0"
+version = "6.10.0"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/15/95/8c81ec6b6ebcbf8aca2de7603070ccf37dbb873b03f20708e0f7c1664bc6/whitenoise-6.11.0.tar.gz", hash = "sha256:0f5bfce6061ae6611cd9396a8231e088722e4fc67bc13a111be74c738d99375f", size = 26432, upload-time = "2025-09-18T09:16:10.995Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/27/9a/4f4b84ff1f3a5c3cbc8070b6ecbbab6cd121c385244c9d24d80bb284190f/whitenoise-6.10.0.tar.gz", hash = "sha256:7b7e53de65d749cb1ce4a7100e751d9742e323b52746f9f93944c0d348ea2d02", size = 26412, upload-time = "2025-09-09T11:07:24.694Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/6c/e9/4366332f9295fe0647d7d3251ce18f5615fbcb12d02c79a26f8dba9221b3/whitenoise-6.11.0-py3-none-any.whl", hash = "sha256:b2aeb45950597236f53b5342b3121c5de69c8da0109362aee506ce88e022d258", size = 20197, upload-time = "2025-09-18T09:16:09.754Z" },
+    { url = "https://files.pythonhosted.org/packages/cb/3b/4fa26e02935334fa0eb1422c938b1db796c55de7a432cc86b9d8cf97260c/whitenoise-6.10.0-py3-none-any.whl", hash = "sha256:bad74a40b33b055ba59731b6048dd08d5647f273b72bef922aa43ddd287b02da", size = 20194, upload-time = "2025-09-09T11:07:23.544Z" },
 ]
 
 [[package]]