Fix some button consistency

---------

Co-authored-by: Trenton H <797416+stumpylog@users.noreply.github.com>

docs/configuration.md

@@ -159,6 +159,23 @@ Available options are `postgresql` and `mariadb`.
 
     Defaults to unset, which uses Django’s built-in defaults.
 
+#### [`PAPERLESS_DB_POOLSIZE=<int>`](#PAPERLESS_DB_POOLSIZE) {#PAPERLESS_DB_POOLSIZE}
+
+: Defines the maximum number of database connections to keep in the pool.
+
+    Only applies to PostgreSQL. This setting is ignored for other database engines.
+
+    The value must be greater than or equal to 1 to be used.
+    Defaults to unset, which disables connection pooling.
+
+    !!! note
+
+    A small pool is typically sufficient — for example, a size of 4.
+    Make sure your PostgreSQL server's max_connections setting is large enough to handle:
+    ```(Paperless workers + Celery workers) × pool size + safety margin```
+    For example, with 4 Paperless workers and 2 Celery workers, and a pool size of 4:
+    (4 + 2) × 4 + 10 = 34 connections required.
+
 #### [`PAPERLESS_DB_READ_CACHE_ENABLED=<bool>`](#PAPERLESS_DB_READ_CACHE_ENABLED) {#PAPERLESS_DB_READ_CACHE_ENABLED}
 
 : Caches the database read query results into Redis. This can significantly improve application response times by caching database queries, at the cost of slightly increased memory usage.
@@ -1759,23 +1776,3 @@ 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

@@ -25,10 +25,9 @@ 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, unless you explicitly choose to do so.
+-   _Your_ data is stored locally on _your_ server and is never transmitted or shared in any way.
 -   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.
-    -   _New!_ Supports remote OCR with Azure AI (opt-in).
+-   Utilizes the open-source Tesseract engine to recognize more than 100 languages.
 -   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

@@ -841,18 +841,6 @@ 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

@@ -15,7 +15,6 @@ 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",
@@ -53,6 +52,7 @@ dependencies = [
   "ocrmypdf~=16.10.0",
   "pathvalidate~=3.3.1",
   "pdf2image~=1.17.0",
+  "psycopg-pool",
   "python-dateutil~=2.9.0",
   "python-dotenv~=1.1.0",
   "python-gnupg~=0.5.4",
@@ -75,9 +75,10 @@ optional-dependencies.mariadb = [
   "mysqlclient~=2.2.7",
 ]
 optional-dependencies.postgres = [
-  "psycopg[c]==3.2.9",
+  "psycopg[c,pool]==3.2.9",
   # Direct dependency for proper resolution of the pre-built wheels
   "psycopg-c==3.2.9",
+  "psycopg-pool==3.2.6",
 ]
 optional-dependencies.webserver = [
   "granian[uvloop]~=2.4.1",
@@ -241,7 +242,6 @@ testpaths = [
   "src/paperless_tesseract/tests/",
   "src/paperless_tika/tests",
   "src/paperless_text/tests/",
-  "src/paperless_remote/tests/",
 ]
 addopts = [
   "--pythonwarnings=all",

src-ui/src/app/components/admin/config/config.component.html

@@ -50,7 +50,7 @@
     <div [ngbNavOutlet]="nav" class="border-start border-end border-bottom p-3 mb-3 shadow-sm"></div>
     <div class="btn-toolbar" role="toolbar">
         <div class="btn-group me-2">
-            <button type="button" (click)="discardChanges()" class="btn btn-secondary" [disabled]="loading || (isDirty$ | async) === false" i18n>Discard</button>
+            <button type="button" (click)="discardChanges()" class="btn btn-outline-secondary" [disabled]="loading || (isDirty$ | async) === false" i18n>Discard</button>
         </div>
         <div class="btn-group">
             <button type="submit" class="btn btn-primary" [disabled]="loading || !configForm.valid || (isDirty$ | async) === false" i18n>Save</button>

src-ui/src/app/components/admin/settings/settings.component.html

@@ -358,6 +358,6 @@
 
   <div [ngbNavOutlet]="nav" class="border-start border-end border-bottom p-3 mb-3 shadow-sm"></div>
 
-  <button type="submit" class="btn btn-primary mb-2" [disabled]="(isDirty$ | async) === false" i18n>Save</button>
-  <button type="button" (click)="reset()" class="btn btn-secondary ms-2 mb-2" [disabled]="(isDirty$ | async) === false" i18n>Cancel</button>
+  <button type="button" (click)="reset()" class="btn btn-outline-secondary mb-2" [disabled]="(isDirty$ | async) === false" i18n>Cancel</button>
+  <button type="submit" class="btn btn-primary ms-2 mb-2" [disabled]="(isDirty$ | async) === false" i18n>Save</button>
 </form>

src-ui/src/app/components/manage/saved-views/saved-views.component.html

@@ -70,6 +70,6 @@
     }
   </ul>
 
-  <button type="submit" class="btn btn-primary mb-2" [disabled]="(isDirty$ | async) === false" i18n>Save</button>
-  <button type="button" (click)="reset()" class="btn btn-secondary ms-2 mb-2" [disabled]="(isDirty$ | async) === false" i18n>Cancel</button>
+  <button type="button" (click)="reset()" class="btn btn-outline-secondary mb-2" [disabled]="(isDirty$ | async) === false" i18n>Cancel</button>
+  <button type="submit" class="btn btn-primary ms-2 mb-2" [disabled]="(isDirty$ | async) === false" i18n>Save</button>
 </form>

src/documents/signals/handlers.py

@@ -12,11 +12,13 @@ from celery.signals import before_task_publish
 from celery.signals import task_failure
 from celery.signals import task_postrun
 from celery.signals import task_prerun
+from celery.signals import worker_process_init
 from django.conf import settings
 from django.contrib.auth.models import Group
 from django.contrib.auth.models import User
 from django.db import DatabaseError
 from django.db import close_old_connections
+from django.db import connections
 from django.db import models
 from django.db.models import Q
 from django.dispatch import receiver
@@ -1439,3 +1441,18 @@ def task_failure_handler(
             task_instance.save()
     except Exception:  # pragma: no cover
         logger.exception("Updating PaperlessTask failed")
+
+
+@worker_process_init.connect
+def close_connection_pool_on_worker_init(**kwargs):
+    """
+    Close the DB connection pool for each Celery child process after it starts.
+
+    This is necessary because the parent process parse the Django configuration,
+    initializes connection pools then forks.
+
+    Closing these pools after forking ensures child processes have a valid connection.
+    """
+    for conn in connections.all(initialized_only=True):
+        if conn.alias == "default" and hasattr(conn, "pool") and conn.pool:
+            conn.close_pool()

src/locale/en_US/LC_MESSAGES/django.po

@@ -2,7 +2,7 @@ msgid ""
 msgstr ""
 "Project-Id-Version: paperless-ngx\n"
 "Report-Msgid-Bugs-To: \n"
-"POT-Creation-Date: 2025-07-08 21:14+0000\n"
+"POT-Creation-Date: 2025-08-02 12:55+0000\n"
 "PO-Revision-Date: 2022-02-17 04:17\n"
 "Last-Translator: \n"
 "Language-Team: English\n"
@@ -1645,147 +1645,147 @@ msgstr ""
 msgid "paperless application settings"
 msgstr ""
 
-#: paperless/settings.py:762
+#: paperless/settings.py:774
 msgid "English (US)"
 msgstr ""
 
-#: paperless/settings.py:763
+#: paperless/settings.py:775
 msgid "Arabic"
 msgstr ""
 
-#: paperless/settings.py:764
+#: paperless/settings.py:776
 msgid "Afrikaans"
 msgstr ""
 
-#: paperless/settings.py:765
+#: paperless/settings.py:777
 msgid "Belarusian"
 msgstr ""
 
-#: paperless/settings.py:766
+#: paperless/settings.py:778
 msgid "Bulgarian"
 msgstr ""
 
-#: paperless/settings.py:767
+#: paperless/settings.py:779
 msgid "Catalan"
 msgstr ""
 
-#: paperless/settings.py:768
+#: paperless/settings.py:780
 msgid "Czech"
 msgstr ""
 
-#: paperless/settings.py:769
+#: paperless/settings.py:781
 msgid "Danish"
 msgstr ""
 
-#: paperless/settings.py:770
+#: paperless/settings.py:782
 msgid "German"
 msgstr ""
 
-#: paperless/settings.py:771
+#: paperless/settings.py:783
 msgid "Greek"
 msgstr ""
 
-#: paperless/settings.py:772
+#: paperless/settings.py:784
 msgid "English (GB)"
 msgstr ""
 
-#: paperless/settings.py:773
+#: paperless/settings.py:785
 msgid "Spanish"
 msgstr ""
 
-#: paperless/settings.py:774
+#: paperless/settings.py:786
 msgid "Persian"
 msgstr ""
 
-#: paperless/settings.py:775
+#: paperless/settings.py:787
 msgid "Finnish"
 msgstr ""
 
-#: paperless/settings.py:776
+#: paperless/settings.py:788
 msgid "French"
 msgstr ""
 
-#: paperless/settings.py:777
+#: paperless/settings.py:789
 msgid "Hungarian"
 msgstr ""
 
-#: paperless/settings.py:778
+#: paperless/settings.py:790
 msgid "Italian"
 msgstr ""
 
-#: paperless/settings.py:779
+#: paperless/settings.py:791
 msgid "Japanese"
 msgstr ""
 
-#: paperless/settings.py:780
+#: paperless/settings.py:792
 msgid "Korean"
 msgstr ""
 
-#: paperless/settings.py:781
+#: paperless/settings.py:793
 msgid "Luxembourgish"
 msgstr ""
 
-#: paperless/settings.py:782
+#: paperless/settings.py:794
 msgid "Norwegian"
 msgstr ""
 
-#: paperless/settings.py:783
+#: paperless/settings.py:795
 msgid "Dutch"
 msgstr ""
 
-#: paperless/settings.py:784
+#: paperless/settings.py:796
 msgid "Polish"
 msgstr ""
 
-#: paperless/settings.py:785
+#: paperless/settings.py:797
 msgid "Portuguese (Brazil)"
 msgstr ""
 
-#: paperless/settings.py:786
+#: paperless/settings.py:798
 msgid "Portuguese"
 msgstr ""
 
-#: paperless/settings.py:787
+#: paperless/settings.py:799
 msgid "Romanian"
 msgstr ""
 
-#: paperless/settings.py:788
+#: paperless/settings.py:800
 msgid "Russian"
 msgstr ""
 
-#: paperless/settings.py:789
+#: paperless/settings.py:801
 msgid "Slovak"
 msgstr ""
 
-#: paperless/settings.py:790
+#: paperless/settings.py:802
 msgid "Slovenian"
 msgstr ""
 
-#: paperless/settings.py:791
+#: paperless/settings.py:803
 msgid "Serbian"
 msgstr ""
 
-#: paperless/settings.py:792
+#: paperless/settings.py:804
 msgid "Swedish"
 msgstr ""
 
-#: paperless/settings.py:793
+#: paperless/settings.py:805
 msgid "Turkish"
 msgstr ""
 
-#: paperless/settings.py:794
+#: paperless/settings.py:806
 msgid "Ukrainian"
 msgstr ""
 
-#: paperless/settings.py:795
+#: paperless/settings.py:807
 msgid "Vietnamese"
 msgstr ""
 
-#: paperless/settings.py:796
+#: paperless/settings.py:808
 msgid "Chinese Simplified"
 msgstr ""
 
-#: paperless/settings.py:797
+#: paperless/settings.py:809
 msgid "Chinese Traditional"
 msgstr ""
 

src/paperless/settings.py

@@ -324,7 +324,6 @@ 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",
@@ -704,6 +703,9 @@ def _parse_db_settings() -> dict:
         # Leave room for future extensibility
         if os.getenv("PAPERLESS_DBENGINE") == "mariadb":
             engine = "django.db.backends.mysql"
+            # Contrary to Postgres, Django does not natively support connection pooling for MariaDB.
+            # However, since MariaDB uses threads instead of forks, establishing connections is significantly faster
+            # compared to PostgreSQL, so the lack of pooling is not an issue
             options = {
                 "read_default_file": "/etc/mysql/my.cnf",
                 "charset": "utf8mb4",
@@ -723,6 +725,15 @@ def _parse_db_settings() -> dict:
                 "sslcert": os.getenv("PAPERLESS_DBSSLCERT", None),
                 "sslkey": os.getenv("PAPERLESS_DBSSLKEY", None),
             }
+            if int(os.getenv("PAPERLESS_DB_POOLSIZE", 0)) > 0:
+                options.update(
+                    {
+                        "pool": {
+                            "min_size": 1,
+                            "max_size": int(os.getenv("PAPERLESS_DB_POOLSIZE")),
+                        },
+                    },
+                )
 
         databases["default"]["ENGINE"] = engine
         databases["default"]["OPTIONS"].update(options)
@@ -1410,11 +1421,3 @@ 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_remote/__init__.py

@@ -1,4 +0,0 @@
-# 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

@@ -1,14 +0,0 @@
-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

@@ -1,15 +0,0 @@
-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

@@ -1,113 +0,0 @@
-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

@@ -1,18 +0,0 @@
-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

@@ -1,29 +0,0 @@
-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

@@ -1,101 +0,0 @@
-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

@@ -93,34 +93,6 @@ 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"
@@ -1411,15 +1383,6 @@ 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"
@@ -1948,7 +1911,6 @@ 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'" },
@@ -2009,10 +1971,11 @@ mariadb = [
     { name = "mysqlclient", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
 ]
 postgres = [
-    { name = "psycopg", extra = ["c"], marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+    { name = "psycopg", extra = ["c", "pool"], marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "psycopg-c", version = "3.2.9", source = { registry = "https://pypi.org/simple" }, marker = "(python_full_version != '3.12.*' and platform_machine == 'aarch64' and sys_platform == 'linux') or (python_full_version != '3.12.*' and platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux') or sys_platform == 'darwin'" },
     { name = "psycopg-c", version = "3.2.9", source = { url = "https://github.com/paperless-ngx/builder/releases/download/psycopg-3.2.9/psycopg_c-3.2.9-cp312-cp312-linux_aarch64.whl" }, marker = "python_full_version == '3.12.*' and platform_machine == 'aarch64' and sys_platform == 'linux'" },
     { name = "psycopg-c", version = "3.2.9", source = { url = "https://github.com/paperless-ngx/builder/releases/download/psycopg-3.2.9/psycopg_c-3.2.9-cp312-cp312-linux_x86_64.whl" }, marker = "python_full_version == '3.12.*' and platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "psycopg-pool", version = "3.2.6", source = { registry = "https://pypi.org/simple" }, marker = "sys_platform == 'linux' or sys_platform == 'darwin'" },
 ]
 webserver = [
     { name = "granian", extra = ["uvloop"], marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
@@ -2080,7 +2043,6 @@ 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" },
@@ -2118,10 +2080,11 @@ requires-dist = [
     { name = "ocrmypdf", specifier = "~=16.10.0" },
     { name = "pathvalidate", specifier = "~=3.3.1" },
     { name = "pdf2image", specifier = "~=1.17.0" },
-    { name = "psycopg", extras = ["c"], marker = "extra == 'postgres'", specifier = "==3.2.9" },
+    { name = "psycopg", extras = ["c", "pool"], marker = "extra == 'postgres'", specifier = "==3.2.9" },
     { name = "psycopg-c", marker = "python_full_version == '3.12.*' and platform_machine == 'aarch64' and sys_platform == 'linux' and extra == 'postgres'", url = "https://github.com/paperless-ngx/builder/releases/download/psycopg-3.2.9/psycopg_c-3.2.9-cp312-cp312-linux_aarch64.whl" },
     { name = "psycopg-c", marker = "python_full_version == '3.12.*' and platform_machine == 'x86_64' and sys_platform == 'linux' and extra == 'postgres'", url = "https://github.com/paperless-ngx/builder/releases/download/psycopg-3.2.9/psycopg_c-3.2.9-cp312-cp312-linux_x86_64.whl" },
     { name = "psycopg-c", marker = "(python_full_version != '3.12.*' and platform_machine == 'aarch64' and extra == 'postgres') or (python_full_version != '3.12.*' and platform_machine == 'x86_64' and extra == 'postgres') or (platform_machine != 'aarch64' and platform_machine != 'x86_64' and extra == 'postgres') or (sys_platform != 'linux' and extra == 'postgres')", specifier = "==3.2.9" },
+    { name = "psycopg-pool", marker = "extra == 'postgres'" },
     { name = "python-dateutil", specifier = "~=2.9.0" },
     { name = "python-dotenv", specifier = "~=1.1.0" },
     { name = "python-gnupg", specifier = "~=0.5.4" },
@@ -2472,6 +2435,9 @@ c = [
     { name = "psycopg-c", version = "3.2.9", source = { url = "https://github.com/paperless-ngx/builder/releases/download/psycopg-3.2.9/psycopg_c-3.2.9-cp312-cp312-linux_aarch64.whl" }, marker = "python_full_version == '3.12.*' and implementation_name != 'pypy' and platform_machine == 'aarch64' and sys_platform == 'linux'" },
     { name = "psycopg-c", version = "3.2.9", source = { url = "https://github.com/paperless-ngx/builder/releases/download/psycopg-3.2.9/psycopg_c-3.2.9-cp312-cp312-linux_x86_64.whl" }, marker = "python_full_version == '3.12.*' and implementation_name != 'pypy' and platform_machine == 'x86_64' and sys_platform == 'linux'" },
 ]
+pool = [
+    { name = "psycopg-pool", version = "3.2.6", source = { registry = "https://pypi.org/simple" }, marker = "sys_platform == 'linux' or sys_platform == 'darwin'" },
+]
 
 [[package]]
 name = "psycopg-c"
@@ -2505,6 +2471,16 @@ wheels = [
     { url = "https://github.com/paperless-ngx/builder/releases/download/psycopg-3.2.9/psycopg_c-3.2.9-cp312-cp312-linux_x86_64.whl", hash = "sha256:250c357319242da102047b04c5cc78af872dbf85c2cb05abf114e1fb5f207917" },
 ]
 
+[[package]]
+name = "psycopg-pool"
+version = "3.2.6"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/cf/13/1e7850bb2c69a63267c3dbf37387d3f71a00fd0e2fa55c5db14d64ba1af4/psycopg_pool-3.2.6.tar.gz", hash = "sha256:0f92a7817719517212fbfe2fd58b8c35c1850cdd2a80d36b581ba2085d9148e5", size = 29770, upload-time = "2025-02-26T12:03:47.129Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/47/fd/4feb52a55c1a4bd748f2acaed1903ab54a723c47f6d0242780f4d97104d4/psycopg_pool-3.2.6-py3-none-any.whl", hash = "sha256:5887318a9f6af906d041a0b1dc1c60f8f0dda8340c2572b74e10907b51ed5da7", size = 38252, upload-time = "2025-02-26T12:03:45.073Z" },
+]
+
+
 [[package]]
 name = "pyasn1"
 version = "0.6.1"