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

[ci skip]

docker/rootfs/etc/s6-overlay/s6-rc.d/init-wait-for-db/run

@@ -50,9 +50,8 @@ wait_for_mariadb() {
 
 	local -r host="${PAPERLESS_DBHOST:-localhost}"
 	local -r port="${PAPERLESS_DBPORT:-3306}"
-	local -r user="${PAPERLESS_DBUSER:-paperless}"
 
-	while ! mariadb-admin --host="${host}" --port="${port}" --user="${user}" ping --silent >/dev/null 2>&1; do
+	while ! mariadb-admin --host="$host" --port="$port" ping --silent >/dev/null 2>&1; do
 		delay_next_attempt
 	done
 	echo "${LOG_PREFIX} Connected to MariaDB"

docs/changelog.md

@@ -1,80 +1,5 @@
 # Changelog
 
-## paperless-ngx 2.20.0
-
-### Notable Changes
-
--   Feature: Upgrade underlying Docker image to Trixie [@stumpylog](https://github.com/stumpylog) ([#10562](https://github.com/paperless-ngx/paperless-ngx/pull/10562))
-
-### Features / Enhancements
-
--   Feature: Upgrade underlying Docker image to Trixie [@stumpylog](https://github.com/stumpylog) ([#10562](https://github.com/paperless-ngx/paperless-ngx/pull/10562))
--   Fixhancement: more log viewer improvements [@shamoon](https://github.com/shamoon) ([#11426](https://github.com/paperless-ngx/paperless-ngx/pull/11426))
--   Performance: Replace duplicated static files with symlinks [@stumpylog](https://github.com/stumpylog) ([#11418](https://github.com/paperless-ngx/paperless-ngx/pull/11418))
--   Enhancement: add more relative dates, support modified [@shamoon](https://github.com/shamoon) ([#11411](https://github.com/paperless-ngx/paperless-ngx/pull/11411))
--   Performance: make move files after select custom field change async [@shamoon](https://github.com/shamoon) ([#11391](https://github.com/paperless-ngx/paperless-ngx/pull/11391))
--   Enhancement: Use a better check for the MariaDB server to be ready [@stumpylog](https://github.com/stumpylog) ([#11396](https://github.com/paperless-ngx/paperless-ngx/pull/11396))
--   Enhancement: speed-up docker container startup [@flrgh](https://github.com/flrgh) ([#11134](https://github.com/paperless-ngx/paperless-ngx/pull/11134))
-
-### Bug Fixes
-
--   Fix: prevent focus loss from change detection in cf query dropdown [@shamoon](https://github.com/shamoon) ([#11409](https://github.com/paperless-ngx/paperless-ngx/pull/11409))
--   Fix: sort editing filterable dropdowns sooner [@shamoon](https://github.com/shamoon) ([#11404](https://github.com/paperless-ngx/paperless-ngx/pull/11404))
--   Fix: support for custom field ordering w advanced search [@shamoon](https://github.com/shamoon) ([#11383](https://github.com/paperless-ngx/paperless-ngx/pull/11383))
-
-### Maintenance
-
--   Chore(deps): Bump the actions group with 7 updates @[dependabot[bot]](https://github.com/apps/dependabot) ([#11259](https://github.com/paperless-ngx/paperless-ngx/pull/11259))
-
-### Dependencies
-
-<details>
-<summary>16 changes</summary>
-
--   Chore: Upgrades psycopg to 3.2.12 [@stumpylog](https://github.com/stumpylog) ([#11420](https://github.com/paperless-ngx/paperless-ngx/pull/11420))
--   Chore(deps-dev): Bump glob from 10.4.1 to 10.5.0 in /src/paperless_mail/templates @[dependabot[bot]](https://github.com/apps/dependabot) ([#11413](https://github.com/paperless-ngx/paperless-ngx/pull/11413))
--   docker-compose(deps): bump gotenberg/gotenberg from 8.24 to 8.25 in /docker/compose @[dependabot[bot]](https://github.com/apps/dependabot) ([#11393](https://github.com/paperless-ngx/paperless-ngx/pull/11393))
--   Chore(deps): Bump the frontend-angular-dependencies group in /src-ui with 21 updates @[dependabot[bot]](https://github.com/apps/dependabot) ([#11260](https://github.com/paperless-ngx/paperless-ngx/pull/11260))
--   Chore(deps-dev): Bump @playwright/test from 1.55.1 to 1.56.1 in /src-ui @[dependabot[bot]](https://github.com/apps/dependabot) ([#11263](https://github.com/paperless-ngx/paperless-ngx/pull/11263))
--   Chore(deps-dev): Bump webpack from 5.102.0 to 5.102.1 in /src-ui @[dependabot[bot]](https://github.com/apps/dependabot) ([#11264](https://github.com/paperless-ngx/paperless-ngx/pull/11264))
--   Chore(deps-dev): Bump the frontend-eslint-dependencies group in /src-ui with 4 updates @[dependabot[bot]](https://github.com/apps/dependabot) ([#11262](https://github.com/paperless-ngx/paperless-ngx/pull/11262))
--   Chore(deps-dev): Bump jest-preset-angular from 15.0.2 to 15.0.3 in /src-ui in the frontend-jest-dependencies group @[dependabot[bot]](https://github.com/apps/dependabot) ([#11261](https://github.com/paperless-ngx/paperless-ngx/pull/11261))
--   Chore(deps-dev): Bump @types/node from 24.6.1 to 24.9.2 in /src-ui @[dependabot[bot]](https://github.com/apps/dependabot) ([#11265](https://github.com/paperless-ngx/paperless-ngx/pull/11265))
--   Chore(deps): Bump the small-changes group across 1 directory with 11 updates @[dependabot[bot]](https://github.com/apps/dependabot) ([#11337](https://github.com/paperless-ngx/paperless-ngx/pull/11337))
--   Chore(deps): Bump django-auditlog from 3.2.1 to 3.3.0 @[dependabot[bot]](https://github.com/apps/dependabot) ([#11021](https://github.com/paperless-ngx/paperless-ngx/pull/11021))
--   Chore(deps): Bump the actions group with 7 updates @[dependabot[bot]](https://github.com/apps/dependabot) ([#11259](https://github.com/paperless-ngx/paperless-ngx/pull/11259))
--   Chore(deps): Bump drf-spectacular-sidecar from 2025.9.1 to 2025.10.1 @[dependabot[bot]](https://github.com/apps/dependabot) ([#11019](https://github.com/paperless-ngx/paperless-ngx/pull/11019))
--   Chore(deps): Bump django-filter from 25.1 to 25.2 @[dependabot[bot]](https://github.com/apps/dependabot) ([#11020](https://github.com/paperless-ngx/paperless-ngx/pull/11020))
--   Chore(deps): Update django-allauth[mfa,socialaccount] requirement from ~=65.4.0 to ~=65.12.1 @[dependabot[bot]](https://github.com/apps/dependabot) ([#11198](https://github.com/paperless-ngx/paperless-ngx/pull/11198))
--   docker(deps): bump astral-sh/uv from 0.9.9-python3.12-bookworm-slim to 0.9.10-python3.12-bookworm-slim @[dependabot[bot]](https://github.com/apps/dependabot) ([#11394](https://github.com/paperless-ngx/paperless-ngx/pull/11394))
-</details>
-
-### All App Changes
-
-<details>
-<summary>19 changes</summary>
-
--   Fixhancement: more log viewer improvements [@shamoon](https://github.com/shamoon) ([#11426](https://github.com/paperless-ngx/paperless-ngx/pull/11426))
--   Chore: Upgrades psycopg to 3.2.12 [@stumpylog](https://github.com/stumpylog) ([#11420](https://github.com/paperless-ngx/paperless-ngx/pull/11420))
--   Enhancement: add more relative dates, support modified [@shamoon](https://github.com/shamoon) ([#11411](https://github.com/paperless-ngx/paperless-ngx/pull/11411))
--   Chore(deps-dev): Bump glob from 10.4.1 to 10.5.0 in /src/paperless_mail/templates @[dependabot[bot]](https://github.com/apps/dependabot) ([#11413](https://github.com/paperless-ngx/paperless-ngx/pull/11413))
--   Performance: make move files after select custom field change async [@shamoon](https://github.com/shamoon) ([#11391](https://github.com/paperless-ngx/paperless-ngx/pull/11391))
--   Fix: prevent focus loss from change detection in cf query dropdown [@shamoon](https://github.com/shamoon) ([#11409](https://github.com/paperless-ngx/paperless-ngx/pull/11409))
--   Fix: sort editing filterable dropdowns sooner [@shamoon](https://github.com/shamoon) ([#11404](https://github.com/paperless-ngx/paperless-ngx/pull/11404))
--   Chore(deps): Bump the frontend-angular-dependencies group in /src-ui with 21 updates @[dependabot[bot]](https://github.com/apps/dependabot) ([#11260](https://github.com/paperless-ngx/paperless-ngx/pull/11260))
--   Chore(deps-dev): Bump @playwright/test from 1.55.1 to 1.56.1 in /src-ui @[dependabot[bot]](https://github.com/apps/dependabot) ([#11263](https://github.com/paperless-ngx/paperless-ngx/pull/11263))
--   Chore(deps-dev): Bump webpack from 5.102.0 to 5.102.1 in /src-ui @[dependabot[bot]](https://github.com/apps/dependabot) ([#11264](https://github.com/paperless-ngx/paperless-ngx/pull/11264))
--   Chore(deps-dev): Bump the frontend-eslint-dependencies group in /src-ui with 4 updates @[dependabot[bot]](https://github.com/apps/dependabot) ([#11262](https://github.com/paperless-ngx/paperless-ngx/pull/11262))
--   Chore(deps-dev): Bump jest-preset-angular from 15.0.2 to 15.0.3 in /src-ui in the frontend-jest-dependencies group @[dependabot[bot]](https://github.com/apps/dependabot) ([#11261](https://github.com/paperless-ngx/paperless-ngx/pull/11261))
--   Chore(deps-dev): Bump @types/node from 24.6.1 to 24.9.2 in /src-ui @[dependabot[bot]](https://github.com/apps/dependabot) ([#11265](https://github.com/paperless-ngx/paperless-ngx/pull/11265))
--   Chore(deps): Bump the small-changes group across 1 directory with 11 updates @[dependabot[bot]](https://github.com/apps/dependabot) ([#11337](https://github.com/paperless-ngx/paperless-ngx/pull/11337))
--   Chore(deps): Bump django-auditlog from 3.2.1 to 3.3.0 @[dependabot[bot]](https://github.com/apps/dependabot) ([#11021](https://github.com/paperless-ngx/paperless-ngx/pull/11021))
--   Chore(deps): Bump drf-spectacular-sidecar from 2025.9.1 to 2025.10.1 @[dependabot[bot]](https://github.com/apps/dependabot) ([#11019](https://github.com/paperless-ngx/paperless-ngx/pull/11019))
--   Chore(deps): Bump django-filter from 25.1 to 25.2 @[dependabot[bot]](https://github.com/apps/dependabot) ([#11020](https://github.com/paperless-ngx/paperless-ngx/pull/11020))
--   Chore(deps): Update django-allauth[mfa,socialaccount] requirement from ~=65.4.0 to ~=65.12.1 @[dependabot[bot]](https://github.com/apps/dependabot) ([#11198](https://github.com/paperless-ngx/paperless-ngx/pull/11198))
--   Fix: support for custom field ordering w advanced search [@shamoon](https://github.com/shamoon) ([#11383](https://github.com/paperless-ngx/paperless-ngx/pull/11383))
-</details>
-
 ## paperless-ngx 2.19.6
 
 ### Bug Fixes

docs/configuration.md

@@ -1794,3 +1794,23 @@ 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.
+    -   _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

@@ -892,6 +892,21 @@ 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

@@ -1,6 +1,6 @@
 [project]
 name = "paperless-ngx"
-version = "2.20.0"
+version = "2.19.6"
 description = "A community-supported supercharged document management system: scan, index and archive all your physical documents"
 readme = "README.md"
 requires-python = ">=3.10"
@@ -16,6 +16,7 @@ classifiers = [
 # This will allow testing to not install a webserver, mysql, etc
 
 dependencies = [
+  "azure-ai-documentintelligence>=1.0.2",
   "babel>=2.17",
   "bleach~=6.3.0",
   "celery[redis]~=5.5.1",
@@ -45,7 +46,7 @@ dependencies = [
   "drf-writable-nested~=0.7.1",
   "filelock~=3.20.0",
   "flower~=2.0.1",
-  "gotenberg-client~=0.13.0",
+  "gotenberg-client~=0.12.0",
   "httpx-oauth~=0.16",
   "imap-tools~=1.11.0",
   "inotifyrecursive~=0.3",
@@ -80,7 +81,7 @@ optional-dependencies.postgres = [
   "psycopg[c,pool]==3.2.12",
   # Direct dependency for proper resolution of the pre-built wheels
   "psycopg-c==3.2.12",
-  "psycopg-pool==3.2.8",
+  "psycopg-pool==3.2.7",
 ]
 optional-dependencies.webserver = [
   "granian[uvloop]~=2.5.1",
@@ -115,7 +116,7 @@ testing = [
 ]
 
 lint = [
-  "pre-commit~=4.5.0",
+  "pre-commit~=4.4.0",
   "pre-commit-uv~=4.2.0",
   "ruff~=0.14.0",
 ]
@@ -252,6 +253,7 @@ testpaths = [
   "src/paperless_tesseract/tests/",
   "src/paperless_tika/tests",
   "src/paperless_text/tests/",
+  "src/paperless_remote/tests/",
 ]
 addopts = [
   "--pythonwarnings=all",

src-ui/package.json

@@ -1,6 +1,6 @@
 {
   "name": "paperless-ngx-ui",
-  "version": "2.20.0",
+  "version": "2.19.6",
   "scripts": {
     "preinstall": "npx only-allow pnpm",
     "ng": "ng",

src-ui/src/environments/environment.prod.ts

@@ -6,7 +6,7 @@ export const environment = {
   apiVersion: '9', // match src/paperless/settings.py
   appTitle: 'Paperless-ngx',
   tag: 'prod',
-  version: '2.20.0',
+  version: '2.19.6',
   webSocketHost: window.location.host,
   webSocketProtocol: window.location.protocol == 'https:' ? 'wss:' : 'ws:',
   webSocketBaseUrl: base_url.pathname + 'ws/',

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",
@@ -1401,3 +1402,10 @@ 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/version.py

@@ -1,6 +1,6 @@
 from typing import Final
 
-__version__: Final[tuple[int, int, int]] = (2, 20, 0)
+__version__: Final[tuple[int, int, int]] = (2, 19, 6)
 # Version string like X.Y.Z
 __full_version_str__: Final[str] = ".".join(map(str, __version__))
 # Version string like X.Y

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 +1,118 @@
+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),
+        )
+
+        try:
+            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)
+            return result.content
+        except Exception as e:
+            self.log.error(f"Azure AI Vision parsing failed: {e}")
+        finally:
+            client.close()
+
+        return None
+
+    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 +1,128 @@
+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."],
+            )
+
+    @mock.patch("azure.ai.documentintelligence.DocumentIntelligenceClient")
+    def test_get_text_with_azure_error_logged_and_returns_none(self, mock_client_cls):
+        mock_client = mock.Mock()
+        mock_client.begin_analyze_document.side_effect = RuntimeError("fail")
+        mock_client_cls.return_value = mock_client
+
+        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())
+            with mock.patch.object(parser.log, "error") as mock_log_error:
+                parser.parse(
+                    self.SAMPLE_FILES / "simple-digital.pdf",
+                    "application/pdf",
+                )
+
+        self.assertIsNone(parser.text)
+        mock_client.begin_analyze_document.assert_called_once()
+        mock_client.close.assert_called_once()
+        mock_log_error.assert_called_once()
+        self.assertIn(
+            "Azure AI Vision parsing failed",
+            mock_log_error.call_args[0][0],
+        )
+
+    @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/02/ff/1175b0b7371e46244032d43a56862d0af455823b5280a50c63d99cc50f18/automat-25.4.16-py3-none-any.whl", hash = "sha256:04e9bce696a8d5671ee698005af6e5a9fa15354140a87f4870744604dcdd3ba1", size = 42842, upload-time = "2025-04-16T20:12:14.447Z" },
 ]
 
+[[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"
@@ -331,15 +359,15 @@ wheels = [
 
 [[package]]
 name = "channels"
-version = "4.3.2"
+version = "4.3.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "asgiref", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "django", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/74/92/b18d4bb54d14986a8b35215a1c9e6a7f9f4d57ca63ac9aee8290ebb4957d/channels-4.3.2.tar.gz", hash = "sha256:f2bb6bfb73ad7fb4705041d07613c7b4e69528f01ef8cb9fb6c21d9295f15667", size = 27023, upload-time = "2025-11-20T15:13:05.102Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/12/a0/46450fcf9e56af18a6b0440ba49db6635419bb7bc84142c35f4143b1a66c/channels-4.3.1.tar.gz", hash = "sha256:97413ffd674542db08e16a9ef09cd86ec0113e5f8125fbd33cf0854adcf27cdb", size = 26896, upload-time = "2025-08-01T13:25:19.952Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/16/34/c32915288b7ef482377b6adc401192f98c6a99b3a145423d3b8aed807898/channels-4.3.2-py3-none-any.whl", hash = "sha256:fef47e9055a603900cf16cef85f050d522d9ac4b3daccf24835bd9580705c176", size = 31313, upload-time = "2025-11-20T15:13:02.357Z" },
+    { url = "https://files.pythonhosted.org/packages/89/1c/eae1c2a8c195760376e7f65d0bdcc3e966695d29cfbe5c54841ce5c71408/channels-4.3.1-py3-none-any.whl", hash = "sha256:b091d4b26f91d807de3e84aead7ba785314f27eaf5bac31dd51b1c956b883859", size = 31286, upload-time = "2025-08-01T13:25:18.845Z" },
 ]
 
 [[package]]
@@ -1073,15 +1101,15 @@ wheels = [
 
 [[package]]
 name = "gotenberg-client"
-version = "0.13.0"
+version = "0.12.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "httpx", extra = ["http2"], marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "typing-extensions", marker = "(python_full_version < '3.11' and sys_platform == 'darwin') or (python_full_version < '3.11' and sys_platform == 'linux')" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/ef/ad/a8ae34ad79918ee2691498e36882a8275603362316be1a57f26911f01d87/gotenberg_client-0.13.0.tar.gz", hash = "sha256:0fb2425d0e1e4f143285ecde90f7687f4d234d2b23316f5d42015337d336a4ab", size = 1211055, upload-time = "2025-11-18T16:15:33.735Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/61/6d/07ea213c146bbe91dffebff2d8f4dc61e7076d3dd34d4fd1467f9163e752/gotenberg_client-0.12.0.tar.gz", hash = "sha256:1ab50878024469fc003c414ee9810ceeb00d4d7d7c36bd2fb75318fbff139e9b", size = 1210884, upload-time = "2025-10-15T15:32:37.669Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/ce/7b/8b301f097027403d9b66fad83e2fd5a5b2bcccb592832473db895671a0ee/gotenberg_client-0.13.0-py3-none-any.whl", hash = "sha256:e787ee39d1d222629b2e2e153402853e84a1a76758b261859b0c81384cdec4e5", size = 51054, upload-time = "2025-11-18T16:15:32.294Z" },
+    { url = "https://files.pythonhosted.org/packages/12/39/fcb24ff053b1be7e5124f56c3d358706a23a328f685c6db33bc9dbc5472d/gotenberg_client-0.12.0-py3-none-any.whl", hash = "sha256:a540b35ac518e902c2860a88fbe448c15fe5a56fe8ec8604e6a2c8c2228fd0cb", size = 51051, upload-time = "2025-10-15T15:32:36.32Z" },
 ]
 
 [[package]]
@@ -1451,6 +1479,15 @@ 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"
@@ -2115,9 +2152,10 @@ wheels = [
 
 [[package]]
 name = "paperless-ngx"
-version = "2.20.0"
+version = "2.19.6"
 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'" },
@@ -2254,6 +2292,7 @@ typing = [
 
 [package.metadata]
 requires-dist = [
+    { name = "azure-ai-documentintelligence", specifier = ">=1.0.2" },
     { name = "babel", specifier = ">=2.17" },
     { name = "bleach", specifier = "~=6.3.0" },
     { name = "celery", extras = ["redis"], specifier = "~=5.5.1" },
@@ -2281,7 +2320,7 @@ requires-dist = [
     { name = "drf-writable-nested", specifier = "~=0.7.1" },
     { name = "filelock", specifier = "~=3.20.0" },
     { name = "flower", specifier = "~=2.0.1" },
-    { name = "gotenberg-client", specifier = "~=0.13.0" },
+    { name = "gotenberg-client", specifier = "~=0.12.0" },
     { name = "granian", extras = ["uvloop"], marker = "extra == 'webserver'", specifier = "~=2.5.1" },
     { name = "httpx-oauth", specifier = "~=0.16" },
     { name = "imap-tools", specifier = "~=1.11.0" },
@@ -2297,7 +2336,7 @@ requires-dist = [
     { 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-bookworm-3.2.12/psycopg_c-3.2.12-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-bookworm-3.2.12/psycopg_c-3.2.12-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 = "==3.2.12" },
-    { name = "psycopg-pool", marker = "extra == 'postgres'", specifier = "==3.2.8" },
+    { name = "psycopg-pool", marker = "extra == 'postgres'", specifier = "==3.2.7" },
     { name = "python-dateutil", specifier = "~=2.9.0" },
     { name = "python-dotenv", specifier = "~=1.2.1" },
     { name = "python-gnupg", specifier = "~=0.5.4" },
@@ -2326,7 +2365,7 @@ dev = [
     { name = "imagehash" },
     { name = "mkdocs-glightbox", specifier = "~=0.5.1" },
     { name = "mkdocs-material", specifier = "~=9.7.0" },
-    { name = "pre-commit", specifier = "~=4.5.0" },
+    { name = "pre-commit", specifier = "~=4.4.0" },
     { name = "pre-commit-uv", specifier = "~=4.2.0" },
     { name = "pytest", specifier = "~=8.4.1" },
     { name = "pytest-cov", specifier = "~=7.0.0" },
@@ -2344,7 +2383,7 @@ docs = [
     { name = "mkdocs-material", specifier = "~=9.7.0" },
 ]
 lint = [
-    { name = "pre-commit", specifier = "~=4.5.0" },
+    { name = "pre-commit", specifier = "~=4.4.0" },
     { name = "pre-commit-uv", specifier = "~=4.2.0" },
     { name = "ruff", specifier = "~=0.14.0" },
 ]
@@ -2625,7 +2664,7 @@ wheels = [
 
 [[package]]
 name = "pre-commit"
-version = "4.5.0"
+version = "4.4.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "cfgv", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
@@ -2634,9 +2673,9 @@ dependencies = [
     { name = "pyyaml", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "virtualenv", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/f4/9b/6a4ffb4ed980519da959e1cf3122fc6cb41211daa58dbae1c73c0e519a37/pre_commit-4.5.0.tar.gz", hash = "sha256:dc5a065e932b19fc1d4c653c6939068fe54325af8e741e74e88db4d28a4dd66b", size = 198428, upload-time = "2025-11-22T21:02:42.304Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/a6/49/7845c2d7bf6474efd8e27905b51b11e6ce411708c91e829b93f324de9929/pre_commit-4.4.0.tar.gz", hash = "sha256:f0233ebab440e9f17cabbb558706eb173d19ace965c68cdce2c081042b4fab15", size = 197501, upload-time = "2025-11-08T21:12:11.607Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/5d/c4/b2d28e9d2edf4f1713eb3c29307f1a63f3d67cf09bdda29715a36a68921a/pre_commit-4.5.0-py2.py3-none-any.whl", hash = "sha256:25e2ce09595174d9c97860a95609f9f852c0614ba602de3561e267547f2335e1", size = 226429, upload-time = "2025-11-22T21:02:40.836Z" },
+    { url = "https://files.pythonhosted.org/packages/27/11/574fe7d13acf30bfd0a8dd7fa1647040f2b8064f13f43e8c963b1e65093b/pre_commit-4.4.0-py2.py3-none-any.whl", hash = "sha256:b35ea52957cbf83dcc5d8ee636cbead8624e3a15fbfa61a370e42158ac8a5813", size = 226049, upload-time = "2025-11-08T21:12:10.228Z" },
 ]
 
 [[package]]
@@ -2731,14 +2770,14 @@ wheels = [
 
 [[package]]
 name = "psycopg-pool"
-version = "3.2.8"
+version = "3.2.7"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "typing-extensions", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/b7/20/10064379ed363b7a2a6da3aca986a668c792a8145d7344854ab14c7d7292/psycopg_pool-3.2.8.tar.gz", hash = "sha256:854e17c2a637c3b9f8d8b24faad57d4cf850baf3fc03ca56ef7e5b4998e391b9", size = 29956, upload-time = "2025-11-21T22:34:35.453Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/9d/8f/3ec52b17087c2ed5fa32b64fd4814dde964c9aa4bd49d0d30fc24725ca6d/psycopg_pool-3.2.7.tar.gz", hash = "sha256:a77d531bfca238e49e5fb5832d65b98e69f2c62bfda3d2d4d833696bdc9ca54b", size = 29765, upload-time = "2025-10-26T00:46:10.379Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/e3/5f/947b4b4e51d67c4c9e97626c815caa9b241a62fd66ddd0d00a4a572013f5/psycopg_pool-3.2.8-py3-none-any.whl", hash = "sha256:5474137f3a58e697e0141d0311e70ec067fc4466031496d7f9ef3e2c28a1dc09", size = 38507, upload-time = "2025-11-21T22:34:31Z" },
+    { url = "https://files.pythonhosted.org/packages/e7/59/74e752f605c6f0e351d4cf1c54fb9a1616dc800db4572b95bbfbb1a6225f/psycopg_pool-3.2.7-py3-none-any.whl", hash = "sha256:4b47bb59d887ef5da522eb63746b9f70e2faf967d34aac4f56ffc65e9606728f", size = 38232, upload-time = "2025-10-26T00:46:00.496Z" },
 ]
 
 [[package]]