Bump ocrmypdf from 16.13.0 to 17.3.0 in the document-processing group

Bumps the document-processing group with 1 update: [ocrmypdf](https://github.com/ocrmypdf/OCRmyPDF). Updates `ocrmypdf` from 16.13.0 to 17.3.0 - [Release notes](https://github.com/ocrmypdf/OCRmyPDF/releases) - [Commits](https://github.com/ocrmypdf/OCRmyPDF/compare/v16.13.0...v17.3.0) --- updated-dependencies: - dependency-name: ocrmypdf dependency-version: 17.3.0 dependency-type: direct:production update-type: version-update:semver-major dependency-group: document-processing ... Signed-off-by: dependabot[bot] <support@github.com>
2026-03-07 09:41:22 +00:00 · 2026-03-06 20:16:28 +00:00
16 changed files with 493 additions and 424 deletions
--- a/.github/workflows/ci-docker.yml
+++ b/.github/workflows/ci-docker.yml
@@ -149,16 +149,15 @@ jobs:
          mkdir -p /tmp/digests
          digest="${{ steps.build.outputs.digest }}"
          echo "digest=${digest}"
-          echo "${digest}" > "/tmp/digests/digest-${{ matrix.arch }}.txt"
+          touch "/tmp/digests/${digest#sha256:}"
      - name: Upload digest
        if: steps.check-push.outputs.should-push == 'true'
        uses: actions/upload-artifact@v7.0.0
        with:
          name: digests-${{ matrix.arch }}
-          path: /tmp/digests/digest-${{ matrix.arch }}.txt
+          path: /tmp/digests/*
          if-no-files-found: error
          retention-days: 1
-          archive: false
  merge-and-push:
    name: Merge and Push Manifest
    runs-on: ubuntu-24.04
@@ -172,7 +171,7 @@ jobs:
        uses: actions/download-artifact@v8.0.0
        with:
          path: /tmp/digests
-          pattern: digest-*.txt
+          pattern: digests-*
          merge-multiple: true
      - name: List digests
        run: |
@@ -218,9 +217,8 @@ jobs:
          tags=$(jq -cr '.tags | map("-t " + .) | join(" ")' <<< "${DOCKER_METADATA_OUTPUT_JSON}")

          digests=""
-          for digest_file in digest-*.txt; do
-            digest=$(cat "${digest_file}")
-            digests+="${{ env.REGISTRY }}/${REPOSITORY}@${digest} "
+          for digest in *; do
+            digests+="${{ env.REGISTRY }}/${REPOSITORY}@sha256:${digest} "
          done

          echo "Creating manifest with tags: ${tags}"
--- a/.github/workflows/pr-bot.yml
+++ b/.github/workflows/pr-bot.yml
@@ -2,24 +2,13 @@ name: PR Bot
 on:
  pull_request_target:
    types: [opened]
+permissions:
+  contents: read
+  pull-requests: write
 jobs:
-  anti-slop:
-    runs-on: ubuntu-latest
-    permissions:
-      contents: read
-      issues: read
-      pull-requests: write
-    steps:
-      - uses: peakoss/anti-slop@v0.2.1
-        with:
-          max-failures: 4
-          failure-add-pr-labels: 'ai'
  pr-bot:
    name: Automated PR Bot
    runs-on: ubuntu-latest
-    permissions:
-      contents: read
-      pull-requests: write
    steps:
      - name: Label PR by file path or branch name
        # see .github/labeler.yml for the labeler config
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -59,7 +59,7 @@ dependencies = [
  "llama-index-llms-openai>=0.6.13",
  "llama-index-vector-stores-faiss>=0.5.2",
  "nltk~=3.9.1",
-  "ocrmypdf~=16.13.0",
+  "ocrmypdf~=17.3.0",
  "openai>=1.76",
  "pathvalidate~=3.3.1",
  "pdf2image~=1.17.0",
--- a/src/paperless/tests/test_adapter.py
+++ b/src/paperless/tests/test_adapter.py
@@ -1,100 +1,107 @@
-import logging
+from unittest import mock

-import pytest
 from allauth.account.adapter import get_adapter
 from allauth.core import context
 from allauth.socialaccount.adapter import get_adapter as get_social_adapter
+from django.conf import settings
 from django.contrib.auth.models import AnonymousUser
 from django.contrib.auth.models import Group
 from django.contrib.auth.models import User
 from django.forms import ValidationError
 from django.http import HttpRequest
+from django.test import TestCase
+from django.test import override_settings
 from django.urls import reverse
-from pytest_django.fixtures import SettingsWrapper
-from pytest_mock import MockerFixture
 from rest_framework.authtoken.models import Token

 from paperless.adapter import DrfTokenStrategy


-@pytest.mark.django_db
-class TestCustomAccountAdapter:
-    def test_is_open_for_signup(self, settings: SettingsWrapper) -> None:
+class TestCustomAccountAdapter(TestCase):
+    def test_is_open_for_signup(self) -> None:
        adapter = get_adapter()

        # With no accounts, signups should be allowed
-        assert adapter.is_open_for_signup(None)
+        self.assertTrue(adapter.is_open_for_signup(None))

        User.objects.create_user("testuser")

+        # Test when ACCOUNT_ALLOW_SIGNUPS is True
        settings.ACCOUNT_ALLOW_SIGNUPS = True
-        assert adapter.is_open_for_signup(None)
+        self.assertTrue(adapter.is_open_for_signup(None))

+        # Test when ACCOUNT_ALLOW_SIGNUPS is False
        settings.ACCOUNT_ALLOW_SIGNUPS = False
-        assert not adapter.is_open_for_signup(None)
+        self.assertFalse(adapter.is_open_for_signup(None))

-    def test_is_safe_url(self, settings: SettingsWrapper) -> None:
+    def test_is_safe_url(self) -> None:
        request = HttpRequest()
-        request.get_host = lambda: "example.com"
+        request.get_host = mock.Mock(return_value="example.com")
        with context.request_context(request):
            adapter = get_adapter()
+            with override_settings(ALLOWED_HOSTS=["*"]):
+                # True because request host is same
+                url = "https://example.com"
+                self.assertTrue(adapter.is_safe_url(url))

-            settings.ALLOWED_HOSTS = ["*"]
-            # True because request host is same
-            assert adapter.is_safe_url("https://example.com")
+            url = "https://evil.com"
            # False despite wildcard because request host is different
-            assert not adapter.is_safe_url("https://evil.com")
+            self.assertFalse(adapter.is_safe_url(url))

            settings.ALLOWED_HOSTS = ["example.com"]
+            url = "https://example.com"
            # True because request host is same
-            assert adapter.is_safe_url("https://example.com")
+            self.assertTrue(adapter.is_safe_url(url))

            settings.ALLOWED_HOSTS = ["*", "example.com"]
+            url = "//evil.com"
            # False because request host is not in allowed hosts
-            assert not adapter.is_safe_url("//evil.com")
+            self.assertFalse(adapter.is_safe_url(url))

-    def test_pre_authenticate(
-        self,
-        settings: SettingsWrapper,
-        mocker: MockerFixture,
-    ) -> None:
-        mocker.patch("allauth.core.internal.ratelimit.consume", return_value=True)
+    @mock.patch("allauth.core.internal.ratelimit.consume", return_value=True)
+    def test_pre_authenticate(self, mock_consume) -> None:
        adapter = get_adapter()
        request = HttpRequest()
-        request.get_host = lambda: "example.com"
+        request.get_host = mock.Mock(return_value="example.com")

        settings.DISABLE_REGULAR_LOGIN = False
        adapter.pre_authenticate(request)

        settings.DISABLE_REGULAR_LOGIN = True
-        with pytest.raises(ValidationError):
+        with self.assertRaises(ValidationError):
            adapter.pre_authenticate(request)

-    def test_get_reset_password_from_key_url(self, settings: SettingsWrapper) -> None:
+    def test_get_reset_password_from_key_url(self) -> None:
        request = HttpRequest()
-        request.get_host = lambda: "foo.org"
+        request.get_host = mock.Mock(return_value="foo.org")
        with context.request_context(request):
            adapter = get_adapter()

-            settings.PAPERLESS_URL = None
-            settings.ACCOUNT_DEFAULT_HTTP_PROTOCOL = "https"
-            expected_url = f"https://foo.org{reverse('account_reset_password_from_key', kwargs={'uidb36': 'UID', 'key': 'KEY'})}"
-            assert adapter.get_reset_password_from_key_url("UID-KEY") == expected_url
+            # Test when PAPERLESS_URL is None
+            with override_settings(
+                PAPERLESS_URL=None,
+                ACCOUNT_DEFAULT_HTTP_PROTOCOL="https",
+            ):
+                expected_url = f"https://foo.org{reverse('account_reset_password_from_key', kwargs={'uidb36': 'UID', 'key': 'KEY'})}"
+                self.assertEqual(
+                    adapter.get_reset_password_from_key_url("UID-KEY"),
+                    expected_url,
+                )

-            settings.PAPERLESS_URL = "https://bar.com"
-            expected_url = f"https://bar.com{reverse('account_reset_password_from_key', kwargs={'uidb36': 'UID', 'key': 'KEY'})}"
-            assert adapter.get_reset_password_from_key_url("UID-KEY") == expected_url
+            # Test when PAPERLESS_URL is not None
+            with override_settings(PAPERLESS_URL="https://bar.com"):
+                expected_url = f"https://bar.com{reverse('account_reset_password_from_key', kwargs={'uidb36': 'UID', 'key': 'KEY'})}"
+                self.assertEqual(
+                    adapter.get_reset_password_from_key_url("UID-KEY"),
+                    expected_url,
+                )

-    def test_save_user_adds_groups(
-        self,
-        settings: SettingsWrapper,
-        mocker: MockerFixture,
-    ) -> None:
-        settings.ACCOUNT_DEFAULT_GROUPS = ["group1", "group2"]
+    @override_settings(ACCOUNT_DEFAULT_GROUPS=["group1", "group2"])
+    def test_save_user_adds_groups(self) -> None:
        Group.objects.create(name="group1")
        user = User.objects.create_user("testuser")
        adapter = get_adapter()
-        form = mocker.MagicMock(
+        form = mock.Mock(
            cleaned_data={
                "username": "testuser",
                "email": "user@example.com",
@@ -103,81 +110,88 @@ class TestCustomAccountAdapter:

        user = adapter.save_user(HttpRequest(), user, form, commit=True)

-        assert user.groups.count() == 1
-        assert user.groups.filter(name="group1").exists()
-        assert not user.groups.filter(name="group2").exists()
+        self.assertEqual(user.groups.count(), 1)
+        self.assertTrue(user.groups.filter(name="group1").exists())
+        self.assertFalse(user.groups.filter(name="group2").exists())

-    def test_fresh_install_save_creates_superuser(self, mocker: MockerFixture) -> None:
+    def test_fresh_install_save_creates_superuser(self) -> None:
        adapter = get_adapter()
-        form = mocker.MagicMock(
+        form = mock.Mock(
            cleaned_data={
                "username": "testuser",
                "email": "user@paperless-ngx.com",
            },
        )
        user = adapter.save_user(HttpRequest(), User(), form, commit=True)
-        assert user.is_superuser
+        self.assertTrue(user.is_superuser)

-        form = mocker.MagicMock(
+        # Next time, it should not create a superuser
+        form = mock.Mock(
            cleaned_data={
                "username": "testuser2",
                "email": "user2@paperless-ngx.com",
            },
        )
        user2 = adapter.save_user(HttpRequest(), User(), form, commit=True)
-        assert not user2.is_superuser
+        self.assertFalse(user2.is_superuser)


-class TestCustomSocialAccountAdapter:
-    @pytest.mark.django_db
-    def test_is_open_for_signup(self, settings: SettingsWrapper) -> None:
+class TestCustomSocialAccountAdapter(TestCase):
+    def test_is_open_for_signup(self) -> None:
        adapter = get_social_adapter()

+        # Test when SOCIALACCOUNT_ALLOW_SIGNUPS is True
        settings.SOCIALACCOUNT_ALLOW_SIGNUPS = True
-        assert adapter.is_open_for_signup(None, None)
+        self.assertTrue(adapter.is_open_for_signup(None, None))

+        # Test when SOCIALACCOUNT_ALLOW_SIGNUPS is False
        settings.SOCIALACCOUNT_ALLOW_SIGNUPS = False
-        assert not adapter.is_open_for_signup(None, None)
+        self.assertFalse(adapter.is_open_for_signup(None, None))

    def test_get_connect_redirect_url(self) -> None:
        adapter = get_social_adapter()
-        assert adapter.get_connect_redirect_url(None, None) == reverse("base")
+        request = None
+        socialaccount = None

-    @pytest.mark.django_db
-    def test_save_user_adds_groups(
-        self,
-        settings: SettingsWrapper,
-        mocker: MockerFixture,
-    ) -> None:
-        settings.SOCIAL_ACCOUNT_DEFAULT_GROUPS = ["group1", "group2"]
+        # Test the default URL
+        expected_url = reverse("base")
+        self.assertEqual(
+            adapter.get_connect_redirect_url(request, socialaccount),
+            expected_url,
+        )
+
+    @override_settings(SOCIAL_ACCOUNT_DEFAULT_GROUPS=["group1", "group2"])
+    def test_save_user_adds_groups(self) -> None:
        Group.objects.create(name="group1")
        adapter = get_social_adapter()
+        request = HttpRequest()
        user = User.objects.create_user("testuser")
-        sociallogin = mocker.MagicMock(user=user)
+        sociallogin = mock.Mock(
+            user=user,
+        )

-        user = adapter.save_user(HttpRequest(), sociallogin, None)
+        user = adapter.save_user(request, sociallogin, None)

-        assert user.groups.count() == 1
-        assert user.groups.filter(name="group1").exists()
-        assert not user.groups.filter(name="group2").exists()
+        self.assertEqual(user.groups.count(), 1)
+        self.assertTrue(user.groups.filter(name="group1").exists())
+        self.assertFalse(user.groups.filter(name="group2").exists())

-    def test_error_logged_on_authentication_error(
-        self,
-        caplog: pytest.LogCaptureFixture,
-    ) -> None:
+    def test_error_logged_on_authentication_error(self) -> None:
        adapter = get_social_adapter()
-        with caplog.at_level(logging.INFO, logger="paperless.auth"):
+        request = HttpRequest()
+        with self.assertLogs("paperless.auth", level="INFO") as log_cm:
            adapter.on_authentication_error(
-                HttpRequest(),
+                request,
                provider="test-provider",
                error="Error",
                exception="Test authentication error",
            )
-        assert any("Test authentication error" in msg for msg in caplog.messages)
+        self.assertTrue(
+            any("Test authentication error" in message for message in log_cm.output),
+        )


-@pytest.mark.django_db
-class TestDrfTokenStrategy:
+class TestDrfTokenStrategy(TestCase):
    def test_create_access_token_creates_new_token(self) -> None:
        """
        GIVEN:
@@ -187,6 +201,7 @@ class TestDrfTokenStrategy:
        THEN:
            - A new token is created and its key is returned
        """
+
        user = User.objects.create_user("testuser")
        request = HttpRequest()
        request.user = user
@@ -194,9 +209,13 @@ class TestDrfTokenStrategy:
        strategy = DrfTokenStrategy()
        token_key = strategy.create_access_token(request)

-        assert token_key is not None
-        assert Token.objects.filter(user=user).exists()
-        assert token_key == Token.objects.get(user=user).key
+        # Verify a token was created
+        self.assertIsNotNone(token_key)
+        self.assertTrue(Token.objects.filter(user=user).exists())
+
+        # Verify the returned key matches the created token
+        token = Token.objects.get(user=user)
+        self.assertEqual(token_key, token.key)

    def test_create_access_token_returns_existing_token(self) -> None:
        """
@@ -207,6 +226,7 @@ class TestDrfTokenStrategy:
        THEN:
            - The same token key is returned (no new token created)
        """
+
        user = User.objects.create_user("testuser")
        existing_token = Token.objects.create(user=user)

@@ -216,8 +236,11 @@ class TestDrfTokenStrategy:
        strategy = DrfTokenStrategy()
        token_key = strategy.create_access_token(request)

-        assert token_key == existing_token.key
-        assert Token.objects.filter(user=user).count() == 1
+        # Verify the existing token key is returned
+        self.assertEqual(token_key, existing_token.key)
+
+        # Verify only one token exists (no duplicate created)
+        self.assertEqual(Token.objects.filter(user=user).count(), 1)

    def test_create_access_token_returns_none_for_unauthenticated_user(self) -> None:
        """
@@ -228,11 +251,12 @@ class TestDrfTokenStrategy:
        THEN:
            - None is returned and no token is created
        """
+
        request = HttpRequest()
        request.user = AnonymousUser()

        strategy = DrfTokenStrategy()
        token_key = strategy.create_access_token(request)

-        assert token_key is None
-        assert Token.objects.count() == 0
+        self.assertIsNone(token_key)
+        self.assertEqual(Token.objects.count(), 0)
--- a/src/paperless/tests/test_checks.py
+++ b/src/paperless/tests/test_checks.py
@@ -1,15 +1,16 @@
 import os
-from collections.abc import Callable
-from dataclasses import dataclass
 from pathlib import Path
 from unittest import mock

 import pytest
 from django.core.checks import Error
 from django.core.checks import Warning
-from pytest_django.fixtures import SettingsWrapper
+from django.test import TestCase
+from django.test import override_settings
 from pytest_mock import MockerFixture

+from documents.tests.utils import DirectoriesMixin
+from documents.tests.utils import FileSystemAssertsMixin
 from paperless.checks import audit_log_check
 from paperless.checks import binaries_check
 from paperless.checks import check_deprecated_db_settings
@@ -19,84 +20,54 @@ from paperless.checks import paths_check
 from paperless.checks import settings_values_check


-@dataclass(frozen=True, slots=True)
-class PaperlessTestDirs:
-    data_dir: Path
-    media_dir: Path
-    consumption_dir: Path
-
-
-# TODO: consolidate with documents/tests/conftest.py PaperlessDirs/paperless_dirs
-#       once the paperless and documents test suites are ready to share fixtures.
-@pytest.fixture()
-def directories(tmp_path: Path, settings: SettingsWrapper) -> PaperlessTestDirs:
-    data_dir = tmp_path / "data"
-    media_dir = tmp_path / "media"
-    consumption_dir = tmp_path / "consumption"
-
-    for d in (data_dir, media_dir, consumption_dir):
-        d.mkdir()
-
-    settings.DATA_DIR = data_dir
-    settings.MEDIA_ROOT = media_dir
-    settings.CONSUMPTION_DIR = consumption_dir
-
-    return PaperlessTestDirs(
-        data_dir=data_dir,
-        media_dir=media_dir,
-        consumption_dir=consumption_dir,
-    )
-
-
-class TestChecks:
+class TestChecks(DirectoriesMixin, TestCase):
    def test_binaries(self) -> None:
-        assert binaries_check(None) == []
+        self.assertEqual(binaries_check(None), [])

-    def test_binaries_fail(self, settings: SettingsWrapper) -> None:
-        settings.CONVERT_BINARY = "uuuhh"
-        assert len(binaries_check(None)) == 1
+    @override_settings(CONVERT_BINARY="uuuhh")
+    def test_binaries_fail(self) -> None:
+        self.assertEqual(len(binaries_check(None)), 1)

-    @pytest.mark.usefixtures("directories")
    def test_paths_check(self) -> None:
-        assert paths_check(None) == []
+        self.assertEqual(paths_check(None), [])

-    def test_paths_check_dont_exist(self, settings: SettingsWrapper) -> None:
-        settings.MEDIA_ROOT = Path("uuh")
-        settings.DATA_DIR = Path("whatever")
-        settings.CONSUMPTION_DIR = Path("idontcare")
+    @override_settings(
+        MEDIA_ROOT=Path("uuh"),
+        DATA_DIR=Path("whatever"),
+        CONSUMPTION_DIR=Path("idontcare"),
+    )
+    def test_paths_check_dont_exist(self) -> None:
+        msgs = paths_check(None)
+        self.assertEqual(len(msgs), 3, str(msgs))
+
+        for msg in msgs:
+            self.assertTrue(msg.msg.endswith("is set but doesn't exist."))
+
+    def test_paths_check_no_access(self) -> None:
+        Path(self.dirs.data_dir).chmod(0o000)
+        Path(self.dirs.media_dir).chmod(0o000)
+        Path(self.dirs.consumption_dir).chmod(0o000)
+
+        self.addCleanup(os.chmod, self.dirs.data_dir, 0o777)
+        self.addCleanup(os.chmod, self.dirs.media_dir, 0o777)
+        self.addCleanup(os.chmod, self.dirs.consumption_dir, 0o777)

        msgs = paths_check(None)
+        self.assertEqual(len(msgs), 3)

-        assert len(msgs) == 3, str(msgs)
        for msg in msgs:
-            assert msg.msg.endswith("is set but doesn't exist.")
+            self.assertTrue(msg.msg.endswith("is not writeable"))

-    def test_paths_check_no_access(self, directories: PaperlessTestDirs) -> None:
-        directories.data_dir.chmod(0o000)
-        directories.media_dir.chmod(0o000)
-        directories.consumption_dir.chmod(0o000)
+    @override_settings(DEBUG=False)
+    def test_debug_disabled(self) -> None:
+        self.assertEqual(debug_mode_check(None), [])

-        try:
-            msgs = paths_check(None)
-        finally:
-            directories.data_dir.chmod(0o777)
-            directories.media_dir.chmod(0o777)
-            directories.consumption_dir.chmod(0o777)
-
-        assert len(msgs) == 3
-        for msg in msgs:
-            assert msg.msg.endswith("is not writeable")
-
-    def test_debug_disabled(self, settings: SettingsWrapper) -> None:
-        settings.DEBUG = False
-        assert debug_mode_check(None) == []
-
-    def test_debug_enabled(self, settings: SettingsWrapper) -> None:
-        settings.DEBUG = True
-        assert len(debug_mode_check(None)) == 1
+    @override_settings(DEBUG=True)
+    def test_debug_enabled(self) -> None:
+        self.assertEqual(len(debug_mode_check(None)), 1)


-class TestSettingsChecksAgainstDefaults:
+class TestSettingsChecksAgainstDefaults(DirectoriesMixin, TestCase):
    def test_all_valid(self) -> None:
        """
        GIVEN:
@@ -107,71 +78,104 @@ class TestSettingsChecksAgainstDefaults:
            - No system check errors reported
        """
        msgs = settings_values_check(None)
-        assert len(msgs) == 0
+        self.assertEqual(len(msgs), 0)


-class TestOcrSettingsChecks:
-    @pytest.mark.parametrize(
-        ("setting", "value", "expected_msg"),
-        [
-            pytest.param(
-                "OCR_OUTPUT_TYPE",
-                "notapdf",
-                'OCR output type "notapdf"',
-                id="invalid-output-type",
-            ),
-            pytest.param(
-                "OCR_MODE",
-                "makeitso",
-                'OCR output mode "makeitso"',
-                id="invalid-mode",
-            ),
-            pytest.param(
-                "OCR_MODE",
-                "skip_noarchive",
-                "deprecated",
-                id="deprecated-mode",
-            ),
-            pytest.param(
-                "OCR_SKIP_ARCHIVE_FILE",
-                "invalid",
-                'OCR_SKIP_ARCHIVE_FILE setting "invalid"',
-                id="invalid-skip-archive-file",
-            ),
-            pytest.param(
-                "OCR_CLEAN",
-                "cleanme",
-                'OCR clean mode "cleanme"',
-                id="invalid-clean",
-            ),
-        ],
-    )
-    def test_invalid_setting_produces_one_error(
-        self,
-        settings: SettingsWrapper,
-        setting: str,
-        value: str,
-        expected_msg: str,
-    ) -> None:
+class TestOcrSettingsChecks(DirectoriesMixin, TestCase):
+    @override_settings(OCR_OUTPUT_TYPE="notapdf")
+    def test_invalid_output_type(self) -> None:
        """
        GIVEN:
            - Default settings
-            - One OCR setting is set to an invalid value
+            - OCR output type is invalid
        WHEN:
            - Settings are validated
        THEN:
-            - Exactly one system check error is reported containing the expected message
+            - system check error reported for OCR output type
        """
-        setattr(settings, setting, value)
-
        msgs = settings_values_check(None)
+        self.assertEqual(len(msgs), 1)

-        assert len(msgs) == 1
-        assert expected_msg in msgs[0].msg
+        msg = msgs[0]
+
+        self.assertIn('OCR output type "notapdf"', msg.msg)
+
+    @override_settings(OCR_MODE="makeitso")
+    def test_invalid_ocr_type(self) -> None:
+        """
+        GIVEN:
+            - Default settings
+            - OCR type is invalid
+        WHEN:
+            - Settings are validated
+        THEN:
+            - system check error reported for OCR type
+        """
+        msgs = settings_values_check(None)
+        self.assertEqual(len(msgs), 1)
+
+        msg = msgs[0]
+
+        self.assertIn('OCR output mode "makeitso"', msg.msg)
+
+    @override_settings(OCR_MODE="skip_noarchive")
+    def test_deprecated_ocr_type(self) -> None:
+        """
+        GIVEN:
+            - Default settings
+            - OCR type is deprecated
+        WHEN:
+            - Settings are validated
+        THEN:
+            - deprecation warning reported for OCR type
+        """
+        msgs = settings_values_check(None)
+        self.assertEqual(len(msgs), 1)
+
+        msg = msgs[0]
+
+        self.assertIn("deprecated", msg.msg)
+
+    @override_settings(OCR_SKIP_ARCHIVE_FILE="invalid")
+    def test_invalid_ocr_skip_archive_file(self) -> None:
+        """
+        GIVEN:
+            - Default settings
+            - OCR_SKIP_ARCHIVE_FILE is invalid
+        WHEN:
+            - Settings are validated
+        THEN:
+            - system check error reported for OCR_SKIP_ARCHIVE_FILE
+        """
+        msgs = settings_values_check(None)
+        self.assertEqual(len(msgs), 1)
+
+        msg = msgs[0]
+
+        self.assertIn('OCR_SKIP_ARCHIVE_FILE setting "invalid"', msg.msg)
+
+    @override_settings(OCR_CLEAN="cleanme")
+    def test_invalid_ocr_clean(self) -> None:
+        """
+        GIVEN:
+            - Default settings
+            - OCR cleaning type is invalid
+        WHEN:
+            - Settings are validated
+        THEN:
+            - system check error reported for OCR cleaning type
+        """
+        msgs = settings_values_check(None)
+        self.assertEqual(len(msgs), 1)
+
+        msg = msgs[0]
+
+        self.assertIn('OCR clean mode "cleanme"', msg.msg)


-class TestTimezoneSettingsChecks:
-    def test_invalid_timezone(self, settings: SettingsWrapper) -> None:
+class TestTimezoneSettingsChecks(DirectoriesMixin, TestCase):
+    @override_settings(TIME_ZONE="TheMoon\\MyCrater")
+    def test_invalid_timezone(self) -> None:
        """
        GIVEN:
            - Default settings
@@ -181,16 +185,17 @@ class TestTimezoneSettingsChecks:
        THEN:
            - system check error reported for timezone
        """
-        settings.TIME_ZONE = "TheMoon\\MyCrater"
-
        msgs = settings_values_check(None)
+        self.assertEqual(len(msgs), 1)

-        assert len(msgs) == 1
-        assert 'Timezone "TheMoon\\MyCrater"' in msgs[0].msg
+        msg = msgs[0]
+
+        self.assertIn('Timezone "TheMoon\\MyCrater"', msg.msg)


-class TestEmailCertSettingsChecks:
-    def test_not_valid_file(self, settings: SettingsWrapper) -> None:
+class TestEmailCertSettingsChecks(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
+    @override_settings(EMAIL_CERTIFICATE_FILE=Path("/tmp/not_actually_here.pem"))
+    def test_not_valid_file(self) -> None:
        """
        GIVEN:
            - Default settings
@@ -200,22 +205,19 @@ class TestEmailCertSettingsChecks:
        THEN:
            - system check error reported for email certificate
        """
-        cert_path = Path("/tmp/not_actually_here.pem")
-        assert not cert_path.is_file()
-        settings.EMAIL_CERTIFICATE_FILE = cert_path
+        self.assertIsNotFile("/tmp/not_actually_here.pem")

        msgs = settings_values_check(None)

-        assert len(msgs) == 1
-        assert "Email cert /tmp/not_actually_here.pem is not a file" in msgs[0].msg
+        self.assertEqual(len(msgs), 1)
+
+        msg = msgs[0]
+
+        self.assertIn("Email cert /tmp/not_actually_here.pem is not a file", msg.msg)


-class TestAuditLogChecks:
-    def test_was_enabled_once(
-        self,
-        settings: SettingsWrapper,
-        mocker: MockerFixture,
-    ) -> None:
+class TestAuditLogChecks(TestCase):
+    def test_was_enabled_once(self) -> None:
        """
        GIVEN:
            - Audit log is not enabled
@@ -224,18 +226,23 @@ class TestAuditLogChecks:
        THEN:
            - system check error reported for disabling audit log
        """
-        settings.AUDIT_LOG_ENABLED = False
-        introspect_mock = mocker.MagicMock()
+        introspect_mock = mock.MagicMock()
        introspect_mock.introspection.table_names.return_value = ["auditlog_logentry"]
-        mocker.patch.dict(
-            "paperless.checks.connections",
-            {"default": introspect_mock},
-        )
+        with override_settings(AUDIT_LOG_ENABLED=False):
+            with mock.patch.dict(
+                "paperless.checks.connections",
+                {"default": introspect_mock},
+            ):
+                msgs = audit_log_check(None)

-        msgs = audit_log_check(None)
+                self.assertEqual(len(msgs), 1)

-        assert len(msgs) == 1
-        assert "auditlog table was found but audit log is disabled." in msgs[0].msg
+                msg = msgs[0]
+
+                self.assertIn(
+                    ("auditlog table was found but audit log is disabled."),
+                    msg.msg,
+                )


 DEPRECATED_VARS: dict[str, str] = {
@@ -264,16 +271,20 @@ class TestDeprecatedDbSettings:
    @pytest.mark.parametrize(
        ("env_var", "db_option_key"),
        [
-            pytest.param("PAPERLESS_DB_TIMEOUT", "timeout", id="db-timeout"),
-            pytest.param(
-                "PAPERLESS_DB_POOLSIZE",
-                "pool.min_size / pool.max_size",
-                id="db-poolsize",
-            ),
-            pytest.param("PAPERLESS_DBSSLMODE", "sslmode", id="ssl-mode"),
-            pytest.param("PAPERLESS_DBSSLROOTCERT", "sslrootcert", id="ssl-rootcert"),
-            pytest.param("PAPERLESS_DBSSLCERT", "sslcert", id="ssl-cert"),
-            pytest.param("PAPERLESS_DBSSLKEY", "sslkey", id="ssl-key"),
+            ("PAPERLESS_DB_TIMEOUT", "timeout"),
+            ("PAPERLESS_DB_POOLSIZE", "pool.min_size / pool.max_size"),
+            ("PAPERLESS_DBSSLMODE", "sslmode"),
+            ("PAPERLESS_DBSSLROOTCERT", "sslrootcert"),
+            ("PAPERLESS_DBSSLCERT", "sslcert"),
+            ("PAPERLESS_DBSSLKEY", "sslkey"),
+        ],
+        ids=[
+            "db-timeout",
+            "db-poolsize",
+            "ssl-mode",
+            "ssl-rootcert",
+            "ssl-cert",
+            "ssl-key",
        ],
    )
    def test_single_deprecated_var_produces_one_warning(
@@ -392,10 +403,7 @@ class TestV3MinimumUpgradeVersionCheck:
    """Test suite for check_v3_minimum_upgrade_version system check."""

    @pytest.fixture
-    def build_conn_mock(
-        self,
-        mocker: MockerFixture,
-    ) -> Callable[[list[str], list[str]], mock.MagicMock]:
+    def build_conn_mock(self, mocker: MockerFixture):
        """Factory fixture that builds a connections['default'] mock.

        Usage::
@@ -415,7 +423,7 @@ class TestV3MinimumUpgradeVersionCheck:
    def test_no_migrations_table_fresh_install(
        self,
        mocker: MockerFixture,
-        build_conn_mock: Callable[[list[str], list[str]], mock.MagicMock],
+        build_conn_mock,
    ) -> None:
        """
        GIVEN:
@@ -434,7 +442,7 @@ class TestV3MinimumUpgradeVersionCheck:
    def test_no_documents_migrations_fresh_install(
        self,
        mocker: MockerFixture,
-        build_conn_mock: Callable[[list[str], list[str]], mock.MagicMock],
+        build_conn_mock,
    ) -> None:
        """
        GIVEN:
@@ -453,7 +461,7 @@ class TestV3MinimumUpgradeVersionCheck:
    def test_v3_state_with_0001_squashed(
        self,
        mocker: MockerFixture,
-        build_conn_mock: Callable[[list[str], list[str]], mock.MagicMock],
+        build_conn_mock,
    ) -> None:
        """
        GIVEN:
@@ -477,7 +485,7 @@ class TestV3MinimumUpgradeVersionCheck:
    def test_v3_state_with_0002_squashed_only(
        self,
        mocker: MockerFixture,
-        build_conn_mock: Callable[[list[str], list[str]], mock.MagicMock],
+        build_conn_mock,
    ) -> None:
        """
        GIVEN:
@@ -496,7 +504,7 @@ class TestV3MinimumUpgradeVersionCheck:
    def test_v2_20_9_state_ready_to_upgrade(
        self,
        mocker: MockerFixture,
-        build_conn_mock: Callable[[list[str], list[str]], mock.MagicMock],
+        build_conn_mock,
    ) -> None:
        """
        GIVEN:
@@ -523,7 +531,7 @@ class TestV3MinimumUpgradeVersionCheck:
    def test_v2_20_8_raises_error(
        self,
        mocker: MockerFixture,
-        build_conn_mock: Callable[[list[str], list[str]], mock.MagicMock],
+        build_conn_mock,
    ) -> None:
        """
        GIVEN:
@@ -550,7 +558,7 @@ class TestV3MinimumUpgradeVersionCheck:
    def test_very_old_version_raises_error(
        self,
        mocker: MockerFixture,
-        build_conn_mock: Callable[[list[str], list[str]], mock.MagicMock],
+        build_conn_mock,
    ) -> None:
        """
        GIVEN:
@@ -577,7 +585,7 @@ class TestV3MinimumUpgradeVersionCheck:
    def test_error_hint_mentions_v2_20_9(
        self,
        mocker: MockerFixture,
-        build_conn_mock: Callable[[list[str], list[str]], mock.MagicMock],
+        build_conn_mock,
    ) -> None:
        """
        GIVEN:
--- a/src/paperless/tests/test_utils.py
+++ b/src/paperless/tests/test_utils.py
@@ -9,50 +9,35 @@ from paperless.utils import ocr_to_dateparser_languages
@pytest.mark.parametrize(
    ("ocr_language", "expected"),
    [
-        pytest.param("eng", ["en"], id="single-language"),
-        pytest.param("fra+ita+lao", ["fr", "it", "lo"], id="multiple-languages"),
-        pytest.param("fil", ["fil"], id="no-two-letter-equivalent"),
-        pytest.param(
-            "aze_cyrl+srp_latn",
-            ["az-Cyrl", "sr-Latn"],
-            id="script-supported-by-dateparser",
-        ),
-        pytest.param(
-            "deu_frak",
-            ["de"],
-            id="script-not-supported-falls-back-to-language",
-        ),
-        pytest.param(
-            "chi_tra+chi_sim",
-            ["zh"],
-            id="chinese-variants-collapse-to-general",
-        ),
-        pytest.param(
-            "eng+unsupported_language+por",
-            ["en", "pt"],
-            id="unsupported-language-skipped",
-        ),
-        pytest.param(
-            "unsupported1+unsupported2",
-            [],
-            id="all-unsupported-returns-empty",
-        ),
-        pytest.param("eng+eng", ["en"], id="duplicates-deduplicated"),
-        pytest.param(
-            "ita_unknownscript",
-            ["it"],
-            id="unknown-script-falls-back-to-language",
-        ),
+        # One language
+        ("eng", ["en"]),
+        # Multiple languages
+        ("fra+ita+lao", ["fr", "it", "lo"]),
+        # Languages that don't have a two-letter equivalent
+        ("fil", ["fil"]),
+        # Languages with a script part supported by dateparser
+        ("aze_cyrl+srp_latn", ["az-Cyrl", "sr-Latn"]),
+        # Languages with a script part not supported by dateparser
+        # In this case, default to the language without script
+        ("deu_frak", ["de"]),
+        # Traditional and simplified chinese don't have the same name in dateparser,
+        # so they're converted to the general chinese language
+        ("chi_tra+chi_sim", ["zh"]),
+        # If a language is not supported by dateparser, fallback to the supported ones
+        ("eng+unsupported_language+por", ["en", "pt"]),
+        # If no language is supported, fallback to default
+        ("unsupported1+unsupported2", []),
+        # Duplicate languages, should not duplicate in result
+        ("eng+eng", ["en"]),
+        # Language with script, but script is not mapped
+        ("ita_unknownscript", ["it"]),
    ],
 )
-def test_ocr_to_dateparser_languages(ocr_language: str, expected: list[str]) -> None:
+def test_ocr_to_dateparser_languages(ocr_language, expected):
    assert sorted(ocr_to_dateparser_languages(ocr_language)) == sorted(expected)


-def test_ocr_to_dateparser_languages_exception(
-    monkeypatch: pytest.MonkeyPatch,
-    caplog: pytest.LogCaptureFixture,
-) -> None:
+def test_ocr_to_dateparser_languages_exception(monkeypatch, caplog):
    # Patch LocaleDataLoader.get_locale_map to raise an exception
    class DummyLoader:
        def get_locale_map(self, locales=None):
--- a/src/paperless/tests/test_views.py
+++ b/src/paperless/tests/test_views.py
@@ -1,31 +1,24 @@
+import tempfile
 from pathlib import Path

-from django.test import Client
-from pytest_django.fixtures import SettingsWrapper
+from django.test import override_settings


-def test_favicon_view(
-    client: Client,
-    tmp_path: Path,
-    settings: SettingsWrapper,
-) -> None:
-    favicon_path = tmp_path / "paperless" / "img" / "favicon.ico"
-    favicon_path.parent.mkdir(parents=True)
-    favicon_path.write_bytes(b"FAKE ICON DATA")
+def test_favicon_view(client):
+    with tempfile.TemporaryDirectory() as tmpdir:
+        static_dir = Path(tmpdir)
+        favicon_path = static_dir / "paperless" / "img" / "favicon.ico"
+        favicon_path.parent.mkdir(parents=True, exist_ok=True)
+        favicon_path.write_bytes(b"FAKE ICON DATA")

-    settings.STATIC_ROOT = tmp_path
-
-    response = client.get("/favicon.ico")
-    assert response.status_code == 200
-    assert response["Content-Type"] == "image/x-icon"
-    assert b"".join(response.streaming_content) == b"FAKE ICON DATA"
+        with override_settings(STATIC_ROOT=static_dir):
+            response = client.get("/favicon.ico")
+            assert response.status_code == 200
+            assert response["Content-Type"] == "image/x-icon"
+            assert b"".join(response.streaming_content) == b"FAKE ICON DATA"


-def test_favicon_view_missing_file(
-    client: Client,
-    tmp_path: Path,
-    settings: SettingsWrapper,
-) -> None:
-    settings.STATIC_ROOT = tmp_path
-    response = client.get("/favicon.ico")
-    assert response.status_code == 404
+def test_favicon_view_missing_file(client):
+    with override_settings(STATIC_ROOT=Path(tempfile.mkdtemp())):
+        response = client.get("/favicon.ico")
+        assert response.status_code == 404
--- a/src/paperless_ai/base_model.py
+++ b/src/paperless_ai/base_model.py
@@ -1,4 +1,4 @@
-from pydantic import BaseModel
+from llama_index.core.bridge.pydantic import BaseModel


 class DocumentClassifierSchema(BaseModel):
--- a/src/paperless_ai/chat.py
+++ b/src/paperless_ai/chat.py
@@ -1,6 +1,10 @@
 import logging
 import sys

+from llama_index.core import VectorStoreIndex
+from llama_index.core.prompts import PromptTemplate
+from llama_index.core.query_engine import RetrieverQueryEngine
+
 from documents.models import Document
 from paperless_ai.client import AIClient
 from paperless_ai.indexing import load_or_build_index
@@ -10,21 +14,15 @@ logger = logging.getLogger("paperless_ai.chat")
 MAX_SINGLE_DOC_CONTEXT_CHARS = 15000
 SINGLE_DOC_SNIPPET_CHARS = 800

-CHAT_PROMPT_TEMPLATE = """Context information is below.
+CHAT_PROMPT_TMPL = PromptTemplate(
+    template="""Context information is below.
    ---------------------
    {context_str}
    ---------------------
    Given the context information and not prior knowledge, answer the query.
    Query: {query_str}
-    Answer:"""
-
-
-def _get_prompt_template():
-    from llama_index.core.prompts import PromptTemplate
-
-    return PromptTemplate(
-        template=CHAT_PROMPT_TEMPLATE,
-    )
+    Answer:""",
+)


 def stream_chat_with_documents(query_str: str, documents: list[Document]):
@@ -45,8 +43,6 @@ def stream_chat_with_documents(query_str: str, documents: list[Document]):
        yield "Sorry, I couldn't find any content to answer your question."
        return

-    from llama_index.core import VectorStoreIndex
-
    local_index = VectorStoreIndex(nodes=nodes)
    retriever = local_index.as_retriever(
        similarity_top_k=3 if len(documents) == 1 else 5,
@@ -89,16 +85,10 @@ def stream_chat_with_documents(query_str: str, documents: list[Document]):
            for node in top_nodes
        )

-    prompt = (
-        _get_prompt_template()
-        .partial_format(
-            context_str=context,
-            query_str=query_str,
-        )
-        .format(llm=client.llm)
-    )
-
-    from llama_index.core.query_engine import RetrieverQueryEngine
+    prompt = CHAT_PROMPT_TMPL.partial_format(
+        context_str=context,
+        query_str=query_str,
+    ).format(llm=client.llm)

    query_engine = RetrieverQueryEngine.from_args(
        retriever=retriever,
--- a/src/paperless_ai/client.py
+++ b/src/paperless_ai/client.py
@@ -1,10 +1,9 @@
 import logging
-from typing import TYPE_CHECKING

-if TYPE_CHECKING:
-    from llama_index.core.llms import ChatMessage
-    from llama_index.llms.ollama import Ollama
-    from llama_index.llms.openai import OpenAI
+from llama_index.core.llms import ChatMessage
+from llama_index.core.program.function_program import get_function_tool
+from llama_index.llms.ollama import Ollama
+from llama_index.llms.openai import OpenAI

 from paperless.config import AIConfig
 from paperless_ai.base_model import DocumentClassifierSchema
@@ -21,18 +20,14 @@ class AIClient:
        self.settings = AIConfig()
        self.llm = self.get_llm()

-    def get_llm(self) -> "Ollama | OpenAI":
+    def get_llm(self) -> Ollama | OpenAI:
        if self.settings.llm_backend == "ollama":
-            from llama_index.llms.ollama import Ollama
-
            return Ollama(
                model=self.settings.llm_model or "llama3.1",
                base_url=self.settings.llm_endpoint or "http://localhost:11434",
                request_timeout=120,
            )
        elif self.settings.llm_backend == "openai":
-            from llama_index.llms.openai import OpenAI
-
            return OpenAI(
                model=self.settings.llm_model or "gpt-3.5-turbo",
                api_base=self.settings.llm_endpoint or None,
@@ -48,9 +43,6 @@ class AIClient:
            self.settings.llm_model,
        )

-        from llama_index.core.llms import ChatMessage
-        from llama_index.core.program.function_program import get_function_tool
-
        user_msg = ChatMessage(role="user", content=prompt)
        tool = get_function_tool(DocumentClassifierSchema)
        result = self.llm.chat_with_tools(
@@ -66,7 +58,7 @@ class AIClient:
        parsed = DocumentClassifierSchema(**tool_calls[0].tool_kwargs)
        return parsed.model_dump()

-    def run_chat(self, messages: list["ChatMessage"]) -> str:
+    def run_chat(self, messages: list[ChatMessage]) -> str:
        logger.debug(
            "Running chat query against %s with model %s",
            self.settings.llm_backend,
--- a/src/paperless_ai/embedding.py
+++ b/src/paperless_ai/embedding.py
@@ -5,9 +5,9 @@ if TYPE_CHECKING:
    from pathlib import Path

 from django.conf import settings
-
-if TYPE_CHECKING:
-    from llama_index.core.base.embeddings.base import BaseEmbedding
+from llama_index.core.base.embeddings.base import BaseEmbedding
+from llama_index.embeddings.huggingface import HuggingFaceEmbedding
+from llama_index.embeddings.openai import OpenAIEmbedding

 from documents.models import Document
 from documents.models import Note
@@ -15,21 +15,17 @@ from paperless.config import AIConfig
 from paperless.models import LLMEmbeddingBackend


-def get_embedding_model() -> "BaseEmbedding":
+def get_embedding_model() -> BaseEmbedding:
    config = AIConfig()

    match config.llm_embedding_backend:
        case LLMEmbeddingBackend.OPENAI:
-            from llama_index.embeddings.openai import OpenAIEmbedding
-
            return OpenAIEmbedding(
                model=config.llm_embedding_model or "text-embedding-3-small",
                api_key=config.llm_api_key,
                api_base=config.llm_endpoint or None,
            )
        case LLMEmbeddingBackend.HUGGINGFACE:
-            from llama_index.embeddings.huggingface import HuggingFaceEmbedding
-
            return HuggingFaceEmbedding(
                model_name=config.llm_embedding_model
                or "sentence-transformers/all-MiniLM-L6-v2",
--- a/src/paperless_ai/indexing.py
+++ b/src/paperless_ai/indexing.py
@@ -4,12 +4,26 @@ from collections.abc import Callable
 from collections.abc import Iterable
 from datetime import timedelta
 from pathlib import Path
-from typing import TYPE_CHECKING
 from typing import TypeVar

+import faiss
+import llama_index.core.settings as llama_settings
 from celery import states
 from django.conf import settings
 from django.utils import timezone
+from llama_index.core import Document as LlamaDocument
+from llama_index.core import StorageContext
+from llama_index.core import VectorStoreIndex
+from llama_index.core import load_index_from_storage
+from llama_index.core.indices.prompt_helper import PromptHelper
+from llama_index.core.node_parser import SimpleNodeParser
+from llama_index.core.prompts import PromptTemplate
+from llama_index.core.retrievers import VectorIndexRetriever
+from llama_index.core.schema import BaseNode
+from llama_index.core.storage.docstore import SimpleDocumentStore
+from llama_index.core.storage.index_store import SimpleIndexStore
+from llama_index.core.text_splitter import TokenTextSplitter
+from llama_index.vector_stores.faiss import FaissVectorStore

 from documents.models import Document
 from documents.models import PaperlessTask
@@ -17,11 +31,6 @@ from paperless_ai.embedding import build_llm_index_text
 from paperless_ai.embedding import get_embedding_dim
 from paperless_ai.embedding import get_embedding_model

-if TYPE_CHECKING:
-    from llama_index.core import StorageContext
-    from llama_index.core import VectorStoreIndex
-    from llama_index.core.schema import BaseNode
-
 _T = TypeVar("_T")
 IterWrapper = Callable[[Iterable[_T]], Iterable[_T]]

@@ -56,17 +65,11 @@ def queue_llm_index_update_if_needed(*, rebuild: bool, reason: str) -> bool:
    return True


-def get_or_create_storage_context(*, rebuild=False) -> "StorageContext":
+def get_or_create_storage_context(*, rebuild=False):
    """
    Loads or creates the StorageContext (vector store, docstore, index store).
    If rebuild=True, deletes and recreates everything.
    """
-    import faiss
-    from llama_index.core import StorageContext
-    from llama_index.core.storage.docstore import SimpleDocumentStore
-    from llama_index.core.storage.index_store import SimpleIndexStore
-    from llama_index.vector_stores.faiss import FaissVectorStore
-
    if rebuild:
        shutil.rmtree(settings.LLM_INDEX_DIR, ignore_errors=True)
        settings.LLM_INDEX_DIR.mkdir(parents=True, exist_ok=True)
@@ -90,7 +93,7 @@ def get_or_create_storage_context(*, rebuild=False) -> "StorageContext":
    )


-def build_document_node(document: Document) -> list["BaseNode"]:
+def build_document_node(document: Document) -> list[BaseNode]:
    """
    Given a Document, returns parsed Nodes ready for indexing.
    """
@@ -109,23 +112,16 @@ def build_document_node(document: Document) -> list["BaseNode"]:
        "added": document.added.isoformat() if document.added else None,
        "modified": document.modified.isoformat(),
    }
-    from llama_index.core import Document as LlamaDocument
-    from llama_index.core.node_parser import SimpleNodeParser
-
    doc = LlamaDocument(text=text, metadata=metadata)
    parser = SimpleNodeParser()
    return parser.get_nodes_from_documents([doc])


-def load_or_build_index(nodes=None) -> "VectorStoreIndex":
+def load_or_build_index(nodes=None):
    """
    Load an existing VectorStoreIndex if present,
    or build a new one using provided nodes if storage is empty.
    """
-    import llama_index.core.settings as llama_settings
-    from llama_index.core import VectorStoreIndex
-    from llama_index.core import load_index_from_storage
-
    embed_model = get_embedding_model()
    llama_settings.Settings.embed_model = embed_model
    storage_context = get_or_create_storage_context()
@@ -147,7 +143,7 @@ def load_or_build_index(nodes=None) -> "VectorStoreIndex":
        )


-def remove_document_docstore_nodes(document: Document, index: "VectorStoreIndex"):
+def remove_document_docstore_nodes(document: Document, index: VectorStoreIndex):
    """
    Removes existing documents from docstore for a given document from the index.
    This is necessary because FAISS IndexFlatL2 is append-only.
@@ -187,9 +183,6 @@ def update_llm_index(
        return msg

    if rebuild or not vector_store_file_exists():
-        import llama_index.core.settings as llama_settings
-        from llama_index.core import VectorStoreIndex
-
        # remove meta.json to force re-detection of embedding dim
        (settings.LLM_INDEX_DIR / "meta.json").unlink(missing_ok=True)
        # Rebuild index from scratch
@@ -278,10 +271,6 @@ def llm_index_remove_document(document: Document):


 def truncate_content(content: str) -> str:
-    from llama_index.core.indices.prompt_helper import PromptHelper
-    from llama_index.core.prompts import PromptTemplate
-    from llama_index.core.text_splitter import TokenTextSplitter
-
    prompt_helper = PromptHelper(
        context_window=8192,
        num_output=512,
@@ -326,8 +315,6 @@ def query_similar_documents(
        else None
    )

-    from llama_index.core.retrievers import VectorIndexRetriever
-
    retriever = VectorIndexRetriever(
        index=index,
        similarity_top_k=top_k,
--- a/src/paperless_ai/tests/test_chat.py
+++ b/src/paperless_ai/tests/test_chat.py
@@ -45,7 +45,7 @@ def test_stream_chat_with_one_document_full_content(mock_document) -> None:
        patch("paperless_ai.chat.AIClient") as mock_client_cls,
        patch("paperless_ai.chat.load_or_build_index") as mock_load_index,
        patch(
-            "llama_index.core.query_engine.RetrieverQueryEngine.from_args",
+            "paperless_ai.chat.RetrieverQueryEngine.from_args",
        ) as mock_query_engine_cls,
    ):
        mock_client = MagicMock()
@@ -76,7 +76,7 @@ def test_stream_chat_with_multiple_documents_retrieval(patch_embed_nodes) -> Non
        patch("paperless_ai.chat.AIClient") as mock_client_cls,
        patch("paperless_ai.chat.load_or_build_index") as mock_load_index,
        patch(
-            "llama_index.core.query_engine.RetrieverQueryEngine.from_args",
+            "paperless_ai.chat.RetrieverQueryEngine.from_args",
        ) as mock_query_engine_cls,
        patch.object(VectorStoreIndex, "as_retriever") as mock_as_retriever,
    ):
--- a/src/paperless_ai/tests/test_client.py
+++ b/src/paperless_ai/tests/test_client.py
@@ -18,13 +18,13 @@ def mock_ai_config():

@pytest.fixture
 def mock_ollama_llm():
-    with patch("llama_index.llms.ollama.Ollama") as MockOllama:
+    with patch("paperless_ai.client.Ollama") as MockOllama:
        yield MockOllama


@pytest.fixture
 def mock_openai_llm():
-    with patch("llama_index.llms.openai.OpenAI") as MockOpenAI:
+    with patch("paperless_ai.client.OpenAI") as MockOpenAI:
        yield MockOpenAI


--- a/src/paperless_ai/tests/test_embedding.py
+++ b/src/paperless_ai/tests/test_embedding.py
@@ -67,7 +67,7 @@ def test_get_embedding_model_openai(mock_ai_config):
    mock_ai_config.return_value.llm_api_key = "test_api_key"
    mock_ai_config.return_value.llm_endpoint = "http://test-url"

-    with patch("llama_index.embeddings.openai.OpenAIEmbedding") as MockOpenAIEmbedding:
+    with patch("paperless_ai.embedding.OpenAIEmbedding") as MockOpenAIEmbedding:
        model = get_embedding_model()
        MockOpenAIEmbedding.assert_called_once_with(
            model="text-embedding-3-small",
@@ -84,7 +84,7 @@ def test_get_embedding_model_huggingface(mock_ai_config):
    )

    with patch(
-        "llama_index.embeddings.huggingface.HuggingFaceEmbedding",
+        "paperless_ai.embedding.HuggingFaceEmbedding",
    ) as MockHuggingFaceEmbedding:
        model = get_embedding_model()
        MockHuggingFaceEmbedding.assert_called_once_with(
--- a/uv.lock
+++ b/uv.lock
@@ -831,6 +831,15 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/2d/82/e5d2c1c67d19841e9edc74954c827444ae826978499bde3dfc1d007c8c11/deepmerge-2.0-py3-none-any.whl", hash = "sha256:6de9ce507115cff0bed95ff0ce9ecc31088ef50cbdf09bc90a09349a318b3d00", size = 13475, upload-time = "2024-08-30T05:31:48.659Z" },
 ]

+[[package]]
+name = "defusedxml"
+version = "0.7.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/0f/d5/c66da9b79e5bdb124974bfe172b4daf3c984ebd9c2a06e2b8a4dc7331c72/defusedxml-0.7.1.tar.gz", hash = "sha256:1bb3032db185915b62d7c6209c5a8792be6a32ab2fedacc84e01b52c51aa3e69", size = 75520, upload-time = "2021-03-08T10:59:26.269Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/07/6c/aa3f2f849e01cb6a001cd8554a88d4c77c5c1a31c95bdf1cf9301e6d9ef4/defusedxml-0.7.1-py2.py3-none-any.whl", hash = "sha256:a352e7e428770286cc899e2542b6cdaedb2b4953ff269a210103ec58f6198a61", size = 25604, upload-time = "2021-03-08T10:59:24.45Z" },
+]
+
 [[package]]
 name = "deprecated"
 version = "1.3.1"
@@ -1283,6 +1292,59 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/a6/ff/ee2f67c0ff146ec98b5df1df637b2bc2d17beeb05df9f427a67bd7a7d79c/flower-2.0.1-py2.py3-none-any.whl", hash = "sha256:9db2c621eeefbc844c8dd88be64aef61e84e2deb29b271e02ab2b5b9f01068e2", size = 383553, upload-time = "2023-08-13T14:37:41.552Z" },
 ]

+[[package]]
+name = "fonttools"
+version = "4.61.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/ec/ca/cf17b88a8df95691275a3d77dc0a5ad9907f328ae53acbe6795da1b2f5ed/fonttools-4.61.1.tar.gz", hash = "sha256:6675329885c44657f826ef01d9e4fb33b9158e9d93c537d84ad8399539bc6f69", size = 3565756, upload-time = "2025-12-12T17:31:24.246Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/69/12/bf9f4eaa2fad039356cc627587e30ed008c03f1cebd3034376b5ee8d1d44/fonttools-4.61.1-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:c6604b735bb12fef8e0efd5578c9fb5d3d8532d5001ea13a19cddf295673ee09", size = 2852213, upload-time = "2025-12-12T17:29:46.675Z" },
+    { url = "https://files.pythonhosted.org/packages/ac/49/4138d1acb6261499bedde1c07f8c2605d1d8f9d77a151e5507fd3ef084b6/fonttools-4.61.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:5ce02f38a754f207f2f06557523cd39a06438ba3aafc0639c477ac409fc64e37", size = 2401689, upload-time = "2025-12-12T17:29:48.769Z" },
+    { url = "https://files.pythonhosted.org/packages/e5/fe/e6ce0fe20a40e03aef906af60aa87668696f9e4802fa283627d0b5ed777f/fonttools-4.61.1-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:77efb033d8d7ff233385f30c62c7c79271c8885d5c9657d967ede124671bbdfb", size = 5058809, upload-time = "2025-12-12T17:29:51.701Z" },
+    { url = "https://files.pythonhosted.org/packages/79/61/1ca198af22f7dd22c17ab86e9024ed3c06299cfdb08170640e9996d501a0/fonttools-4.61.1-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:75c1a6dfac6abd407634420c93864a1e274ebc1c7531346d9254c0d8f6ca00f9", size = 5036039, upload-time = "2025-12-12T17:29:53.659Z" },
+    { url = "https://files.pythonhosted.org/packages/99/cc/fa1801e408586b5fce4da9f5455af8d770f4fc57391cd5da7256bb364d38/fonttools-4.61.1-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:0de30bfe7745c0d1ffa2b0b7048fb7123ad0d71107e10ee090fa0b16b9452e87", size = 5034714, upload-time = "2025-12-12T17:29:55.592Z" },
+    { url = "https://files.pythonhosted.org/packages/bf/aa/b7aeafe65adb1b0a925f8f25725e09f078c635bc22754f3fecb7456955b0/fonttools-4.61.1-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:58b0ee0ab5b1fc9921eccfe11d1435added19d6494dde14e323f25ad2bc30c56", size = 5158648, upload-time = "2025-12-12T17:29:57.861Z" },
+    { url = "https://files.pythonhosted.org/packages/6f/16/7decaa24a1bd3a70c607b2e29f0adc6159f36a7e40eaba59846414765fd4/fonttools-4.61.1-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:f3cb4a569029b9f291f88aafc927dd53683757e640081ca8c412781ea144565e", size = 2851593, upload-time = "2025-12-12T17:30:04.225Z" },
+    { url = "https://files.pythonhosted.org/packages/94/98/3c4cb97c64713a8cf499b3245c3bf9a2b8fd16a3e375feff2aed78f96259/fonttools-4.61.1-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:41a7170d042e8c0024703ed13b71893519a1a6d6e18e933e3ec7507a2c26a4b2", size = 2400231, upload-time = "2025-12-12T17:30:06.47Z" },
+    { url = "https://files.pythonhosted.org/packages/b7/37/82dbef0f6342eb01f54bca073ac1498433d6ce71e50c3c3282b655733b31/fonttools-4.61.1-cp312-cp312-manylinux1_x86_64.manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:10d88e55330e092940584774ee5e8a6971b01fc2f4d3466a1d6c158230880796", size = 4954103, upload-time = "2025-12-12T17:30:08.432Z" },
+    { url = "https://files.pythonhosted.org/packages/6c/44/f3aeac0fa98e7ad527f479e161aca6c3a1e47bb6996b053d45226fe37bf2/fonttools-4.61.1-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:15acc09befd16a0fb8a8f62bc147e1a82817542d72184acca9ce6e0aeda9fa6d", size = 5004295, upload-time = "2025-12-12T17:30:10.56Z" },
+    { url = "https://files.pythonhosted.org/packages/14/e8/7424ced75473983b964d09f6747fa09f054a6d656f60e9ac9324cf40c743/fonttools-4.61.1-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:e6bcdf33aec38d16508ce61fd81838f24c83c90a1d1b8c68982857038673d6b8", size = 4944109, upload-time = "2025-12-12T17:30:12.874Z" },
+    { url = "https://files.pythonhosted.org/packages/c8/8b/6391b257fa3d0b553d73e778f953a2f0154292a7a7a085e2374b111e5410/fonttools-4.61.1-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:5fade934607a523614726119164ff621e8c30e8fa1ffffbbd358662056ba69f0", size = 5093598, upload-time = "2025-12-12T17:30:15.79Z" },
+    { url = "https://files.pythonhosted.org/packages/4b/cf/00ba28b0990982530addb8dc3e9e6f2fa9cb5c20df2abdda7baa755e8fe1/fonttools-4.61.1-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:8c56c488ab471628ff3bfa80964372fc13504ece601e0d97a78ee74126b2045c", size = 2846454, upload-time = "2025-12-12T17:30:24.938Z" },
+    { url = "https://files.pythonhosted.org/packages/5a/ca/468c9a8446a2103ae645d14fee3f610567b7042aba85031c1c65e3ef7471/fonttools-4.61.1-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:dc492779501fa723b04d0ab1f5be046797fee17d27700476edc7ee9ae535a61e", size = 2398191, upload-time = "2025-12-12T17:30:27.343Z" },
+    { url = "https://files.pythonhosted.org/packages/a3/4b/d67eedaed19def5967fade3297fed8161b25ba94699efc124b14fb68cdbc/fonttools-4.61.1-cp313-cp313-manylinux1_x86_64.manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:64102ca87e84261419c3747a0d20f396eb024bdbeb04c2bfb37e2891f5fadcb5", size = 4928410, upload-time = "2025-12-12T17:30:29.771Z" },
+    { url = "https://files.pythonhosted.org/packages/b0/8d/6fb3494dfe61a46258cd93d979cf4725ded4eb46c2a4ca35e4490d84daea/fonttools-4.61.1-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:4c1b526c8d3f615a7b1867f38a9410849c8f4aef078535742198e942fba0e9bd", size = 4984460, upload-time = "2025-12-12T17:30:32.073Z" },
+    { url = "https://files.pythonhosted.org/packages/f7/f1/a47f1d30b3dc00d75e7af762652d4cbc3dff5c2697a0dbd5203c81afd9c3/fonttools-4.61.1-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:41ed4b5ec103bd306bb68f81dc166e77409e5209443e5773cb4ed837bcc9b0d3", size = 4925800, upload-time = "2025-12-12T17:30:34.339Z" },
+    { url = "https://files.pythonhosted.org/packages/a7/01/e6ae64a0981076e8a66906fab01539799546181e32a37a0257b77e4aa88b/fonttools-4.61.1-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:b501c862d4901792adaec7c25b1ecc749e2662543f68bb194c42ba18d6eec98d", size = 5067859, upload-time = "2025-12-12T17:30:36.593Z" },
+    { url = "https://files.pythonhosted.org/packages/32/8f/4e7bf82c0cbb738d3c2206c920ca34ca74ef9dabde779030145d28665104/fonttools-4.61.1-cp314-cp314-macosx_10_15_universal2.whl", hash = "sha256:fff4f534200a04b4a36e7ae3cb74493afe807b517a09e99cb4faa89a34ed6ecd", size = 2846094, upload-time = "2025-12-12T17:30:43.511Z" },
+    { url = "https://files.pythonhosted.org/packages/71/09/d44e45d0a4f3a651f23a1e9d42de43bc643cce2971b19e784cc67d823676/fonttools-4.61.1-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:d9203500f7c63545b4ce3799319fe4d9feb1a1b89b28d3cb5abd11b9dd64147e", size = 2396589, upload-time = "2025-12-12T17:30:45.681Z" },
+    { url = "https://files.pythonhosted.org/packages/89/18/58c64cafcf8eb677a99ef593121f719e6dcbdb7d1c594ae5a10d4997ca8a/fonttools-4.61.1-cp314-cp314-manylinux1_x86_64.manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:fa646ecec9528bef693415c79a86e733c70a4965dd938e9a226b0fc64c9d2e6c", size = 4877892, upload-time = "2025-12-12T17:30:47.709Z" },
+    { url = "https://files.pythonhosted.org/packages/8a/ec/9e6b38c7ba1e09eb51db849d5450f4c05b7e78481f662c3b79dbde6f3d04/fonttools-4.61.1-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:11f35ad7805edba3aac1a3710d104592df59f4b957e30108ae0ba6c10b11dd75", size = 4972884, upload-time = "2025-12-12T17:30:49.656Z" },
+    { url = "https://files.pythonhosted.org/packages/5e/87/b5339da8e0256734ba0dbbf5b6cdebb1dd79b01dc8c270989b7bcd465541/fonttools-4.61.1-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:b931ae8f62db78861b0ff1ac017851764602288575d65b8e8ff1963fed419063", size = 4924405, upload-time = "2025-12-12T17:30:51.735Z" },
+    { url = "https://files.pythonhosted.org/packages/0b/47/e3409f1e1e69c073a3a6fd8cb886eb18c0bae0ee13db2c8d5e7f8495e8b7/fonttools-4.61.1-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:b148b56f5de675ee16d45e769e69f87623a4944f7443850bf9a9376e628a89d2", size = 5035553, upload-time = "2025-12-12T17:30:54.823Z" },
+    { url = "https://files.pythonhosted.org/packages/39/5c/908ad78e46c61c3e3ed70c3b58ff82ab48437faf84ec84f109592cabbd9f/fonttools-4.61.1-cp314-cp314t-macosx_10_15_universal2.whl", hash = "sha256:e76ce097e3c57c4bcb67c5aa24a0ecdbd9f74ea9219997a707a4061fbe2707aa", size = 2929571, upload-time = "2025-12-12T17:31:02.574Z" },
+    { url = "https://files.pythonhosted.org/packages/bd/41/975804132c6dea64cdbfbaa59f3518a21c137a10cccf962805b301ac6ab2/fonttools-4.61.1-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:9cfef3ab326780c04d6646f68d4b4742aae222e8b8ea1d627c74e38afcbc9d91", size = 2435317, upload-time = "2025-12-12T17:31:04.974Z" },
+    { url = "https://files.pythonhosted.org/packages/b0/5a/aef2a0a8daf1ebaae4cfd83f84186d4a72ee08fd6a8451289fcd03ffa8a4/fonttools-4.61.1-cp314-cp314t-manylinux1_x86_64.manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:a75c301f96db737e1c5ed5fd7d77d9c34466de16095a266509e13da09751bd19", size = 4882124, upload-time = "2025-12-12T17:31:07.456Z" },
+    { url = "https://files.pythonhosted.org/packages/80/33/d6db3485b645b81cea538c9d1c9219d5805f0877fda18777add4671c5240/fonttools-4.61.1-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:91669ccac46bbc1d09e9273546181919064e8df73488ea087dcac3e2968df9ba", size = 5100391, upload-time = "2025-12-12T17:31:09.732Z" },
+    { url = "https://files.pythonhosted.org/packages/6c/d6/675ba631454043c75fcf76f0ca5463eac8eb0666ea1d7badae5fea001155/fonttools-4.61.1-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:c33ab3ca9d3ccd581d58e989d67554e42d8d4ded94ab3ade3508455fe70e65f7", size = 4978800, upload-time = "2025-12-12T17:31:11.681Z" },
+    { url = "https://files.pythonhosted.org/packages/7f/33/d3ec753d547a8d2bdaedd390d4a814e8d5b45a093d558f025c6b990b554c/fonttools-4.61.1-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:664c5a68ec406f6b1547946683008576ef8b38275608e1cee6c061828171c118", size = 5006426, upload-time = "2025-12-12T17:31:13.764Z" },
+    { url = "https://files.pythonhosted.org/packages/c7/4e/ce75a57ff3aebf6fc1f4e9d508b8e5810618a33d900ad6c19eb30b290b97/fonttools-4.61.1-py3-none-any.whl", hash = "sha256:17d2bf5d541add43822bcf0c43d7d847b160c9bb01d15d5007d84e2217aaa371", size = 1148996, upload-time = "2025-12-12T17:31:21.03Z" },
+]
+
+[[package]]
+name = "fpdf2"
+version = "2.8.7"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "defusedxml", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+    { name = "fonttools", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+    { name = "pillow", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/27/f2/72feae0b2827ed38013e4307b14f95bf0b3d124adfef4d38a7d57533f7be/fpdf2-2.8.7.tar.gz", hash = "sha256:7060ccee5a9c7ab0a271fb765a36a23639f83ef8996c34e3d46af0a17ede57f9", size = 362351, upload-time = "2026-02-28T05:39:16.456Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/66/0a/cf50ecffa1e3747ed9380a3adfc829259f1f86b3fdbd9e505af789003141/fpdf2-2.8.7-py3-none-any.whl", hash = "sha256:d391fc508a3ce02fc43a577c830cda4fe6f37646f2d143d489839940932fbc19", size = 327056, upload-time = "2026-02-28T05:39:14.619Z" },
+]
+
 [[package]]
 name = "frozenlist"
 version = "1.8.0"
@@ -2655,10 +2717,11 @@ wheels = [

 [[package]]
 name = "ocrmypdf"
-version = "16.13.0"
+version = "17.3.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
    { name = "deprecation", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+    { name = "fpdf2", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
    { name = "img2pdf", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
    { name = "packaging", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
    { name = "pdfminer-six", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
@@ -2666,11 +2729,14 @@ dependencies = [
    { name = "pikepdf", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
    { name = "pillow", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
    { name = "pluggy", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+    { name = "pydantic", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+    { name = "pypdfium2", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
    { name = "rich", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+    { name = "uharfbuzz", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/8c/52/be1aaece0703a736757d8957c0d4f19c37561054169b501eb0e7132f15e5/ocrmypdf-16.13.0.tar.gz", hash = "sha256:29d37e915234ce717374863a9cc5dd32d29e063dfe60c51380dda71254c88248", size = 7042247, upload-time = "2025-12-24T07:58:35.86Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/fa/fe/60bdc79529be1ad8b151d426ed2020d5ac90328c54e9ba92bd808e1535c1/ocrmypdf-17.3.0.tar.gz", hash = "sha256:4022f13aad3f405e330056a07aa8bd63714b48b414693831b56e2cf2c325f52d", size = 7378015, upload-time = "2026-02-21T09:30:07.207Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/41/b1/e2e7ad98de0d3ee05b44dbc3f78ccb158a620f3add82d00c85490120e7f2/ocrmypdf-16.13.0-py3-none-any.whl", hash = "sha256:fad8a6f7cc52cdc6225095c401a1766c778c47efe9f1e854ae4dc64a550a3d37", size = 165377, upload-time = "2025-12-24T07:58:33.925Z" },
+    { url = "https://files.pythonhosted.org/packages/3d/b1/b7ae057a1bcb1495067ee3c4d48c1ce5fc66addd9492307c5a0ff799a7f2/ocrmypdf-17.3.0-py3-none-any.whl", hash = "sha256:c8882e7864954d3db6bcee49cc9f261b65bff66b7e5925eb68a1c281f41cad23", size = 488130, upload-time = "2026-02-21T09:30:05.236Z" },
 ]

 [[package]]
@@ -2909,7 +2975,7 @@ requires-dist = [
    { name = "llama-index-vector-stores-faiss", specifier = ">=0.5.2" },
    { name = "mysqlclient", marker = "extra == 'mariadb'", specifier = "~=2.2.7" },
    { name = "nltk", specifier = "~=3.9.1" },
-    { name = "ocrmypdf", specifier = "~=16.13.0" },
+    { name = "ocrmypdf", specifier = "~=17.3.0" },
    { name = "openai", specifier = ">=1.76" },
    { name = "pathvalidate", specifier = "~=3.3.1" },
    { name = "pdf2image", specifier = "~=1.17.0" },
@@ -3586,6 +3652,30 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/d1/81/ef2b1dfd1862567d573a4fdbc9f969067621764fbb74338496840a1d2977/pyopenssl-25.3.0-py3-none-any.whl", hash = "sha256:1fda6fc034d5e3d179d39e59c1895c9faeaf40a79de5fc4cbbfbe0d36f4a77b6", size = 57268, upload-time = "2025-09-17T00:32:19.474Z" },
 ]

+[[package]]
+name = "pypdfium2"
+version = "5.5.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/fb/f6/42f5f1b9beb7e036f5532832b9c590fd107c52a78f704302c03bc6793954/pypdfium2-5.5.0.tar.gz", hash = "sha256:3283c61f54c3c546d140da201ef48a51c18b0ad54293091a010029ac13ece23a", size = 270502, upload-time = "2026-02-18T23:22:37.643Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/bc/a9/379ec56c4481f39f0e37a7ce42f4844e6ddd7662571922e2b348105960ab/pypdfium2-5.5.0-py3-none-macosx_11_0_arm64.whl", hash = "sha256:0770bd3f0be5c68443fc4017e43b1b1fe8f36877481cab70fd29b68b2c362e1b", size = 2815036, upload-time = "2026-02-18T23:22:00.288Z" },
+    { url = "https://files.pythonhosted.org/packages/91/a4/b0cc01aaae1fdf1ca4e080cc55bb432f5a2234f33209a602bc498a47850d/pypdfium2-5.5.0-py3-none-macosx_11_0_x86_64.whl", hash = "sha256:5ab41a3b9953d9be44be35c36a2340f1d67c602db98a0d6f70006610871ae43a", size = 2948686, upload-time = "2026-02-18T23:22:02.213Z" },
+    { url = "https://files.pythonhosted.org/packages/26/99/25a0c71b551d100b505c618910afec0df402b230e087078c8078f8b1fcff/pypdfium2-5.5.0-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2492a22c3126a004cee2fa208ea4aa03ede2c7e205d05814934ab18f83d073e9", size = 2977311, upload-time = "2026-02-18T23:22:03.603Z" },
+    { url = "https://files.pythonhosted.org/packages/85/64/691e21539566f7a0521295948b5589d2fdfe3df5acab9c29ff410633a839/pypdfium2-5.5.0-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:83ff93e08b1fadb00040564e2eccc99147fc1a632ba5daff745126b373d78446", size = 2762449, upload-time = "2026-02-18T23:22:05.044Z" },
+    { url = "https://files.pythonhosted.org/packages/74/b1/9af288557291e2964bf5ffd460b7ed1090fcb8c54addfd6c7c5deb9ba7c7/pypdfium2-5.5.0-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b7e85de3332bedf8e5f157c248063b4eaf968660e1e490353b6e581d9f96a4c6", size = 3074851, upload-time = "2026-02-18T23:22:07.431Z" },
+    { url = "https://files.pythonhosted.org/packages/a4/1e/c61fddbdea5ea1ba478dc7ecc9d68069d17b858e5fed04e4e071811f0858/pypdfium2-5.5.0-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:e258365f34b6e334bb415e44dd9b1ee78a6e525bf854a1e74af67af7ede7555b", size = 3423003, upload-time = "2026-02-18T23:22:09.749Z" },
+    { url = "https://files.pythonhosted.org/packages/36/5f/d2eb58c54abba3a6c3bc4c297b3a11348dd4b4deb073f1aa8a872a298278/pypdfium2-5.5.0-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bec21d833404ca771f02fa5cefb0b73e2148f05cbdb3b5b9989bdd51d9b5cbac", size = 3002104, upload-time = "2026-02-18T23:22:12.035Z" },
+    { url = "https://files.pythonhosted.org/packages/1c/33/87423eec4f5d4287d5a1726dbb9f06fb1f1aebc38ff75dcff817c492769d/pypdfium2-5.5.0-py3-none-manylinux_2_27_s390x.manylinux_2_28_s390x.whl", hash = "sha256:1dd6ccbe1b5e2e778e8b021e47f9485b4fd42eaa6c9bdda2631641724e1fcc04", size = 3097209, upload-time = "2026-02-18T23:22:13.809Z" },
+    { url = "https://files.pythonhosted.org/packages/97/0a/a3fd71f00838bba7922691107219bee67f50fbda6d12df330ef485a97848/pypdfium2-5.5.0-py3-none-manylinux_2_38_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:da3eada345570cec5e34872d1472d4ac542f0e650ccdb6c2eac08ae1a5f07c82", size = 2965027, upload-time = "2026-02-18T23:22:16.324Z" },
+    { url = "https://files.pythonhosted.org/packages/75/4a/2181260bd8a0b1b30ac50b7fd6ee3366e04f3a9f1c29351d882652da7fa7/pypdfium2-5.5.0-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:a087fb4088c7433fd3d78833dbe42cfb66df3d5ac98e3edf66110520fb33c0f0", size = 4131431, upload-time = "2026-02-18T23:22:18.469Z" },
+    { url = "https://files.pythonhosted.org/packages/15/bb/3ccf481191346eda11c0c208bd4e46f8de019ae7d9e9c1b660633f0bb3f4/pypdfium2-5.5.0-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:e6418cdc500ef85a90319f9bc7f1c54fc133460379f509429403225d8a4c157f", size = 3747468, upload-time = "2026-02-18T23:22:20.679Z" },
+    { url = "https://files.pythonhosted.org/packages/15/51/17e50ec72cf2235ac18d9cbe907859501c769d3e964818fefac6a3e10727/pypdfium2-5.5.0-py3-none-musllinux_1_2_i686.whl", hash = "sha256:8f7b66eedfac26eb2df4b00936e081b0a1c76fb8ee1c12639d85c2e73b0769ef", size = 4337579, upload-time = "2026-02-18T23:22:23.245Z" },
+    { url = "https://files.pythonhosted.org/packages/c6/e4/f9bdf06f4d3f1e56eff9d997392a00a4b66cbc9c20f33934c4edc2a7943f/pypdfium2-5.5.0-py3-none-musllinux_1_2_ppc64le.whl", hash = "sha256:faea3246591ce2ea6218cd06679071275e3c65f11c3f5c9091eb7fb07610af6a", size = 4376104, upload-time = "2026-02-18T23:22:25.337Z" },
+    { url = "https://files.pythonhosted.org/packages/8c/20/06baf1f5d494e035f50fc895fa1da5ed652d03ecc59aeb3aabb0daa5adfc/pypdfium2-5.5.0-py3-none-musllinux_1_2_riscv64.whl", hash = "sha256:aba26d404b51a9de3d3e80c867a95c71abf1c79552001ae22707451e59186b3d", size = 3929824, upload-time = "2026-02-18T23:22:26.889Z" },
+    { url = "https://files.pythonhosted.org/packages/3a/01/28940e54e6936674e9a05eb58ccce7c54d8e2ac81cd84ec0b76e7d32a010/pypdfium2-5.5.0-py3-none-musllinux_1_2_s390x.whl", hash = "sha256:e0fa8f81679e6e71f26806f4db853571ee6435dc3bde7a46acdd182ef886a5b9", size = 4270200, upload-time = "2026-02-18T23:22:28.668Z" },
+    { url = "https://files.pythonhosted.org/packages/cb/d4/1f36c505a3770aad9a88c895a46d61fd4c0535f79548f02c93b97ff89604/pypdfium2-5.5.0-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:ee22df3376d350eeb64d2002a1071e3a02c0d874c557a3cd8229a8fc572cdaac", size = 4180794, upload-time = "2026-02-18T23:22:30.11Z" },
+]
+
 [[package]]
 name = "pyrefly"
 version = "0.54.0"
@@ -5072,6 +5162,23 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/b1/5e/512aeb40fd819f4660d00f96f5c7371ee36fc8c6b605128c5ee59e0b28c6/u_msgpack_python-2.8.0-py2.py3-none-any.whl", hash = "sha256:1d853d33e78b72c4228a2025b4db28cda81214076e5b0422ed0ae1b1b2bb586a", size = 10590, upload-time = "2023-05-18T09:28:10.323Z" },
 ]

+[[package]]
+name = "uharfbuzz"
+version = "0.53.3"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/1c/8d/7c82298bfa5c96f018541661bc2ccdf90dfe397bb2724db46725bf495466/uharfbuzz-0.53.3.tar.gz", hash = "sha256:9a87175c14d1361322ce2a3504e63c6b66062934a5edf47266aed5b33416806c", size = 1714488, upload-time = "2026-01-24T13:10:43.693Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/51/88/5df9337adb60d7b1ad150b162bbc5c56d783d15546714085d92b9531f8f3/uharfbuzz-0.53.3-cp310-abi3-macosx_10_9_universal2.whl", hash = "sha256:d977e41a501d9e8af3f2c329d75031037ee79634bc29ca3872e9115c44e67d25", size = 2722639, upload-time = "2026-01-24T13:10:22.436Z" },
+    { url = "https://files.pythonhosted.org/packages/39/c4/8b4b050e77d6cb9a84af509e5796734f0e687bd02ad11757a581bd6f197d/uharfbuzz-0.53.3-cp310-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:21d512c94aa992691aaf5b433deaca7e51f4ea54c68b99f535974073364f806f", size = 1647506, upload-time = "2026-01-24T13:10:24.16Z" },
+    { url = "https://files.pythonhosted.org/packages/30/ff/8e7cf78d525604f3e0a43b9468263fcf2acb5d208a3979c3bfa8dc61112d/uharfbuzz-0.53.3-cp310-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:dca9a2e071c0c59ba8f382356f31a2518ac3dc7cc77e4f3519defc454c5b9a97", size = 1706448, upload-time = "2026-01-24T13:10:25.729Z" },
+    { url = "https://files.pythonhosted.org/packages/9b/a0/739471cdd52723ecc9fc80f36fb92c706a87265dc258521c1b14d99414f7/uharfbuzz-0.53.3-cp310-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:1191a74ddcf18ec721161b6b33a8ab31b0c6a2b15c6724a9b663127bf7f07d2e", size = 2664628, upload-time = "2026-01-24T13:10:27.814Z" },
+    { url = "https://files.pythonhosted.org/packages/ae/4a/63a81e9eef922b9f26bd948b518b73704d01a8d8e83324b2f99084ab7af0/uharfbuzz-0.53.3-cp310-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:35ec3b600b3f63e7659792f9bd43e1ffb389d3d2aac8285f269d11efbe04787d", size = 2757384, upload-time = "2026-01-24T13:10:29.669Z" },
+    { url = "https://files.pythonhosted.org/packages/e2/d2/27be1201488323d0ff0c99fb966a0522b2736f79bd5a5b7b99526fca3d98/uharfbuzz-0.53.3-pp311-pypy311_pp73-macosx_10_15_x86_64.whl", hash = "sha256:6f0ad2812303d2c7ccff596fd6c9d5629874f3a83f30255e11639c9b7ba4e89d", size = 1335822, upload-time = "2026-01-24T13:10:34.774Z" },
+    { url = "https://files.pythonhosted.org/packages/70/99/53e39bcd4dec5981eb70a6a76285a862c8a76b80cd52e8f40fe51adab032/uharfbuzz-0.53.3-pp311-pypy311_pp73-macosx_11_0_arm64.whl", hash = "sha256:757d9ed1841912e8f229319f335cf7dd25a2fd377e444bda9deb720617192e12", size = 1237560, upload-time = "2026-01-24T13:10:36.971Z" },
+    { url = "https://files.pythonhosted.org/packages/aa/2b/04d8cde466acfe70373d4f489da5c6eab0aba07d50442dd21217cb0fd167/uharfbuzz-0.53.3-pp311-pypy311_pp73-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:5d3a0b824811bd1be129356818e6cdbf0e4b056bb60aa9a5eb270bff9d21f24c", size = 1497923, upload-time = "2026-01-24T13:10:38.743Z" },
+    { url = "https://files.pythonhosted.org/packages/f3/01/a250521491bc995609275e0062c552b16f437a3ce15de83250176245093e/uharfbuzz-0.53.3-pp311-pypy311_pp73-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:9211d798b2921a99b8c34e810676137f66372d3b5447765b72d969bdfa6abe6a", size = 1556794, upload-time = "2026-01-24T13:10:40.262Z" },
+]
+
 [[package]]
 name = "ujson"
 version = "5.11.0"