Bump scikit-learn from 1.7.2 to 1.8.0 in the data-nlp-search group

Bumps the data-nlp-search group with 1 update: [scikit-learn](https://github.com/scikit-learn/scikit-learn).


Updates `scikit-learn` from 1.7.2 to 1.8.0
- [Release notes](https://github.com/scikit-learn/scikit-learn/releases)
- [Commits](https://github.com/scikit-learn/scikit-learn/compare/1.7.2...1.8.0)

---
updated-dependencies:
- dependency-name: scikit-learn
  dependency-version: 1.8.0
  dependency-type: direct:production
  update-type: version-update:semver-minor
  dependency-group: data-nlp-search
...

Signed-off-by: dependabot[bot] <support@github.com>

.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}"

.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

docs/api.md

@@ -369,38 +369,41 @@ operations, using the endpoint: `/api/bulk_edit_objects/`, which requires a json
 
 ## API Versioning
 
-The REST API is versioned.
+The REST API is versioned since Paperless-ngx 1.3.0.
 
 -   Versioning ensures that changes to the API don't break older
     clients.
 -   Clients specify the specific version of the API they wish to use
     with every request and Paperless will handle the request using the
     specified API version.
--   Even if the underlying data model changes, supported older API
-    versions continue to serve compatible data.
--   If no version is specified, Paperless serves the configured default
-    API version (currently `10`).
--   Supported API versions are currently `9` and `10`.
+-   Even if the underlying data model changes, older API versions will
+    always serve compatible data.
+-   If no version is specified, Paperless will serve version 1 to ensure
+    compatibility with older clients that do not request a specific API
+    version.
 
 API versions are specified by submitting an additional HTTP `Accept`
 header with every request:
 
 ```
-Accept: application/json; version=10
+Accept: application/json; version=6
 ```
 
-If an invalid version is specified, Paperless responds with
-`406 Not Acceptable` and an error message in the body.
+If an invalid version is specified, Paperless 1.3.0 will respond with
+"406 Not Acceptable" and an error message in the body. Earlier
+versions of Paperless will serve API version 1 regardless of whether a
+version is specified via the `Accept` header.
 
 If a client wishes to verify whether it is compatible with any given
 server, the following procedure should be performed:
 
-1.  Perform an _authenticated_ request against any API endpoint. The
-    server will add two custom headers to the response:
+1.  Perform an _authenticated_ request against any API endpoint. If the
+    server is on version 1.3.0 or newer, the server will add two custom
+    headers to the response:
 
     ```
-    X-Api-Version: 10
-    X-Version: <server-version>
+    X-Api-Version: 2
+    X-Version: 1.3.0
     ```
 
 2.  Determine whether the client is compatible with this server based on

pyproject.toml

@@ -71,7 +71,7 @@ dependencies = [
   "rapidfuzz~=3.14.0",
   "redis[hiredis]~=5.2.1",
   "regex>=2025.9.18",
-  "scikit-learn~=1.7.0",
+  "scikit-learn~=1.8.0",
   "sentence-transformers>=4.1",
   "setproctitle~=1.3.4",
   "tika-client~=0.10.0",

src-ui/messages.xlf

@@ -3434,46 +3434,39 @@
           <context context-type="linenumber">9</context>
         </context-group>
       </trans-unit>
-      <trans-unit id="6705735915615634619" datatype="html">
-        <source>{VAR_PLURAL, plural, =1 {One page} other {<x id="INTERPOLATION"/> pages}}</source>
-        <context-group purpose="location">
-          <context context-type="sourcefile">src/app/components/common/confirm-dialog/merge-confirm-dialog/merge-confirm-dialog.component.html</context>
-          <context context-type="linenumber">25</context>
-        </context-group>
-      </trans-unit>
       <trans-unit id="7508164375697837821" datatype="html">
         <source>Use metadata from:</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/common/confirm-dialog/merge-confirm-dialog/merge-confirm-dialog.component.html</context>
-          <context context-type="linenumber">34</context>
+          <context context-type="linenumber">22</context>
         </context-group>
       </trans-unit>
       <trans-unit id="2020403212524346652" datatype="html">
         <source>Regenerate all metadata</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/common/confirm-dialog/merge-confirm-dialog/merge-confirm-dialog.component.html</context>
-          <context context-type="linenumber">36</context>
+          <context context-type="linenumber">24</context>
         </context-group>
       </trans-unit>
       <trans-unit id="2710430925353472741" datatype="html">
         <source>Try to include archive version in merge for non-PDF files</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/common/confirm-dialog/merge-confirm-dialog/merge-confirm-dialog.component.html</context>
-          <context context-type="linenumber">44</context>
+          <context context-type="linenumber">32</context>
         </context-group>
       </trans-unit>
       <trans-unit id="5612366187076076264" datatype="html">
         <source>Delete original documents after successful merge</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/common/confirm-dialog/merge-confirm-dialog/merge-confirm-dialog.component.html</context>
-          <context context-type="linenumber">48</context>
+          <context context-type="linenumber">36</context>
         </context-group>
       </trans-unit>
       <trans-unit id="5138283234724909648" datatype="html">
         <source>Note that only PDFs will be included.</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/common/confirm-dialog/merge-confirm-dialog/merge-confirm-dialog.component.html</context>
-          <context context-type="linenumber">51</context>
+          <context context-type="linenumber">39</context>
         </context-group>
       </trans-unit>
       <trans-unit id="1309641780471803652" datatype="html">

src-ui/src/app/components/common/confirm-dialog/merge-confirm-dialog/merge-confirm-dialog.component.html

@@ -10,22 +10,10 @@
         <ul class="list-group"
             cdkDropList
             (cdkDropListDropped)="onDrop($event)">
-            @for (document of documents; track document.id) {
-                <li class="list-group-item d-flex align-items-center" cdkDrag>
+            @for (documentID of documentIDs; track documentID) {
+                <li class="list-group-item" cdkDrag>
                     <i-bs name="grip-vertical" class="me-2"></i-bs>
-                    <div class="d-flex flex-column">
-                        <div>
-                          @if (document.correspondent) {
-                            <b>{{document.correspondent | correspondentName | async}}: </b>
-                          }{{document.title}}
-                        </div>
-                        <small class="text-muted">
-                          {{document.created | customDate:'mediumDate'}}
-                          @if (document.page_count) {
-                            | {document.page_count, plural, =1 {One page} other {{{document.page_count}} pages}}
-                          }
-                        </small>
-                    </div>
+                    {{getDocument(documentID)?.title}}
                 </li>
             }
         </ul>

src-ui/src/app/components/common/confirm-dialog/merge-confirm-dialog/merge-confirm-dialog.component.ts

@@ -3,14 +3,11 @@ import {
   DragDropModule,
   moveItemInArray,
 } from '@angular/cdk/drag-drop'
-import { AsyncPipe } from '@angular/common'
 import { Component, OnInit, inject } from '@angular/core'
 import { FormsModule, ReactiveFormsModule } from '@angular/forms'
 import { NgxBootstrapIconsModule } from 'ngx-bootstrap-icons'
 import { takeUntil } from 'rxjs'
 import { Document } from 'src/app/data/document'
-import { CorrespondentNamePipe } from 'src/app/pipes/correspondent-name.pipe'
-import { CustomDatePipe } from 'src/app/pipes/custom-date.pipe'
 import { PermissionsService } from 'src/app/services/permissions.service'
 import { DocumentService } from 'src/app/services/rest/document.service'
 import { ConfirmDialogComponent } from '../confirm-dialog.component'
@@ -20,9 +17,6 @@ import { ConfirmDialogComponent } from '../confirm-dialog.component'
   templateUrl: './merge-confirm-dialog.component.html',
   styleUrl: './merge-confirm-dialog.component.scss',
   imports: [
-    AsyncPipe,
-    CorrespondentNamePipe,
-    CustomDatePipe,
     DragDropModule,
     FormsModule,
     ReactiveFormsModule,

src/documents/management/commands/document_exporter.py

@@ -3,6 +3,7 @@ import json
 import os
 import shutil
 import tempfile
+from itertools import chain
 from itertools import islice
 from pathlib import Path
 from typing import TYPE_CHECKING
@@ -80,87 +81,6 @@ def serialize_queryset_batched(
         yield serializers.serialize("python", chunk)
 
 
-class StreamingManifestWriter:
-    """Incrementally writes a JSON array to a file, one record at a time.
-
-    Writes to <target>.tmp first; on close(), optionally BLAKE2b-compares
-    with the existing file (--compare-json) and renames or discards accordingly.
-    On exception, discard() deletes the tmp file and leaves the original intact.
-    """
-
-    def __init__(
-        self,
-        path: Path,
-        *,
-        compare_json: bool = False,
-        files_in_export_dir: "set[Path] | None" = None,
-    ) -> None:
-        self._path = path.resolve()
-        self._tmp_path = self._path.with_suffix(self._path.suffix + ".tmp")
-        self._compare_json = compare_json
-        self._files_in_export_dir: set[Path] = (
-            files_in_export_dir if files_in_export_dir is not None else set()
-        )
-        self._file = None
-        self._first = True
-
-    def open(self) -> None:
-        self._path.parent.mkdir(parents=True, exist_ok=True)
-        self._file = self._tmp_path.open("w", encoding="utf-8")
-        self._file.write("[")
-        self._first = True
-
-    def write_record(self, record: dict) -> None:
-        if not self._first:
-            self._file.write(",\n")
-        else:
-            self._first = False
-        self._file.write(
-            json.dumps(record, cls=DjangoJSONEncoder, indent=2, ensure_ascii=False),
-        )
-
-    def write_batch(self, records: list[dict]) -> None:
-        for record in records:
-            self.write_record(record)
-
-    def close(self) -> None:
-        if self._file is None:
-            return
-        self._file.write("\n]")
-        self._file.close()
-        self._file = None
-        self._finalize()
-
-    def discard(self) -> None:
-        if self._file is not None:
-            self._file.close()
-            self._file = None
-        if self._tmp_path.exists():
-            self._tmp_path.unlink()
-
-    def _finalize(self) -> None:
-        """Compare with existing file (if --compare-json) then rename or discard tmp."""
-        if self._path in self._files_in_export_dir:
-            self._files_in_export_dir.remove(self._path)
-            if self._compare_json:
-                existing_hash = hashlib.blake2b(self._path.read_bytes()).hexdigest()
-                new_hash = hashlib.blake2b(self._tmp_path.read_bytes()).hexdigest()
-                if existing_hash == new_hash:
-                    self._tmp_path.unlink()
-                    return
-        self._tmp_path.rename(self._path)
-
-    def __enter__(self) -> "StreamingManifestWriter":
-        self.open()
-        return self
-
-    def __exit__(self, exc_type, exc_val, exc_tb) -> None:
-        if exc_type is not None:
-            self.discard()
-        else:
-            self.close()
-
-
 class Command(CryptMixin, BaseCommand):
     help = (
         "Decrypt and rename all files in our collection into a given target "
@@ -402,83 +322,95 @@ class Command(CryptMixin, BaseCommand):
         if settings.AUDIT_LOG_ENABLED:
             manifest_key_to_object_query["log_entries"] = LogEntry.objects.all()
 
-        # Crypto setup before streaming begins
-        if self.passphrase:
-            self.setup_crypto(passphrase=self.passphrase)
-        elif MailAccount.objects.count() > 0 or SocialToken.objects.count() > 0:
-            self.stdout.write(
-                self.style.NOTICE(
-                    "No passphrase was given, sensitive fields will be in plaintext",
-                ),
-            )
+        with transaction.atomic():
+            manifest_dict = {}
 
-        document_manifest: list[dict] = []
-        manifest_path = (self.target / "manifest.json").resolve()
-
-        with StreamingManifestWriter(
-            manifest_path,
-            compare_json=self.compare_json,
-            files_in_export_dir=self.files_in_export_dir,
-        ) as writer:
-            with transaction.atomic():
-                for key, qs in manifest_key_to_object_query.items():
-                    if key == "documents":
-                        # Accumulate for file-copy loop; written to manifest after
-                        for batch in serialize_queryset_batched(
-                            qs,
+            # Build an overall manifest
+            for key, object_query in manifest_key_to_object_query.items():
+                manifest_dict[key] = list(
+                    chain.from_iterable(
+                        serialize_queryset_batched(
+                            object_query,
                             batch_size=self.batch_size,
-                        ):
-                            for record in batch:
-                                self._encrypt_record_inline(record)
-                            document_manifest.extend(batch)
-                    elif self.split_manifest and key in (
-                        "notes",
-                        "custom_field_instances",
-                    ):
-                        # Written per-document in _write_split_manifest
-                        pass
-                    else:
-                        for batch in serialize_queryset_batched(
-                            qs,
-                            batch_size=self.batch_size,
-                        ):
-                            for record in batch:
-                                self._encrypt_record_inline(record)
-                            writer.write_batch(batch)
-
-            document_map: dict[int, Document] = {
-                d.pk: d for d in Document.objects.order_by("id")
-            }
-
-            # 3. Export files from each document
-            for document_dict in tqdm.tqdm(
-                document_manifest,
-                total=len(document_manifest),
-                disable=self.no_progress_bar,
-            ):
-                document = document_map[document_dict["pk"]]
-
-                # 3.1. generate a unique filename
-                base_name = self.generate_base_name(document)
-
-                # 3.2. write filenames into manifest
-                original_target, thumbnail_target, archive_target = (
-                    self.generate_document_targets(document, base_name, document_dict)
+                        ),
+                    ),
                 )
 
-                # 3.3. write files to target folder
-                if not self.data_only:
-                    self.copy_document_files(
-                        document,
-                        original_target,
-                        thumbnail_target,
-                        archive_target,
-                    )
+            self.encrypt_secret_fields(manifest_dict)
 
-                if self.split_manifest:
-                    self._write_split_manifest(document_dict, document, base_name)
-                else:
-                    writer.write_record(document_dict)
+            # These are treated specially and included in the per-document manifest
+            # if that setting is enabled.  Otherwise, they are just exported to the bulk
+            # manifest
+            document_map: dict[int, Document] = {
+                d.pk: d for d in manifest_key_to_object_query["documents"]
+            }
+            document_manifest = manifest_dict["documents"]
+
+        # 3. Export files from each document
+        for index, document_dict in tqdm.tqdm(
+            enumerate(document_manifest),
+            total=len(document_manifest),
+            disable=self.no_progress_bar,
+        ):
+            document = document_map[document_dict["pk"]]
+
+            # 3.1. generate a unique filename
+            base_name = self.generate_base_name(document)
+
+            # 3.2. write filenames into manifest
+            original_target, thumbnail_target, archive_target = (
+                self.generate_document_targets(document, base_name, document_dict)
+            )
+
+            # 3.3. write files to target folder
+            if not self.data_only:
+                self.copy_document_files(
+                    document,
+                    original_target,
+                    thumbnail_target,
+                    archive_target,
+                )
+
+            if self.split_manifest:
+                manifest_name = base_name.with_name(f"{base_name.stem}-manifest.json")
+                if self.use_folder_prefix:
+                    manifest_name = Path("json") / manifest_name
+                manifest_name = (self.target / manifest_name).resolve()
+                manifest_name.parent.mkdir(parents=True, exist_ok=True)
+                content = [document_manifest[index]]
+                content += list(
+                    filter(
+                        lambda d: d["fields"]["document"] == document_dict["pk"],
+                        manifest_dict["notes"],
+                    ),
+                )
+                content += list(
+                    filter(
+                        lambda d: d["fields"]["document"] == document_dict["pk"],
+                        manifest_dict["custom_field_instances"],
+                    ),
+                )
+
+                self.check_and_write_json(
+                    content,
+                    manifest_name,
+                )
+
+        # These were exported already
+        if self.split_manifest:
+            del manifest_dict["documents"]
+            del manifest_dict["notes"]
+            del manifest_dict["custom_field_instances"]
+
+        # 4.1 write primary manifest to target folder
+        manifest = []
+        for key, item in manifest_dict.items():
+            manifest.extend(item)
+        manifest_path = (self.target / "manifest.json").resolve()
+        self.check_and_write_json(
+            manifest,
+            manifest_path,
+        )
 
         # 4.2 write version information to target folder
         extra_metadata_path = (self.target / "metadata.json").resolve()
@@ -600,42 +532,6 @@ class Command(CryptMixin, BaseCommand):
                 archive_target,
             )
 
-    def _encrypt_record_inline(self, record: dict) -> None:
-        """Encrypt sensitive fields in a single record, if passphrase is set."""
-        if not self.passphrase:
-            return
-        fields = self.CRYPT_FIELDS_BY_MODEL.get(record.get("model", ""))
-        if fields:
-            for field in fields:
-                if record["fields"].get(field):
-                    record["fields"][field] = self.encrypt_string(
-                        value=record["fields"][field],
-                    )
-
-    def _write_split_manifest(
-        self,
-        document_dict: dict,
-        document: Document,
-        base_name: Path,
-    ) -> None:
-        """Write per-document manifest file for --split-manifest mode."""
-        content = [document_dict]
-        content.extend(
-            serializers.serialize("python", Note.objects.filter(document=document)),
-        )
-        content.extend(
-            serializers.serialize(
-                "python",
-                CustomFieldInstance.objects.filter(document=document),
-            ),
-        )
-        manifest_name = base_name.with_name(f"{base_name.stem}-manifest.json")
-        if self.use_folder_prefix:
-            manifest_name = Path("json") / manifest_name
-        manifest_name = (self.target / manifest_name).resolve()
-        manifest_name.parent.mkdir(parents=True, exist_ok=True)
-        self.check_and_write_json(content, manifest_name)
-
     def check_and_write_json(
         self,
         content: list[dict] | dict,
@@ -653,14 +549,14 @@ class Command(CryptMixin, BaseCommand):
         if target in self.files_in_export_dir:
             self.files_in_export_dir.remove(target)
             if self.compare_json:
-                target_checksum = hashlib.blake2b(target.read_bytes()).hexdigest()
+                target_checksum = hashlib.md5(target.read_bytes()).hexdigest()
                 src_str = json.dumps(
                     content,
                     cls=DjangoJSONEncoder,
                     indent=2,
                     ensure_ascii=False,
                 )
-                src_checksum = hashlib.blake2b(src_str.encode("utf-8")).hexdigest()
+                src_checksum = hashlib.md5(src_str.encode("utf-8")).hexdigest()
                 if src_checksum == target_checksum:
                     perform_write = False
 
@@ -710,3 +606,28 @@ class Command(CryptMixin, BaseCommand):
         if perform_copy:
             target.parent.mkdir(parents=True, exist_ok=True)
             copy_file_with_basic_stats(source, target)
+
+    def encrypt_secret_fields(self, manifest: dict) -> None:
+        """
+        Encrypts certain fields in the export.  Currently limited to the mail account password
+        """
+
+        if self.passphrase:
+            self.setup_crypto(passphrase=self.passphrase)
+
+            for crypt_config in self.CRYPT_FIELDS:
+                exporter_key = crypt_config["exporter_key"]
+                crypt_fields = crypt_config["fields"]
+                for manifest_record in manifest[exporter_key]:
+                    for field in crypt_fields:
+                        if manifest_record["fields"][field]:
+                            manifest_record["fields"][field] = self.encrypt_string(
+                                value=manifest_record["fields"][field],
+                            )
+
+        elif MailAccount.objects.count() > 0 or SocialToken.objects.count() > 0:
+            self.stdout.write(
+                self.style.NOTICE(
+                    "No passphrase was given, sensitive fields will be in plaintext",
+                ),
+            )

src/documents/management/commands/mixins.py

@@ -71,7 +71,7 @@ class CryptMixin:
     key_size = 32
     kdf_algorithm = "pbkdf2_sha256"
 
-    CRYPT_FIELDS: list[CryptFields] = [
+    CRYPT_FIELDS: CryptFields = [
         {
             "exporter_key": "mail_accounts",
             "model_name": "paperless_mail.mailaccount",
@@ -89,10 +89,6 @@ class CryptMixin:
             ],
         },
     ]
-    # O(1) lookup for per-record encryption; derived from CRYPT_FIELDS at class definition time
-    CRYPT_FIELDS_BY_MODEL: dict[str, list[str]] = {
-        cfg["model_name"]: cfg["fields"] for cfg in CRYPT_FIELDS
-    }
 
     def get_crypt_params(self) -> dict[str, dict[str, str | int]]:
         return {

src/documents/serialisers.py

@@ -703,6 +703,15 @@ class StoragePathField(serializers.PrimaryKeyRelatedField):
 
 
 class CustomFieldSerializer(serializers.ModelSerializer):
+    def __init__(self, *args, **kwargs):
+        context = kwargs.get("context")
+        self.api_version = int(
+            context.get("request").version
+            if context and context.get("request")
+            else settings.REST_FRAMEWORK["DEFAULT_VERSION"],
+        )
+        super().__init__(*args, **kwargs)
+
     data_type = serializers.ChoiceField(
         choices=CustomField.FieldDataType,
         read_only=False,
@@ -782,6 +791,38 @@ class CustomFieldSerializer(serializers.ModelSerializer):
             )
         return super().validate(attrs)
 
+    def to_internal_value(self, data):
+        ret = super().to_internal_value(data)
+
+        if (
+            self.api_version < 7
+            and ret.get("data_type", "") == CustomField.FieldDataType.SELECT
+            and isinstance(ret.get("extra_data", {}).get("select_options"), list)
+        ):
+            ret["extra_data"]["select_options"] = [
+                {
+                    "label": option,
+                    "id": get_random_string(length=16),
+                }
+                for option in ret["extra_data"]["select_options"]
+            ]
+
+        return ret
+
+    def to_representation(self, instance):
+        ret = super().to_representation(instance)
+
+        if (
+            self.api_version < 7
+            and instance.data_type == CustomField.FieldDataType.SELECT
+        ):
+            # Convert the select options with ids to a list of strings
+            ret["extra_data"]["select_options"] = [
+                option["label"] for option in ret["extra_data"]["select_options"]
+            ]
+
+        return ret
+
 
 class ReadWriteSerializerMethodField(serializers.SerializerMethodField):
     """
@@ -896,6 +937,50 @@ class CustomFieldInstanceSerializer(serializers.ModelSerializer):
 
         return data
 
+    def get_api_version(self):
+        return int(
+            self.context.get("request").version
+            if self.context.get("request")
+            else settings.REST_FRAMEWORK["DEFAULT_VERSION"],
+        )
+
+    def to_internal_value(self, data):
+        ret = super().to_internal_value(data)
+
+        if (
+            self.get_api_version() < 7
+            and ret.get("field").data_type == CustomField.FieldDataType.SELECT
+            and ret.get("value") is not None
+        ):
+            # Convert the index of the option in the field.extra_data["select_options"]
+            # list to the options unique id
+            ret["value"] = ret.get("field").extra_data["select_options"][ret["value"]][
+                "id"
+            ]
+
+        return ret
+
+    def to_representation(self, instance):
+        ret = super().to_representation(instance)
+
+        if (
+            self.get_api_version() < 7
+            and instance.field.data_type == CustomField.FieldDataType.SELECT
+        ):
+            # return the index of the option in the field.extra_data["select_options"] list
+            ret["value"] = next(
+                (
+                    idx
+                    for idx, option in enumerate(
+                        instance.field.extra_data["select_options"],
+                    )
+                    if option["id"] == instance.value
+                ),
+                None,
+            )
+
+        return ret
+
     class Meta:
         model = CustomFieldInstance
         fields = [
@@ -919,6 +1004,20 @@ class NotesSerializer(serializers.ModelSerializer):
         fields = ["id", "note", "created", "user"]
         ordering = ["-created"]
 
+    def to_representation(self, instance):
+        ret = super().to_representation(instance)
+
+        request = self.context.get("request")
+        api_version = int(
+            request.version if request else settings.REST_FRAMEWORK["DEFAULT_VERSION"],
+        )
+
+        if api_version < 8 and "user" in ret:
+            user_id = ret["user"]["id"]
+            ret["user"] = user_id
+
+        return ret
+
 
 def _get_viewable_duplicates(
     document: Document,
@@ -1073,6 +1172,22 @@ class DocumentSerializer(
             doc["content"] = getattr(instance, "effective_content") or ""
         if self.truncate_content and "content" in self.fields:
             doc["content"] = doc.get("content")[0:550]
+
+        request = self.context.get("request")
+        api_version = int(
+            request.version if request else settings.REST_FRAMEWORK["DEFAULT_VERSION"],
+        )
+
+        if api_version < 9 and "created" in self.fields:
+            # provide created as a datetime for backwards compatibility
+            from django.utils import timezone
+
+            doc["created"] = timezone.make_aware(
+                datetime.combine(
+                    instance.created,
+                    datetime.min.time(),
+                ),
+            ).isoformat()
         return doc
 
     def to_internal_value(self, data):
@@ -1325,124 +1440,6 @@ class SavedViewSerializer(OwnedObjectSerializer):
             "set_permissions",
         ]
 
-    def _get_api_version(self) -> int:
-        request = self.context.get("request")
-        return int(
-            request.version if request else settings.REST_FRAMEWORK["DEFAULT_VERSION"],
-        )
-
-    def _update_legacy_visibility_preferences(
-        self,
-        saved_view_id: int,
-        *,
-        show_on_dashboard: bool | None,
-        show_in_sidebar: bool | None,
-    ) -> UiSettings | None:
-        if show_on_dashboard is None and show_in_sidebar is None:
-            return None
-
-        request = self.context.get("request")
-        user = request.user if request else self.user
-        if user is None:
-            return None
-
-        ui_settings, _ = UiSettings.objects.get_or_create(
-            user=user,
-            defaults={"settings": {}},
-        )
-        current_settings = (
-            ui_settings.settings if isinstance(ui_settings.settings, dict) else {}
-        )
-        current_settings = dict(current_settings)
-
-        saved_views_settings = current_settings.get("saved_views")
-        if isinstance(saved_views_settings, dict):
-            saved_views_settings = dict(saved_views_settings)
-        else:
-            saved_views_settings = {}
-
-        dashboard_ids = {
-            int(raw_id)
-            for raw_id in saved_views_settings.get("dashboard_views_visible_ids", [])
-            if str(raw_id).isdigit()
-        }
-        sidebar_ids = {
-            int(raw_id)
-            for raw_id in saved_views_settings.get("sidebar_views_visible_ids", [])
-            if str(raw_id).isdigit()
-        }
-
-        if show_on_dashboard is not None:
-            if show_on_dashboard:
-                dashboard_ids.add(saved_view_id)
-            else:
-                dashboard_ids.discard(saved_view_id)
-        if show_in_sidebar is not None:
-            if show_in_sidebar:
-                sidebar_ids.add(saved_view_id)
-            else:
-                sidebar_ids.discard(saved_view_id)
-
-        saved_views_settings["dashboard_views_visible_ids"] = sorted(dashboard_ids)
-        saved_views_settings["sidebar_views_visible_ids"] = sorted(sidebar_ids)
-        current_settings["saved_views"] = saved_views_settings
-        ui_settings.settings = current_settings
-        ui_settings.save(update_fields=["settings"])
-        return ui_settings
-
-    def to_representation(self, instance):
-        # TODO: remove this and related backwards compatibility code when API v9 is dropped
-        ret = super().to_representation(instance)
-        request = self.context.get("request")
-        api_version = self._get_api_version()
-
-        if api_version < 10:
-            dashboard_ids = set()
-            sidebar_ids = set()
-            user = request.user if request else None
-            if user is not None and hasattr(user, "ui_settings"):
-                ui_settings = user.ui_settings.settings or None
-                saved_views = None
-                if isinstance(ui_settings, dict):
-                    saved_views = ui_settings.get("saved_views", {})
-                if isinstance(saved_views, dict):
-                    dashboard_ids = set(
-                        saved_views.get("dashboard_views_visible_ids", []),
-                    )
-                    sidebar_ids = set(
-                        saved_views.get("sidebar_views_visible_ids", []),
-                    )
-            ret["show_on_dashboard"] = instance.id in dashboard_ids
-            ret["show_in_sidebar"] = instance.id in sidebar_ids
-
-        return ret
-
-    def to_internal_value(self, data):
-        # TODO: remove this and related backwards compatibility code when API v9 is dropped
-        api_version = self._get_api_version()
-        if api_version >= 10:
-            return super().to_internal_value(data)
-
-        normalized_data = data.copy()
-        legacy_visibility_fields = {}
-        boolean_field = serializers.BooleanField()
-
-        for field_name in ("show_on_dashboard", "show_in_sidebar"):
-            if field_name in normalized_data:
-                try:
-                    legacy_visibility_fields[field_name] = (
-                        boolean_field.to_internal_value(
-                            normalized_data.get(field_name),
-                        )
-                    )
-                except serializers.ValidationError as exc:
-                    raise serializers.ValidationError({field_name: exc.detail})
-                del normalized_data[field_name]
-
-        ret = super().to_internal_value(normalized_data)
-        ret.update(legacy_visibility_fields)
-        return ret
-
     def validate(self, attrs):
         attrs = super().validate(attrs)
         if "display_fields" in attrs and attrs["display_fields"] is not None:
@@ -1462,9 +1459,6 @@ class SavedViewSerializer(OwnedObjectSerializer):
         return attrs
 
     def update(self, instance, validated_data):
-        request = self.context.get("request")
-        show_on_dashboard = validated_data.pop("show_on_dashboard", None)
-        show_in_sidebar = validated_data.pop("show_in_sidebar", None)
         if "filter_rules" in validated_data:
             rules_data = validated_data.pop("filter_rules")
         else:
@@ -1486,19 +1480,9 @@ class SavedViewSerializer(OwnedObjectSerializer):
             SavedViewFilterRule.objects.filter(saved_view=instance).delete()
             for rule_data in rules_data:
                 SavedViewFilterRule.objects.create(saved_view=instance, **rule_data)
-        ui_settings = self._update_legacy_visibility_preferences(
-            instance.id,
-            show_on_dashboard=show_on_dashboard,
-            show_in_sidebar=show_in_sidebar,
-        )
-        if request is not None and ui_settings is not None:
-            request.user.ui_settings = ui_settings
         return instance
 
     def create(self, validated_data):
-        request = self.context.get("request")
-        show_on_dashboard = validated_data.pop("show_on_dashboard", None)
-        show_in_sidebar = validated_data.pop("show_in_sidebar", None)
         rules_data = validated_data.pop("filter_rules")
         if "user" in validated_data:
             # backwards compatibility
@@ -1506,13 +1490,6 @@ class SavedViewSerializer(OwnedObjectSerializer):
         saved_view = super().create(validated_data)
         for rule_data in rules_data:
             SavedViewFilterRule.objects.create(saved_view=saved_view, **rule_data)
-        ui_settings = self._update_legacy_visibility_preferences(
-            saved_view.id,
-            show_on_dashboard=show_on_dashboard,
-            show_in_sidebar=show_in_sidebar,
-        )
-        if request is not None and ui_settings is not None:
-            request.user.ui_settings = ui_settings
         return saved_view
 
 

src/documents/tests/test_api_custom_fields.py

@@ -323,6 +323,113 @@ class TestCustomFieldsAPI(DirectoriesMixin, APITestCase):
 
         mock_delay.assert_called_once_with(cf_select)
 
+    def test_custom_field_select_old_version(self) -> None:
+        """
+        GIVEN:
+            - Nothing
+        WHEN:
+            - API post request is made for custom fields with api version header < 7
+            - API get request is made for custom fields with api version header < 7
+        THEN:
+            - The select options are created with unique ids
+            - The select options are returned in the old format
+        """
+        resp = self.client.post(
+            self.ENDPOINT,
+            headers={"Accept": "application/json; version=6"},
+            data=json.dumps(
+                {
+                    "data_type": "select",
+                    "name": "Select Field",
+                    "extra_data": {
+                        "select_options": [
+                            "Option 1",
+                            "Option 2",
+                        ],
+                    },
+                },
+            ),
+            content_type="application/json",
+        )
+        self.assertEqual(resp.status_code, status.HTTP_201_CREATED)
+
+        field = CustomField.objects.get(name="Select Field")
+        self.assertEqual(
+            field.extra_data["select_options"],
+            [
+                {"label": "Option 1", "id": ANY},
+                {"label": "Option 2", "id": ANY},
+            ],
+        )
+
+        resp = self.client.get(
+            f"{self.ENDPOINT}{field.id}/",
+            headers={"Accept": "application/json; version=6"},
+        )
+        self.assertEqual(resp.status_code, status.HTTP_200_OK)
+
+        data = resp.json()
+        self.assertEqual(
+            data["extra_data"]["select_options"],
+            [
+                "Option 1",
+                "Option 2",
+            ],
+        )
+
+    def test_custom_field_select_value_old_version(self) -> None:
+        """
+        GIVEN:
+            - Existing document with custom field select
+        WHEN:
+            - API post request is made to add the field for document with api version header < 7
+            - API get request is made for document with api version header < 7
+        THEN:
+            - The select value is returned in the old format, the index of the option
+        """
+        custom_field_select = CustomField.objects.create(
+            name="Select Field",
+            data_type=CustomField.FieldDataType.SELECT,
+            extra_data={
+                "select_options": [
+                    {"label": "Option 1", "id": "abc-123"},
+                    {"label": "Option 2", "id": "def-456"},
+                ],
+            },
+        )
+
+        doc = Document.objects.create(
+            title="WOW",
+            content="the content",
+            checksum="123",
+            mime_type="application/pdf",
+        )
+
+        resp = self.client.patch(
+            f"/api/documents/{doc.id}/",
+            headers={"Accept": "application/json; version=6"},
+            data=json.dumps(
+                {
+                    "custom_fields": [
+                        {"field": custom_field_select.id, "value": 1},
+                    ],
+                },
+            ),
+            content_type="application/json",
+        )
+        self.assertEqual(resp.status_code, status.HTTP_200_OK)
+        doc.refresh_from_db()
+        self.assertEqual(doc.custom_fields.first().value, "def-456")
+
+        resp = self.client.get(
+            f"/api/documents/{doc.id}/",
+            headers={"Accept": "application/json; version=6"},
+        )
+        self.assertEqual(resp.status_code, status.HTTP_200_OK)
+
+        data = resp.json()
+        self.assertEqual(data["custom_fields"][0]["value"], 1)
+
     def test_create_custom_field_monetary_validation(self) -> None:
         """
         GIVEN:

src/documents/tests/test_api_documents.py

@@ -41,7 +41,6 @@ from documents.models import SavedView
 from documents.models import ShareLink
 from documents.models import StoragePath
 from documents.models import Tag
-from documents.models import UiSettings
 from documents.models import Workflow
 from documents.models import WorkflowAction
 from documents.models import WorkflowTrigger
@@ -177,7 +176,7 @@ class TestDocumentApi(DirectoriesMixin, DocumentConsumeDelayMixin, APITestCase):
         results = response.data["results"]
         self.assertEqual(len(results[0]), 0)
 
-    def test_document_fields_respects_created(self) -> None:
+    def test_document_fields_api_version_8_respects_created(self) -> None:
         Document.objects.create(
             title="legacy",
             checksum="123",
@@ -187,6 +186,7 @@ class TestDocumentApi(DirectoriesMixin, DocumentConsumeDelayMixin, APITestCase):
 
         response = self.client.get(
             "/api/documents/?fields=id",
+            headers={"Accept": "application/json; version=8"},
             format="json",
         )
         self.assertEqual(response.status_code, status.HTTP_200_OK)
@@ -196,22 +196,25 @@ class TestDocumentApi(DirectoriesMixin, DocumentConsumeDelayMixin, APITestCase):
 
         response = self.client.get(
             "/api/documents/?fields=id,created",
+            headers={"Accept": "application/json; version=8"},
             format="json",
         )
         self.assertEqual(response.status_code, status.HTTP_200_OK)
         results = response.data["results"]
         self.assertIn("id", results[0])
         self.assertIn("created", results[0])
-        self.assertEqual(results[0]["created"], "2024-01-15")
+        self.assertRegex(results[0]["created"], r"^2024-01-15T00:00:00.*$")
 
-    def test_document_created_format(self) -> None:
+    def test_document_legacy_created_format(self) -> None:
         """
         GIVEN:
             - Existing document
         WHEN:
-            - Document is requested
+            - Document is requested with api version ≥ 9
+            - Document is requested with api version < 9
         THEN:
             - Document created field is returned as date
+            - Document created field is returned as datetime
         """
         doc = Document.objects.create(
             title="none",
@@ -222,6 +225,14 @@ class TestDocumentApi(DirectoriesMixin, DocumentConsumeDelayMixin, APITestCase):
 
         response = self.client.get(
             f"/api/documents/{doc.pk}/",
+            headers={"Accept": "application/json; version=8"},
+        )
+        self.assertEqual(response.status_code, status.HTTP_200_OK)
+        self.assertRegex(response.data["created"], r"^2023-01-01T00:00:00.*$")
+
+        response = self.client.get(
+            f"/api/documents/{doc.pk}/",
+            headers={"Accept": "application/json; version=9"},
         )
         self.assertEqual(response.status_code, status.HTTP_200_OK)
         self.assertEqual(response.data["created"], "2023-01-01")
@@ -2189,205 +2200,6 @@ class TestDocumentApi(DirectoriesMixin, DocumentConsumeDelayMixin, APITestCase):
         self.assertEqual(response.status_code, status.HTTP_200_OK)
         self.assertEqual(response.data["count"], 0)
 
-    def test_saved_view_api_version_backward_compatibility(self) -> None:
-        """
-        GIVEN:
-            - Saved views and UiSettings with visibility preferences
-        WHEN:
-            - API request with version=9 (legacy)
-            - API request with version=10 (current)
-        THEN:
-            - Version 9 returns show_on_dashboard and show_in_sidebar from UiSettings
-            - Version 10 omits these fields (moved to UiSettings)
-        """
-        v1 = SavedView.objects.create(
-            owner=self.user,
-            name="dashboard_view",
-            sort_field="created",
-        )
-        v2 = SavedView.objects.create(
-            owner=self.user,
-            name="sidebar_view",
-            sort_field="created",
-        )
-        v3 = SavedView.objects.create(
-            owner=self.user,
-            name="hidden_view",
-            sort_field="created",
-        )
-
-        UiSettings.objects.update_or_create(
-            user=self.user,
-            defaults={
-                "settings": {
-                    "saved_views": {
-                        "dashboard_views_visible_ids": [v1.id],
-                        "sidebar_views_visible_ids": [v2.id],
-                    },
-                },
-            },
-        )
-
-        response_v9 = self.client.get(
-            "/api/saved_views/",
-            headers={"Accept": "application/json; version=9"},
-            format="json",
-        )
-        self.assertEqual(response_v9.status_code, status.HTTP_200_OK)
-        results_v9 = {r["id"]: r for r in response_v9.data["results"]}
-        self.assertIn("show_on_dashboard", results_v9[v1.id])
-        self.assertIn("show_in_sidebar", results_v9[v1.id])
-        self.assertTrue(results_v9[v1.id]["show_on_dashboard"])
-        self.assertFalse(results_v9[v1.id]["show_in_sidebar"])
-        self.assertTrue(results_v9[v2.id]["show_in_sidebar"])
-        self.assertFalse(results_v9[v2.id]["show_on_dashboard"])
-        self.assertFalse(results_v9[v3.id]["show_on_dashboard"])
-        self.assertFalse(results_v9[v3.id]["show_in_sidebar"])
-
-        response_v10 = self.client.get(
-            "/api/saved_views/",
-            headers={"Accept": "application/json; version=10"},
-            format="json",
-        )
-        self.assertEqual(response_v10.status_code, status.HTTP_200_OK)
-        results_v10 = {r["id"]: r for r in response_v10.data["results"]}
-        self.assertNotIn("show_on_dashboard", results_v10[v1.id])
-        self.assertNotIn("show_in_sidebar", results_v10[v1.id])
-
-    def test_saved_view_api_version_9_user_without_ui_settings(self) -> None:
-        """
-        GIVEN:
-            - User with no UiSettings and a saved view
-        WHEN:
-            - API request with version=9
-        THEN:
-            - show_on_dashboard and show_in_sidebar are False (default)
-        """
-        SavedView.objects.create(
-            owner=self.user,
-            name="test_view",
-            sort_field="created",
-        )
-        UiSettings.objects.filter(user=self.user).delete()
-
-        response = self.client.get(
-            "/api/saved_views/",
-            headers={"Accept": "application/json; version=9"},
-            format="json",
-        )
-        self.assertEqual(response.status_code, status.HTTP_200_OK)
-        result = response.data["results"][0]
-        self.assertFalse(result["show_on_dashboard"])
-        self.assertFalse(result["show_in_sidebar"])
-
-    def test_saved_view_api_version_9_create_writes_visibility_to_ui_settings(
-        self,
-    ) -> None:
-        """
-        GIVEN:
-            - No UiSettings for the current user
-        WHEN:
-            - A saved view is created through API version 9 with visibility flags
-        THEN:
-            - Visibility is persisted in UiSettings.saved_views
-        """
-        UiSettings.objects.filter(user=self.user).delete()
-
-        response = self.client.post(
-            "/api/saved_views/",
-            {
-                "name": "legacy-v9-create",
-                "sort_field": "created",
-                "filter_rules": [],
-                "show_on_dashboard": True,
-                "show_in_sidebar": False,
-            },
-            headers={"Accept": "application/json; version=9"},
-            format="json",
-        )
-        self.assertEqual(response.status_code, status.HTTP_201_CREATED)
-        self.assertTrue(response.data["show_on_dashboard"])
-        self.assertFalse(response.data["show_in_sidebar"])
-
-        self.user.refresh_from_db()
-        self.assertTrue(hasattr(self.user, "ui_settings"))
-        saved_view_settings = self.user.ui_settings.settings["saved_views"]
-        self.assertListEqual(
-            saved_view_settings["dashboard_views_visible_ids"],
-            [response.data["id"]],
-        )
-        self.assertListEqual(saved_view_settings["sidebar_views_visible_ids"], [])
-
-    def test_saved_view_api_version_9_patch_writes_visibility_to_ui_settings(
-        self,
-    ) -> None:
-        """
-        GIVEN:
-            - Existing saved views and UiSettings visibility ids
-        WHEN:
-            - A saved view is updated through API version 9 visibility flags
-        THEN:
-            - The per-user UiSettings visibility ids are updated
-        """
-        v1 = SavedView.objects.create(
-            owner=self.user,
-            name="legacy-v9-patch-1",
-            sort_field="created",
-        )
-        v2 = SavedView.objects.create(
-            owner=self.user,
-            name="legacy-v9-patch-2",
-            sort_field="created",
-        )
-        UiSettings.objects.update_or_create(
-            user=self.user,
-            defaults={
-                "settings": {
-                    "saved_views": {
-                        "dashboard_views_visible_ids": [v1.id],
-                        "sidebar_views_visible_ids": [v1.id, v2.id],
-                    },
-                },
-            },
-        )
-
-        response = self.client.patch(
-            f"/api/saved_views/{v1.id}/",
-            {
-                "show_on_dashboard": False,
-            },
-            headers={"Accept": "application/json; version=9"},
-            format="json",
-        )
-        self.assertEqual(response.status_code, status.HTTP_200_OK)
-        self.assertFalse(response.data["show_on_dashboard"])
-        self.assertTrue(response.data["show_in_sidebar"])
-
-        self.user.refresh_from_db()
-        saved_view_settings = self.user.ui_settings.settings["saved_views"]
-        self.assertListEqual(saved_view_settings["dashboard_views_visible_ids"], [])
-        self.assertListEqual(
-            saved_view_settings["sidebar_views_visible_ids"],
-            [v1.id, v2.id],
-        )
-
-        response = self.client.patch(
-            f"/api/saved_views/{v1.id}/",
-            {
-                "show_in_sidebar": False,
-            },
-            headers={"Accept": "application/json; version=9"},
-            format="json",
-        )
-        self.assertEqual(response.status_code, status.HTTP_200_OK)
-        self.assertFalse(response.data["show_on_dashboard"])
-        self.assertFalse(response.data["show_in_sidebar"])
-
-        self.user.refresh_from_db()
-        saved_view_settings = self.user.ui_settings.settings["saved_views"]
-        self.assertListEqual(saved_view_settings["dashboard_views_visible_ids"], [])
-        self.assertListEqual(saved_view_settings["sidebar_views_visible_ids"], [v2.id])
-
     def test_saved_view_create_update_patch(self) -> None:
         User.objects.create_user("user1")
 
@@ -2791,6 +2603,26 @@ class TestDocumentApi(DirectoriesMixin, DocumentConsumeDelayMixin, APITestCase):
             },
         )
 
+    def test_docnote_serializer_v7(self) -> None:
+        doc = Document.objects.create(
+            title="test",
+            mime_type="application/pdf",
+            content="this is a document which will have notes!",
+        )
+        Note.objects.create(
+            note="This is a note.",
+            document=doc,
+            user=self.user,
+        )
+        self.assertEqual(
+            self.client.get(
+                f"/api/documents/{doc.pk}/",
+                headers={"Accept": "application/json; version=7"},
+                format="json",
+            ).data["notes"][0]["user"],
+            self.user.id,
+        )
+
     def test_create_note(self) -> None:
         """
         GIVEN:
@@ -3559,13 +3391,14 @@ class TestDocumentApi(DirectoriesMixin, DocumentConsumeDelayMixin, APITestCase):
             )
 
 
-class TestDocumentApiTagColors(DirectoriesMixin, APITestCase):
+class TestDocumentApiV2(DirectoriesMixin, APITestCase):
     def setUp(self) -> None:
         super().setUp()
 
         self.user = User.objects.create_superuser(username="temp_admin")
 
         self.client.force_authenticate(user=self.user)
+        self.client.defaults["HTTP_ACCEPT"] = "application/json; version=2"
 
     def test_tag_validate_color(self) -> None:
         self.assertEqual(

src/documents/tests/test_api_filter_by_custom_fields.py

@@ -152,7 +152,7 @@ class TestCustomFieldsSearch(DirectoriesMixin, APITestCase):
             context={
                 "request": types.SimpleNamespace(
                     method="GET",
-                    version="9",
+                    version="7",
                 ),
             },
         )

src/documents/tests/test_management_exporter.py

@@ -753,31 +753,6 @@ class TestExportImport(
             call_command("document_importer", "--no-progress-bar", self.target)
             self.assertEqual(Document.objects.count(), 4)
 
-    def test_folder_prefix_with_split(self) -> None:
-        """
-        GIVEN:
-            - Request to export documents to directory
-        WHEN:
-            - Option use_folder_prefix is used
-            - Option split manifest is used
-        THEN:
-            - Documents can be imported again
-        """
-        shutil.rmtree(Path(self.dirs.media_dir) / "documents")
-        shutil.copytree(
-            Path(__file__).parent / "samples" / "documents",
-            Path(self.dirs.media_dir) / "documents",
-        )
-
-        self._do_export(use_folder_prefix=True, split_manifest=True)
-
-        with paperless_environment():
-            self.assertEqual(Document.objects.count(), 4)
-            Document.objects.all().delete()
-            self.assertEqual(Document.objects.count(), 0)
-            call_command("document_importer", "--no-progress-bar", self.target)
-            self.assertEqual(Document.objects.count(), 4)
-
     def test_import_db_transaction_failed(self) -> None:
         """
         GIVEN:

src/locale/en_US/LC_MESSAGES/django.po

@@ -2,7 +2,7 @@ msgid ""
 msgstr ""
 "Project-Id-Version: paperless-ngx\n"
 "Report-Msgid-Bugs-To: \n"
-"POT-Creation-Date: 2026-03-09 01:51+0000\n"
+"POT-Creation-Date: 2026-03-06 20:00+0000\n"
 "PO-Revision-Date: 2022-02-17 04:17\n"
 "Last-Translator: \n"
 "Language-Team: English\n"
@@ -1299,7 +1299,7 @@ msgstr ""
 msgid "workflow runs"
 msgstr ""
 
-#: documents/serialisers.py:463 documents/serialisers.py:2482
+#: documents/serialisers.py:463 documents/serialisers.py:2344
 msgid "Insufficient permissions."
 msgstr ""
 
@@ -1307,39 +1307,39 @@ msgstr ""
 msgid "Invalid color."
 msgstr ""
 
-#: documents/serialisers.py:2105
+#: documents/serialisers.py:1967
 #, python-format
 msgid "File type %(type)s not supported"
 msgstr ""
 
-#: documents/serialisers.py:2149
+#: documents/serialisers.py:2011
 #, python-format
 msgid "Custom field id must be an integer: %(id)s"
 msgstr ""
 
-#: documents/serialisers.py:2156
+#: documents/serialisers.py:2018
 #, python-format
 msgid "Custom field with id %(id)s does not exist"
 msgstr ""
 
-#: documents/serialisers.py:2173 documents/serialisers.py:2183
+#: documents/serialisers.py:2035 documents/serialisers.py:2045
 msgid ""
 "Custom fields must be a list of integers or an object mapping ids to values."
 msgstr ""
 
-#: documents/serialisers.py:2178
+#: documents/serialisers.py:2040
 msgid "Some custom fields don't exist or were specified twice."
 msgstr ""
 
-#: documents/serialisers.py:2325
+#: documents/serialisers.py:2187
 msgid "Invalid variable detected."
 msgstr ""
 
-#: documents/serialisers.py:2538
+#: documents/serialisers.py:2400
 msgid "Duplicate document identifiers are not allowed."
 msgstr ""
 
-#: documents/serialisers.py:2568 documents/views.py:3328
+#: documents/serialisers.py:2430 documents/views.py:3328
 #, python-format
 msgid "Documents not found: %(ids)s"
 msgstr ""

src/paperless/settings/__init__.py

@@ -379,7 +379,7 @@ REST_FRAMEWORK = {
     "DEFAULT_VERSION": "10",  # match src-ui/src/environments/environment.prod.ts
     # Make sure these are ordered and that the most recent version appears
     # last. See api.md#api-versioning when adding new versions.
-    "ALLOWED_VERSIONS": ["9", "10"],
+    "ALLOWED_VERSIONS": ["2", "3", "4", "5", "6", "7", "8", "9", "10"],
     # DRF Spectacular default schema
     "DEFAULT_SCHEMA_CLASS": "drf_spectacular.openapi.AutoSchema",
 }

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)

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:

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):

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

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):

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
@@ -10,13 +14,15 @@ logger = logging.getLogger("paperless_ai.chat")
 MAX_SINGLE_DOC_CONTEXT_CHARS = 15000
 SINGLE_DOC_SNIPPET_CHARS = 800
 
-CHAT_PROMPT_TMPL = """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:"""
+    Answer:""",
+)
 
 
 def stream_chat_with_documents(query_str: str, documents: list[Document]):
@@ -37,10 +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
-    from llama_index.core.prompts import PromptTemplate
-    from llama_index.core.query_engine import RetrieverQueryEngine
-
     local_index = VectorStoreIndex(nodes=nodes)
     retriever = local_index.as_retriever(
         similarity_top_k=3 if len(documents) == 1 else 5,
@@ -83,8 +85,7 @@ def stream_chat_with_documents(query_str: str, documents: list[Document]):
             for node in top_nodes
         )
 
-    prompt_template = PromptTemplate(template=CHAT_PROMPT_TMPL)
-    prompt = prompt_template.partial_format(
+    prompt = CHAT_PROMPT_TMPL.partial_format(
         context_str=context,
         query_str=query_str,
     ).format(llm=client.llm)

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,

src/paperless_ai/embedding.py

@@ -1,12 +1,13 @@
 import json
 from typing import TYPE_CHECKING
 
-from django.conf import settings
-
 if TYPE_CHECKING:
     from pathlib import Path
 
-    from llama_index.core.base.embeddings.base import BaseEmbedding
+from django.conf import settings
+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
@@ -14,21 +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",

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
@@ -20,10 +34,6 @@ from paperless_ai.embedding import get_embedding_model
 _T = TypeVar("_T")
 IterWrapper = Callable[[Iterable[_T]], Iterable[_T]]
 
-if TYPE_CHECKING:
-    from llama_index.core import VectorStoreIndex
-    from llama_index.core.schema import BaseNode
-
 
 def _identity(iterable: Iterable[_T]) -> Iterable[_T]:
     return iterable
@@ -65,23 +75,12 @@ def get_or_create_storage_context(*, rebuild=False):
         settings.LLM_INDEX_DIR.mkdir(parents=True, exist_ok=True)
 
     if rebuild or not settings.LLM_INDEX_DIR.exists():
-        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
-
         embedding_dim = get_embedding_dim()
         faiss_index = faiss.IndexFlatL2(embedding_dim)
         vector_store = FaissVectorStore(faiss_index=faiss_index)
         docstore = SimpleDocumentStore()
         index_store = SimpleIndexStore()
     else:
-        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
-
         vector_store = FaissVectorStore.from_persist_dir(settings.LLM_INDEX_DIR)
         docstore = SimpleDocumentStore.from_persist_dir(settings.LLM_INDEX_DIR)
         index_store = SimpleIndexStore.from_persist_dir(settings.LLM_INDEX_DIR)
@@ -94,7 +93,7 @@ def get_or_create_storage_context(*, rebuild=False):
     )
 
 
-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.
     """
@@ -113,9 +112,6 @@ 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])
@@ -126,10 +122,6 @@ 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()
@@ -151,7 +143,7 @@ def load_or_build_index(nodes=None):
         )
 
 
-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.
@@ -182,8 +174,6 @@ def update_llm_index(
     """
     Rebuild or update the LLM index.
     """
-    from llama_index.core import VectorStoreIndex
-
     nodes = []
 
     documents = Document.objects.all()
@@ -197,8 +187,6 @@ def update_llm_index(
         (settings.LLM_INDEX_DIR / "meta.json").unlink(missing_ok=True)
         # Rebuild index from scratch
         logger.info("Rebuilding LLM index.")
-        import llama_index.core.settings as llama_settings
-
         embed_model = get_embedding_model()
         llama_settings.Settings.embed_model = embed_model
         storage_context = get_or_create_storage_context(rebuild=True)
@@ -283,10 +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,
@@ -331,8 +315,6 @@ def query_similar_documents(
         else None
     )
 
-    from llama_index.core.retrievers import VectorIndexRetriever
-
     retriever = VectorIndexRetriever(
         index=index,
         similarity_top_k=top_k,

src/paperless_ai/tests/test_ai_indexing.py

@@ -181,11 +181,11 @@ def test_load_or_build_index_builds_when_nodes_given(
 ) -> None:
     with (
         patch(
-            "llama_index.core.load_index_from_storage",
+            "paperless_ai.indexing.load_index_from_storage",
             side_effect=ValueError("Index not found"),
         ),
         patch(
-            "llama_index.core.VectorStoreIndex",
+            "paperless_ai.indexing.VectorStoreIndex",
             return_value=MagicMock(),
         ) as mock_index_cls,
         patch(
@@ -206,7 +206,7 @@ def test_load_or_build_index_raises_exception_when_no_nodes(
 ) -> None:
     with (
         patch(
-            "llama_index.core.load_index_from_storage",
+            "paperless_ai.indexing.load_index_from_storage",
             side_effect=ValueError("Index not found"),
         ),
         patch(
@@ -225,11 +225,11 @@ def test_load_or_build_index_succeeds_when_nodes_given(
 ) -> None:
     with (
         patch(
-            "llama_index.core.load_index_from_storage",
+            "paperless_ai.indexing.load_index_from_storage",
             side_effect=ValueError("Index not found"),
         ),
         patch(
-            "llama_index.core.VectorStoreIndex",
+            "paperless_ai.indexing.VectorStoreIndex",
             return_value=MagicMock(),
         ) as mock_index_cls,
         patch(
@@ -334,7 +334,7 @@ def test_query_similar_documents(
         patch(
             "paperless_ai.indexing.vector_store_file_exists",
         ) as mock_vector_store_exists,
-        patch("llama_index.core.retrievers.VectorIndexRetriever") as mock_retriever_cls,
+        patch("paperless_ai.indexing.VectorIndexRetriever") as mock_retriever_cls,
         patch("paperless_ai.indexing.Document.objects.filter") as mock_filter,
     ):
         mock_storage.return_value = MagicMock()

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,
     ):

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
 
 

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(

uv.lock

@@ -2926,7 +2926,7 @@ requires-dist = [
     { name = "rapidfuzz", specifier = "~=3.14.0" },
     { name = "redis", extras = ["hiredis"], specifier = "~=5.2.1" },
     { name = "regex", specifier = ">=2025.9.18" },
-    { name = "scikit-learn", specifier = "~=1.7.0" },
+    { name = "scikit-learn", specifier = "~=1.8.0" },
     { name = "sentence-transformers", specifier = ">=4.1" },
     { name = "setproctitle", specifier = "~=1.3.4" },
     { name = "tika-client", specifier = "~=0.10.0" },
@@ -4214,7 +4214,7 @@ wheels = [
 
 [[package]]
 name = "scikit-learn"
-version = "1.7.2"
+version = "1.8.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "joblib", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
@@ -4222,28 +4222,32 @@ dependencies = [
     { name = "scipy", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "threadpoolctl", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/98/c2/a7855e41c9d285dfe86dc50b250978105dce513d6e459ea66a6aeb0e1e0c/scikit_learn-1.7.2.tar.gz", hash = "sha256:20e9e49ecd130598f1ca38a1d85090e1a600147b9c02fa6f15d69cb53d968fda", size = 7193136, upload-time = "2025-09-09T08:21:29.075Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/0e/d4/40988bf3b8e34feec1d0e6a051446b1f66225f8529b9309becaeef62b6c4/scikit_learn-1.8.0.tar.gz", hash = "sha256:9bccbb3b40e3de10351f8f5068e105d0f4083b1a65fa07b6634fbc401a6287fd", size = 7335585, upload-time = "2025-12-10T07:08:53.618Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/43/83/564e141eef908a5863a54da8ca342a137f45a0bfb71d1d79704c9894c9d1/scikit_learn-1.7.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:c7509693451651cd7361d30ce4e86a1347493554f172b1c72a39300fa2aea79e", size = 9331967, upload-time = "2025-09-09T08:20:32.421Z" },
-    { url = "https://files.pythonhosted.org/packages/18/d6/ba863a4171ac9d7314c4d3fc251f015704a2caeee41ced89f321c049ed83/scikit_learn-1.7.2-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:0486c8f827c2e7b64837c731c8feff72c0bd2b998067a8a9cbc10643c31f0fe1", size = 8648645, upload-time = "2025-09-09T08:20:34.436Z" },
-    { url = "https://files.pythonhosted.org/packages/ef/0e/97dbca66347b8cf0ea8b529e6bb9367e337ba2e8be0ef5c1a545232abfde/scikit_learn-1.7.2-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:89877e19a80c7b11a2891a27c21c4894fb18e2c2e077815bcade10d34287b20d", size = 9715424, upload-time = "2025-09-09T08:20:36.776Z" },
-    { url = "https://files.pythonhosted.org/packages/f7/32/1f3b22e3207e1d2c883a7e09abb956362e7d1bd2f14458c7de258a26ac15/scikit_learn-1.7.2-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:8da8bf89d4d79aaec192d2bda62f9b56ae4e5b4ef93b6a56b5de4977e375c1f1", size = 9509234, upload-time = "2025-09-09T08:20:38.957Z" },
-    { url = "https://files.pythonhosted.org/packages/a7/aa/3996e2196075689afb9fce0410ebdb4a09099d7964d061d7213700204409/scikit_learn-1.7.2-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:8d91a97fa2b706943822398ab943cde71858a50245e31bc71dba62aab1d60a96", size = 9259818, upload-time = "2025-09-09T08:20:43.19Z" },
-    { url = "https://files.pythonhosted.org/packages/43/5d/779320063e88af9c4a7c2cf463ff11c21ac9c8bd730c4a294b0000b666c9/scikit_learn-1.7.2-cp312-cp312-macosx_12_0_arm64.whl", hash = "sha256:acbc0f5fd2edd3432a22c69bed78e837c70cf896cd7993d71d51ba6708507476", size = 8636997, upload-time = "2025-09-09T08:20:45.468Z" },
-    { url = "https://files.pythonhosted.org/packages/5c/d0/0c577d9325b05594fdd33aa970bf53fb673f051a45496842caee13cfd7fe/scikit_learn-1.7.2-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:e5bf3d930aee75a65478df91ac1225ff89cd28e9ac7bd1196853a9229b6adb0b", size = 9478381, upload-time = "2025-09-09T08:20:47.982Z" },
-    { url = "https://files.pythonhosted.org/packages/82/70/8bf44b933837ba8494ca0fc9a9ab60f1c13b062ad0197f60a56e2fc4c43e/scikit_learn-1.7.2-cp312-cp312-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:b4d6e9deed1a47aca9fe2f267ab8e8fe82ee20b4526b2c0cd9e135cea10feb44", size = 9300296, upload-time = "2025-09-09T08:20:50.366Z" },
-    { url = "https://files.pythonhosted.org/packages/ae/93/a3038cb0293037fd335f77f31fe053b89c72f17b1c8908c576c29d953e84/scikit_learn-1.7.2-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:0b7dacaa05e5d76759fb071558a8b5130f4845166d88654a0f9bdf3eb57851b7", size = 9212382, upload-time = "2025-09-09T08:20:54.731Z" },
-    { url = "https://files.pythonhosted.org/packages/40/dd/9a88879b0c1104259136146e4742026b52df8540c39fec21a6383f8292c7/scikit_learn-1.7.2-cp313-cp313-macosx_12_0_arm64.whl", hash = "sha256:abebbd61ad9e1deed54cca45caea8ad5f79e1b93173dece40bb8e0c658dbe6fe", size = 8592042, upload-time = "2025-09-09T08:20:57.313Z" },
-    { url = "https://files.pythonhosted.org/packages/46/af/c5e286471b7d10871b811b72ae794ac5fe2989c0a2df07f0ec723030f5f5/scikit_learn-1.7.2-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:502c18e39849c0ea1a5d681af1dbcf15f6cce601aebb657aabbfe84133c1907f", size = 9434180, upload-time = "2025-09-09T08:20:59.671Z" },
-    { url = "https://files.pythonhosted.org/packages/f1/fd/df59faa53312d585023b2da27e866524ffb8faf87a68516c23896c718320/scikit_learn-1.7.2-cp313-cp313-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:7a4c328a71785382fe3fe676a9ecf2c86189249beff90bf85e22bdb7efaf9ae0", size = 9283660, upload-time = "2025-09-09T08:21:01.71Z" },
-    { url = "https://files.pythonhosted.org/packages/55/87/ef5eb1f267084532c8e4aef98a28b6ffe7425acbfd64b5e2f2e066bc29b3/scikit_learn-1.7.2-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:9acb6c5e867447b4e1390930e3944a005e2cb115922e693c08a323421a6966e8", size = 9558731, upload-time = "2025-09-09T08:21:06.381Z" },
-    { url = "https://files.pythonhosted.org/packages/93/f8/6c1e3fc14b10118068d7938878a9f3f4e6d7b74a8ddb1e5bed65159ccda8/scikit_learn-1.7.2-cp313-cp313t-macosx_12_0_arm64.whl", hash = "sha256:2a41e2a0ef45063e654152ec9d8bcfc39f7afce35b08902bfe290c2498a67a6a", size = 9038852, upload-time = "2025-09-09T08:21:08.628Z" },
-    { url = "https://files.pythonhosted.org/packages/83/87/066cafc896ee540c34becf95d30375fe5cbe93c3b75a0ee9aa852cd60021/scikit_learn-1.7.2-cp313-cp313t-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:98335fb98509b73385b3ab2bd0639b1f610541d3988ee675c670371d6a87aa7c", size = 9527094, upload-time = "2025-09-09T08:21:11.486Z" },
-    { url = "https://files.pythonhosted.org/packages/9c/2b/4903e1ccafa1f6453b1ab78413938c8800633988c838aa0be386cbb33072/scikit_learn-1.7.2-cp313-cp313t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:191e5550980d45449126e23ed1d5e9e24b2c68329ee1f691a3987476e115e09c", size = 9367436, upload-time = "2025-09-09T08:21:13.602Z" },
-    { url = "https://files.pythonhosted.org/packages/d9/82/dee5acf66837852e8e68df6d8d3a6cb22d3df997b733b032f513d95205b7/scikit_learn-1.7.2-cp314-cp314-macosx_10_13_x86_64.whl", hash = "sha256:fa8f63940e29c82d1e67a45d5297bdebbcb585f5a5a50c4914cc2e852ab77f33", size = 9208906, upload-time = "2025-09-09T08:21:18.557Z" },
-    { url = "https://files.pythonhosted.org/packages/3c/30/9029e54e17b87cb7d50d51a5926429c683d5b4c1732f0507a6c3bed9bf65/scikit_learn-1.7.2-cp314-cp314-macosx_12_0_arm64.whl", hash = "sha256:f95dc55b7902b91331fa4e5845dd5bde0580c9cd9612b1b2791b7e80c3d32615", size = 8627836, upload-time = "2025-09-09T08:21:20.695Z" },
-    { url = "https://files.pythonhosted.org/packages/60/18/4a52c635c71b536879f4b971c2cedf32c35ee78f48367885ed8025d1f7ee/scikit_learn-1.7.2-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:9656e4a53e54578ad10a434dc1f993330568cfee176dff07112b8785fb413106", size = 9426236, upload-time = "2025-09-09T08:21:22.645Z" },
-    { url = "https://files.pythonhosted.org/packages/99/7e/290362f6ab582128c53445458a5befd471ed1ea37953d5bcf80604619250/scikit_learn-1.7.2-cp314-cp314-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:96dc05a854add0e50d3f47a1ef21a10a595016da5b007c7d9cd9d0bffd1fcc61", size = 9312593, upload-time = "2025-09-09T08:21:24.65Z" },
+    { url = "https://files.pythonhosted.org/packages/c9/92/53ea2181da8ac6bf27170191028aee7251f8f841f8d3edbfdcaf2008fde9/scikit_learn-1.8.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:146b4d36f800c013d267b29168813f7a03a43ecd2895d04861f1240b564421da", size = 8595835, upload-time = "2025-12-10T07:07:39.385Z" },
+    { url = "https://files.pythonhosted.org/packages/01/18/d154dc1638803adf987910cdd07097d9c526663a55666a97c124d09fb96a/scikit_learn-1.8.0-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:f984ca4b14914e6b4094c5d52a32ea16b49832c03bd17a110f004db3c223e8e1", size = 8080381, upload-time = "2025-12-10T07:07:41.93Z" },
+    { url = "https://files.pythonhosted.org/packages/8a/44/226142fcb7b7101e64fdee5f49dbe6288d4c7af8abf593237b70fca080a4/scikit_learn-1.8.0-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:5e30adb87f0cc81c7690a84f7932dd66be5bac57cfe16b91cb9151683a4a2d3b", size = 8799632, upload-time = "2025-12-10T07:07:43.899Z" },
+    { url = "https://files.pythonhosted.org/packages/36/4d/4a67f30778a45d542bbea5db2dbfa1e9e100bf9ba64aefe34215ba9f11f6/scikit_learn-1.8.0-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:ada8121bcb4dac28d930febc791a69f7cb1673c8495e5eee274190b73a4559c1", size = 9103788, upload-time = "2025-12-10T07:07:45.982Z" },
+    { url = "https://files.pythonhosted.org/packages/90/74/e6a7cc4b820e95cc38cf36cd74d5aa2b42e8ffc2d21fe5a9a9c45c1c7630/scikit_learn-1.8.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:5fb63362b5a7ddab88e52b6dbb47dac3fd7dafeee740dc6c8d8a446ddedade8e", size = 8548242, upload-time = "2025-12-10T07:07:51.568Z" },
+    { url = "https://files.pythonhosted.org/packages/49/d8/9be608c6024d021041c7f0b3928d4749a706f4e2c3832bbede4fb4f58c95/scikit_learn-1.8.0-cp312-cp312-macosx_12_0_arm64.whl", hash = "sha256:5025ce924beccb28298246e589c691fe1b8c1c96507e6d27d12c5fadd85bfd76", size = 8079075, upload-time = "2025-12-10T07:07:53.697Z" },
+    { url = "https://files.pythonhosted.org/packages/dd/47/f187b4636ff80cc63f21cd40b7b2d177134acaa10f6bb73746130ee8c2e5/scikit_learn-1.8.0-cp312-cp312-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:4496bb2cf7a43ce1a2d7524a79e40bc5da45cf598dbf9545b7e8316ccba47bb4", size = 8660492, upload-time = "2025-12-10T07:07:55.574Z" },
+    { url = "https://files.pythonhosted.org/packages/97/74/b7a304feb2b49df9fafa9382d4d09061a96ee9a9449a7cbea7988dda0828/scikit_learn-1.8.0-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:a0bcfe4d0d14aec44921545fd2af2338c7471de9cb701f1da4c9d85906ab847a", size = 8931904, upload-time = "2025-12-10T07:07:57.666Z" },
+    { url = "https://files.pythonhosted.org/packages/03/aa/e22e0768512ce9255eba34775be2e85c2048da73da1193e841707f8f039c/scikit_learn-1.8.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:0d6ae97234d5d7079dc0040990a6f7aeb97cb7fa7e8945f1999a429b23569e0a", size = 8513770, upload-time = "2025-12-10T07:08:03.251Z" },
+    { url = "https://files.pythonhosted.org/packages/58/37/31b83b2594105f61a381fc74ca19e8780ee923be2d496fcd8d2e1147bd99/scikit_learn-1.8.0-cp313-cp313-macosx_12_0_arm64.whl", hash = "sha256:edec98c5e7c128328124a029bceb09eda2d526997780fef8d65e9a69eead963e", size = 8044458, upload-time = "2025-12-10T07:08:05.336Z" },
+    { url = "https://files.pythonhosted.org/packages/2d/5a/3f1caed8765f33eabb723596666da4ebbf43d11e96550fb18bdec42b467b/scikit_learn-1.8.0-cp313-cp313-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:74b66d8689d52ed04c271e1329f0c61635bcaf5b926db9b12d58914cdc01fe57", size = 8610341, upload-time = "2025-12-10T07:08:07.732Z" },
+    { url = "https://files.pythonhosted.org/packages/38/cf/06896db3f71c75902a8e9943b444a56e727418f6b4b4a90c98c934f51ed4/scikit_learn-1.8.0-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:8fdf95767f989b0cfedb85f7ed8ca215d4be728031f56ff5a519ee1e3276dc2e", size = 8900022, upload-time = "2025-12-10T07:08:09.862Z" },
+    { url = "https://files.pythonhosted.org/packages/d2/7d/a630359fc9dcc95496588c8d8e3245cc8fd81980251079bc09c70d41d951/scikit_learn-1.8.0-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:7cc267b6108f0a1499a734167282c00c4ebf61328566b55ef262d48e9849c735", size = 8826045, upload-time = "2025-12-10T07:08:15.215Z" },
+    { url = "https://files.pythonhosted.org/packages/cc/56/a0c86f6930cfcd1c7054a2bc417e26960bb88d32444fe7f71d5c2cfae891/scikit_learn-1.8.0-cp313-cp313t-macosx_12_0_arm64.whl", hash = "sha256:fe1c011a640a9f0791146011dfd3c7d9669785f9fed2b2a5f9e207536cf5c2fd", size = 8420324, upload-time = "2025-12-10T07:08:17.561Z" },
+    { url = "https://files.pythonhosted.org/packages/46/1e/05962ea1cebc1cf3876667ecb14c283ef755bf409993c5946ade3b77e303/scikit_learn-1.8.0-cp313-cp313t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:72358cce49465d140cc4e7792015bb1f0296a9742d5622c67e31399b75468b9e", size = 8680651, upload-time = "2025-12-10T07:08:19.952Z" },
+    { url = "https://files.pythonhosted.org/packages/fe/56/a85473cd75f200c9759e3a5f0bcab2d116c92a8a02ee08ccd73b870f8bb4/scikit_learn-1.8.0-cp313-cp313t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:80832434a6cc114f5219211eec13dcbc16c2bac0e31ef64c6d346cde3cf054cb", size = 8925045, upload-time = "2025-12-10T07:08:22.11Z" },
+    { url = "https://files.pythonhosted.org/packages/24/05/1af2c186174cc92dcab2233f327336058c077d38f6fe2aceb08e6ab4d509/scikit_learn-1.8.0-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:c22a2da7a198c28dd1a6e1136f19c830beab7fdca5b3e5c8bba8394f8a5c45b3", size = 8528667, upload-time = "2025-12-10T07:08:27.541Z" },
+    { url = "https://files.pythonhosted.org/packages/a8/25/01c0af38fe969473fb292bba9dc2b8f9b451f3112ff242c647fee3d0dfe7/scikit_learn-1.8.0-cp314-cp314-macosx_12_0_arm64.whl", hash = "sha256:6b595b07a03069a2b1740dc08c2299993850ea81cce4fe19b2421e0c970de6b7", size = 8066524, upload-time = "2025-12-10T07:08:29.822Z" },
+    { url = "https://files.pythonhosted.org/packages/be/ce/a0623350aa0b68647333940ee46fe45086c6060ec604874e38e9ab7d8e6c/scikit_learn-1.8.0-cp314-cp314-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:29ffc74089f3d5e87dfca4c2c8450f88bdc61b0fc6ed5d267f3988f19a1309f6", size = 8657133, upload-time = "2025-12-10T07:08:31.865Z" },
+    { url = "https://files.pythonhosted.org/packages/b8/cb/861b41341d6f1245e6ca80b1c1a8c4dfce43255b03df034429089ca2a2c5/scikit_learn-1.8.0-cp314-cp314-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:fb65db5d7531bccf3a4f6bec3462223bea71384e2cda41da0f10b7c292b9e7c4", size = 8923223, upload-time = "2025-12-10T07:08:34.166Z" },
+    { url = "https://files.pythonhosted.org/packages/2d/d1/ef294ca754826daa043b2a104e59960abfab4cf653891037d19dd5b6f3cf/scikit_learn-1.8.0-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:4511be56637e46c25721e83d1a9cea9614e7badc7040c4d573d75fbe257d6fd7", size = 8848305, upload-time = "2025-12-10T07:08:41.013Z" },
+    { url = "https://files.pythonhosted.org/packages/5b/e2/b1f8b05138ee813b8e1a4149f2f0d289547e60851fd1bb268886915adbda/scikit_learn-1.8.0-cp314-cp314t-macosx_12_0_arm64.whl", hash = "sha256:a69525355a641bf8ef136a7fa447672fb54fe8d60cab5538d9eb7c6438543fb9", size = 8432257, upload-time = "2025-12-10T07:08:42.873Z" },
+    { url = "https://files.pythonhosted.org/packages/26/11/c32b2138a85dcb0c99f6afd13a70a951bfdff8a6ab42d8160522542fb647/scikit_learn-1.8.0-cp314-cp314t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:c2656924ec73e5939c76ac4c8b026fc203b83d8900362eb2599d8aee80e4880f", size = 8678673, upload-time = "2025-12-10T07:08:45.362Z" },
+    { url = "https://files.pythonhosted.org/packages/c7/57/51f2384575bdec454f4fe4e7a919d696c9ebce914590abf3e52d47607ab8/scikit_learn-1.8.0-cp314-cp314t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:15fc3b5d19cc2be65404786857f2e13c70c83dd4782676dd6814e3b89dc8f5b9", size = 8922467, upload-time = "2025-12-10T07:08:47.408Z" },
 ]
 
 [[package]]