mirror of
https://github.com/paperless-ngx/paperless-ngx.git
synced 2026-11-21 13:02:40 +00:00
Enhancement: prefer existing tags, types, correspondents, and storage paths in AI suggestions (#13676)
AI Suggestions previously invented near-duplicate metadata because the classification prompt had no knowledge of the installation's own taxonomy. This surfaces a small, ranked, permission-filtered set of existing tags/document types/correspondents/storage paths - drawn from the document's RAG neighbors plus its own already-assigned metadata - so the model prefers reusing what already exists. The LLM response schema now returns existing_ids (IDs of reused candidates) separately from new_names (genuinely new suggestions). Only new_names goes through localization and fuzzy name-matching; existing_ids is resolved deterministically and never touched by the localization pass, so exact matches can no longer be silently corrupted by translation.
This commit is contained in:
1 parent
3322c92837
commit
0e5fbc973a
16 files changed
+2639
-520
No files matched your search
@@ -41,7 +41,16 @@ class SuggestionCacheData:
|
||||
CLASSIFIER_VERSION_KEY: Final[str] = "classifier_version"
|
||||
CLASSIFIER_HASH_KEY: Final[str] = "classifier_hash"
|
||||
CLASSIFIER_MODIFIED_KEY: Final[str] = "classifier_modified"
|
||||
LLM_CACHE_CLASSIFIER_VERSION: Final[int] = 1000 # Marker distinguishing LLM suggestions
|
||||
# Marker distinguishing LLM suggestions from classifier-generated ones (whose
|
||||
# FORMAT_VERSION lives in a much lower range - see DocumentClassifier). Bump
|
||||
# this whenever the *shape* of the cached `suggestions` dict changes, so a
|
||||
# cache entry written by a previous release can never be read back by code
|
||||
# that expects a different shape:
|
||||
# 1000 - initial LLM suggestions cache (flat lists of resolved object ids
|
||||
# per taxonomy field)
|
||||
# 1001 - suggestions reshaped to {"existing_ids": [...], "new_names":
|
||||
# [...]} per taxonomy field (#13676)
|
||||
LLM_CACHE_CLASSIFIER_VERSION: Final[int] = 1001
|
||||
|
||||
CACHE_1_MINUTE: Final[int] = 60
|
||||
CACHE_5_MINUTES: Final[int] = 5 * CACHE_1_MINUTE
|
||||
@@ -204,7 +213,11 @@ def get_llm_suggestion_cache(
|
||||
doc_key = get_suggestion_cache_key(document_id)
|
||||
data: SuggestionCacheData = cache.get(doc_key)
|
||||
|
||||
if data and data.classifier_hash == backend:
|
||||
if (
|
||||
data
|
||||
and data.classifier_version == LLM_CACHE_CLASSIFIER_VERSION
|
||||
and data.classifier_hash == backend
|
||||
):
|
||||
return data
|
||||
|
||||
return None
|
||||
|
||||
@@ -1,4 +1,5 @@
|
||||
from typing import Any
|
||||
from typing import TypeVar
|
||||
|
||||
from django.contrib.auth.models import Group
|
||||
from django.contrib.auth.models import Permission
|
||||
@@ -235,6 +236,58 @@ def permitted_object_ids(
|
||||
).values_list("id", flat=True)
|
||||
|
||||
|
||||
ModelT = TypeVar("ModelT", bound=Model)
|
||||
|
||||
|
||||
def user_is_unrestricted(user: User | None) -> bool:
|
||||
"""
|
||||
True when ``user`` means "no restriction at all" (an absent user, or an
|
||||
*active* superuser) without needing a database check to know it.
|
||||
|
||||
``permitted_object_ids(None, ...)`` itself means the much narrower "only
|
||||
unowned rows", which is NOT the same thing as "no user filtering
|
||||
requested", so callers must special-case this before ever calling it.
|
||||
A deactivated superuser is deliberately NOT unrestricted here, matching
|
||||
permitted_object_ids's own is_active-before-is_superuser ordering.
|
||||
|
||||
Callers that can avoid a database round trip entirely when this is true
|
||||
(e.g. checking a single already-loaded object's visibility rather than
|
||||
filtering a queryset) should do so via this function directly, rather
|
||||
than through restrict_queryset_to_visible() below.
|
||||
"""
|
||||
if user is None:
|
||||
return True
|
||||
return (
|
||||
getattr(user, "is_authenticated", False)
|
||||
and getattr(user, "is_active", False)
|
||||
and getattr(user, "is_superuser", False)
|
||||
)
|
||||
|
||||
|
||||
def restrict_queryset_to_visible(
|
||||
queryset: QuerySet[ModelT],
|
||||
user: User | None,
|
||||
perm: str,
|
||||
) -> QuerySet[ModelT]:
|
||||
"""
|
||||
Restrict ``queryset`` to the rows ``user`` may see with ``perm``.
|
||||
|
||||
Delegates the visibility check to the database as a
|
||||
``WHERE id IN (subquery)`` rather than materializing the full
|
||||
permitted-id set into a Python collection first: a caller that only
|
||||
needs to check a small handful of rows (a resolved-id list, a few
|
||||
RAG-neighbour candidate ids) never pays for scanning or holding the
|
||||
installation's entire taxonomy in memory to do it.
|
||||
|
||||
Returns ``queryset`` unchanged for user_is_unrestricted(user); every
|
||||
other case is delegated to ``permitted_object_ids`` rather than
|
||||
re-deciding the ordering here.
|
||||
"""
|
||||
if user_is_unrestricted(user):
|
||||
return queryset
|
||||
return queryset.filter(pk__in=permitted_object_ids(user, queryset.model, perm))
|
||||
|
||||
|
||||
def permitted_document_ids(
|
||||
user: User | None,
|
||||
*,
|
||||
|
||||
@@ -22,6 +22,7 @@ from documents.models import StoragePath
|
||||
from documents.models import Tag
|
||||
from documents.permissions import permitted_document_ids
|
||||
from documents.permissions import permitted_object_ids
|
||||
from documents.permissions import restrict_queryset_to_visible
|
||||
from documents.serialisers import _get_viewable_duplicates
|
||||
from documents.tests.factories import CorrespondentFactory
|
||||
from documents.tests.factories import DocumentFactory
|
||||
@@ -736,7 +737,7 @@ class TestBulkEditObjectsTagDescendantPartialPermission:
|
||||
NOTE: this uses ``set_permissions`` (owner reassignment) rather than
|
||||
``delete`` as the operation, because Tag.tn_parent (django-treenode)
|
||||
cascades deletes to descendants at the database/ORM level regardless
|
||||
of which tags the view resolved into ``objs`` -- a delete-based test
|
||||
of which tags the view resolved into ``objs`` - a delete-based test
|
||||
would pass/fail based on FK cascade behavior, not on whether the
|
||||
descendant-expansion logic itself respected per-object permissions.
|
||||
"""
|
||||
@@ -783,3 +784,97 @@ class TestBulkEditObjectsTagDescendantPartialPermission:
|
||||
assert parent.owner == requester
|
||||
assert permitted_child.owner == requester
|
||||
assert unpermitted_child.owner == owner
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
class TestRestrictQuerysetToVisible:
|
||||
"""restrict_queryset_to_visible() returns its queryset argument
|
||||
unchanged only for "no restriction at all", so the cases that may do
|
||||
that have to be kept narrow."""
|
||||
|
||||
def test_no_user_means_no_restriction(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- No user at all (a system-triggered call)
|
||||
WHEN:
|
||||
- restrict_queryset_to_visible() is called
|
||||
THEN:
|
||||
- The queryset is returned unfiltered, rather than
|
||||
permitted_object_ids(None, ...)'s narrower "unowned rows only"
|
||||
"""
|
||||
owner = User.objects.create_user(username="vis_none_owner")
|
||||
tag = TagFactory(owner=owner)
|
||||
|
||||
visible = restrict_queryset_to_visible(Tag.objects.all(), None, "view_tag")
|
||||
|
||||
assert tag.pk in visible.values_list("pk", flat=True)
|
||||
|
||||
def test_active_superuser_means_no_restriction(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- An active superuser
|
||||
WHEN:
|
||||
- restrict_queryset_to_visible() is called
|
||||
THEN:
|
||||
- The queryset is returned unfiltered, skipping the permission
|
||||
lookup entirely
|
||||
"""
|
||||
superuser = User.objects.create_superuser(username="vis_active_super")
|
||||
owner = User.objects.create_user(username="vis_active_super_owner")
|
||||
tag = TagFactory(owner=owner)
|
||||
|
||||
visible = restrict_queryset_to_visible(
|
||||
Tag.objects.all(),
|
||||
superuser,
|
||||
"view_tag",
|
||||
)
|
||||
|
||||
assert tag.pk in visible.values_list("pk", flat=True)
|
||||
|
||||
def test_inactive_superuser_is_denied_not_unrestricted(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- A deactivated superuser
|
||||
WHEN:
|
||||
- restrict_queryset_to_visible() is called
|
||||
THEN:
|
||||
- No rows are visible, never the whole unrestricted queryset -
|
||||
deactivation has to win over the superuser shortcut, matching
|
||||
permitted_object_ids's own ordering
|
||||
"""
|
||||
user = User.objects.create_user(
|
||||
username="vis_inactive_super",
|
||||
is_active=False,
|
||||
is_superuser=True,
|
||||
)
|
||||
TagFactory(owner=None)
|
||||
TagFactory(owner=user)
|
||||
|
||||
visible = restrict_queryset_to_visible(Tag.objects.all(), user, "view_tag")
|
||||
|
||||
assert not visible.exists()
|
||||
|
||||
def test_regular_user_gets_permitted_ids(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- An ordinary active user and a tag owned by someone else
|
||||
WHEN:
|
||||
- restrict_queryset_to_visible() is called
|
||||
THEN:
|
||||
- Only the rows permitted_object_ids() reports are visible
|
||||
"""
|
||||
user = User.objects.create_user(username="vis_regular")
|
||||
other = User.objects.create_user(username="vis_regular_other")
|
||||
own = TagFactory(owner=user)
|
||||
hidden = TagFactory(owner=other)
|
||||
|
||||
visible_ids = set(
|
||||
restrict_queryset_to_visible(
|
||||
Tag.objects.all(),
|
||||
user,
|
||||
"view_tag",
|
||||
).values_list("pk", flat=True),
|
||||
)
|
||||
|
||||
assert own.pk in visible_ids
|
||||
assert hidden.pk not in visible_ids
|
||||
@@ -352,20 +352,95 @@ class TestAISuggestions(DirectoriesMixin, TestCase):
|
||||
mock_refresh_cache,
|
||||
mock_get_cache,
|
||||
) -> None:
|
||||
mock_get_cache.return_value = MagicMock(suggestions={"tags": ["tag1", "tag2"]})
|
||||
"""
|
||||
GIVEN:
|
||||
- A cached LLM classification holding the raw existing_ids/
|
||||
new_names choices (never resolved object ids)
|
||||
WHEN:
|
||||
- ai_suggestions is requested
|
||||
THEN:
|
||||
- The cached choices are resolved into ids for this request
|
||||
(not returned verbatim from the cache) and the cache's TTL is
|
||||
refreshed
|
||||
"""
|
||||
mock_get_cache.return_value = MagicMock(
|
||||
suggestions={
|
||||
"title": "Cached Title",
|
||||
"tags": {"existing_ids": [self.tag1.pk], "new_names": []},
|
||||
"correspondents": {"existing_ids": [], "new_names": []},
|
||||
"document_types": {"existing_ids": [], "new_names": []},
|
||||
"storage_paths": {"existing_ids": [], "new_names": []},
|
||||
"dates": [],
|
||||
},
|
||||
)
|
||||
|
||||
self.client.force_login(user=self.user)
|
||||
response = self.client.get(
|
||||
f"/api/documents/{self.document.pk}/ai_suggestions/",
|
||||
)
|
||||
self.assertEqual(response.status_code, status.HTTP_200_OK)
|
||||
self.assertEqual(response.json(), {"tags": ["tag1", "tag2"]})
|
||||
self.assertEqual(response.json()["title"], "Cached Title")
|
||||
self.assertEqual(response.json()["tags"], [self.tag1.pk])
|
||||
mock_get_cache.assert_called_once_with(
|
||||
self.document.pk,
|
||||
backend="mock_backend",
|
||||
)
|
||||
mock_refresh_cache.assert_called_once_with(self.document.pk)
|
||||
|
||||
@patch("documents.views.get_llm_suggestion_cache")
|
||||
@patch("documents.views.refresh_suggestions_cache")
|
||||
@override_settings(
|
||||
AI_ENABLED=True,
|
||||
LLM_BACKEND="mock_backend",
|
||||
)
|
||||
def test_ai_suggestions_cache_hit_re_filters_for_narrower_requester(
|
||||
self,
|
||||
mock_refresh_cache,
|
||||
mock_get_cache,
|
||||
) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- A cached LLM classification whose existing_ids include a tag
|
||||
only visible to a broader-visibility user (e.g. the requester
|
||||
who originally generated it)
|
||||
- A second, non-superuser requester who may change the document
|
||||
but has no permission to view that tag
|
||||
WHEN:
|
||||
- ai_suggestions is requested by the second requester and the
|
||||
cache is hit
|
||||
THEN:
|
||||
- The cache hit still runs permission filtering fresh for this
|
||||
requester; the invisible tag id does not leak into either the
|
||||
matched or suggested tags
|
||||
"""
|
||||
tag_owner = User.objects.create_user(username="cache_tag_owner")
|
||||
invisible_tag = Tag.objects.create(name="cache_restricted", owner=tag_owner)
|
||||
requester = User.objects.create_user(username="cache_requester")
|
||||
requester.user_permissions.add(
|
||||
*Permission.objects.filter(
|
||||
codename__in=["view_document", "change_document", "view_tag"],
|
||||
),
|
||||
)
|
||||
mock_get_cache.return_value = MagicMock(
|
||||
suggestions={
|
||||
"title": "Untitled",
|
||||
"tags": {"existing_ids": [invisible_tag.pk], "new_names": []},
|
||||
"correspondents": {"existing_ids": [], "new_names": []},
|
||||
"document_types": {"existing_ids": [], "new_names": []},
|
||||
"storage_paths": {"existing_ids": [], "new_names": []},
|
||||
"dates": [],
|
||||
},
|
||||
)
|
||||
|
||||
self.client.force_login(user=requester)
|
||||
response = self.client.get(
|
||||
f"/api/documents/{self.document.pk}/ai_suggestions/",
|
||||
)
|
||||
|
||||
self.assertEqual(response.status_code, status.HTTP_200_OK)
|
||||
self.assertEqual(response.json()["tags"], [])
|
||||
self.assertEqual(response.json()["suggested_tags"], [])
|
||||
|
||||
@patch("documents.views.get_ai_document_classification")
|
||||
@override_settings(
|
||||
AI_ENABLED=True,
|
||||
@@ -377,10 +452,16 @@ class TestAISuggestions(DirectoriesMixin, TestCase):
|
||||
) -> None:
|
||||
mock_get_ai_classification.return_value = {
|
||||
"title": "AI Title",
|
||||
"tags": ["tag1", "tag2"],
|
||||
"correspondents": ["correspondent1"],
|
||||
"document_types": ["type1"],
|
||||
"storage_paths": ["path1"],
|
||||
"tags": {"existing_ids": [self.tag1.pk], "new_names": ["tag2"]},
|
||||
"correspondents": {
|
||||
"existing_ids": [self.correspondent1.pk],
|
||||
"new_names": [],
|
||||
},
|
||||
"document_types": {
|
||||
"existing_ids": [self.document_type1.pk],
|
||||
"new_names": [],
|
||||
},
|
||||
"storage_paths": {"existing_ids": [self.path1.pk], "new_names": []},
|
||||
"dates": ["2023-01-01"],
|
||||
}
|
||||
|
||||
@@ -422,10 +503,10 @@ class TestAISuggestions(DirectoriesMixin, TestCase):
|
||||
UiSettings.objects.create(user=self.user, settings={"language": "de-de"})
|
||||
mock_get_ai_classification.return_value = {
|
||||
"title": "KI Title",
|
||||
"tags": [],
|
||||
"correspondents": [],
|
||||
"document_types": [],
|
||||
"storage_paths": [],
|
||||
"tags": {"existing_ids": [], "new_names": []},
|
||||
"correspondents": {"existing_ids": [], "new_names": []},
|
||||
"document_types": {"existing_ids": [], "new_names": []},
|
||||
"storage_paths": {"existing_ids": [], "new_names": []},
|
||||
"dates": [],
|
||||
}
|
||||
|
||||
@@ -461,10 +542,10 @@ class TestAISuggestions(DirectoriesMixin, TestCase):
|
||||
UiSettings.objects.create(user=self.user, settings={"language": "de-de"})
|
||||
mock_get_ai_classification.return_value = {
|
||||
"title": "Titre IA",
|
||||
"tags": [],
|
||||
"correspondents": [],
|
||||
"document_types": [],
|
||||
"storage_paths": [],
|
||||
"tags": {"existing_ids": [], "new_names": []},
|
||||
"correspondents": {"existing_ids": [], "new_names": []},
|
||||
"document_types": {"existing_ids": [], "new_names": []},
|
||||
"storage_paths": {"existing_ids": [], "new_names": []},
|
||||
"dates": [],
|
||||
}
|
||||
|
||||
@@ -502,10 +583,10 @@ class TestAISuggestions(DirectoriesMixin, TestCase):
|
||||
either yields a cache miss instead of a stale hit."""
|
||||
mock_get_ai_classification.return_value = {
|
||||
"title": "Answer A",
|
||||
"tags": [],
|
||||
"correspondents": [],
|
||||
"document_types": [],
|
||||
"storage_paths": [],
|
||||
"tags": {"existing_ids": [], "new_names": []},
|
||||
"correspondents": {"existing_ids": [], "new_names": []},
|
||||
"document_types": {"existing_ids": [], "new_names": []},
|
||||
"storage_paths": {"existing_ids": [], "new_names": []},
|
||||
"dates": [],
|
||||
}
|
||||
|
||||
@@ -579,6 +660,132 @@ class TestAISuggestions(DirectoriesMixin, TestCase):
|
||||
get_llm_suggestion_cache(self.document.pk, backend="openai-like"),
|
||||
)
|
||||
|
||||
@patch("documents.views.get_ai_document_classification")
|
||||
@override_settings(
|
||||
AI_ENABLED=True,
|
||||
LLM_BACKEND="mock_backend",
|
||||
)
|
||||
def test_ai_suggestions_combines_existing_ids_and_new_names(
|
||||
self,
|
||||
mock_get_ai_classification,
|
||||
) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- AI classification returns a taxonomy choice with both an
|
||||
existing tag id and a new tag name not present in the database
|
||||
WHEN:
|
||||
- ai_suggestions is requested
|
||||
THEN:
|
||||
- the existing id is resolved into the matched tags list
|
||||
- the new name is fuzzy-matched, and since it doesn't match any
|
||||
existing tag, it is surfaced as a suggested tag
|
||||
"""
|
||||
mock_get_ai_classification.return_value = {
|
||||
"title": "Lab Report",
|
||||
"tags": {"existing_ids": [self.tag1.pk], "new_names": ["Follow-up"]},
|
||||
"correspondents": {"existing_ids": [], "new_names": []},
|
||||
"document_types": {"existing_ids": [], "new_names": []},
|
||||
"storage_paths": {"existing_ids": [], "new_names": []},
|
||||
"dates": [],
|
||||
}
|
||||
|
||||
self.client.force_login(user=self.user)
|
||||
response = self.client.get(
|
||||
f"/api/documents/{self.document.pk}/ai_suggestions/",
|
||||
)
|
||||
|
||||
self.assertEqual(response.status_code, status.HTTP_200_OK)
|
||||
self.assertEqual(response.json()["tags"], [self.tag1.pk])
|
||||
self.assertEqual(response.json()["suggested_tags"], ["Follow-up"])
|
||||
|
||||
@patch("documents.views.get_ai_document_classification")
|
||||
@override_settings(
|
||||
AI_ENABLED=True,
|
||||
LLM_BACKEND="mock_backend",
|
||||
)
|
||||
def test_ai_suggestions_deduplicates_id_matched_via_both_paths(
|
||||
self,
|
||||
mock_get_ai_classification,
|
||||
) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- AI classification returns the same tag both as an existing_id
|
||||
and as a new_name that fuzzy-matches that same tag
|
||||
WHEN:
|
||||
- ai_suggestions is requested
|
||||
THEN:
|
||||
- The tag's id appears exactly once in the response, not twice
|
||||
"""
|
||||
mock_get_ai_classification.return_value = {
|
||||
"title": "Lab Report",
|
||||
"tags": {
|
||||
"existing_ids": [self.tag1.pk],
|
||||
"new_names": [self.tag1.name],
|
||||
},
|
||||
"correspondents": {"existing_ids": [], "new_names": []},
|
||||
"document_types": {"existing_ids": [], "new_names": []},
|
||||
"storage_paths": {"existing_ids": [], "new_names": []},
|
||||
"dates": [],
|
||||
}
|
||||
|
||||
self.client.force_login(user=self.user)
|
||||
response = self.client.get(
|
||||
f"/api/documents/{self.document.pk}/ai_suggestions/",
|
||||
)
|
||||
|
||||
self.assertEqual(response.status_code, status.HTTP_200_OK)
|
||||
self.assertEqual(response.json()["tags"], [self.tag1.pk])
|
||||
self.assertEqual(response.json()["suggested_tags"], [])
|
||||
|
||||
@patch("documents.views.get_ai_document_classification")
|
||||
@override_settings(
|
||||
AI_ENABLED=True,
|
||||
LLM_BACKEND="mock_backend",
|
||||
)
|
||||
def test_ai_suggestions_existing_id_not_visible_falls_through_to_suggested(
|
||||
self,
|
||||
mock_get_ai_classification,
|
||||
) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- A non-superuser who may change the document but has no
|
||||
permission to view a tag owned by somebody else
|
||||
- AI classification returns that tag's id in existing_ids (e.g.
|
||||
from a cached response generated for a broader-visibility user)
|
||||
WHEN:
|
||||
- ai_suggestions is requested by that user
|
||||
THEN:
|
||||
- the invisible id is silently dropped by resolve_tag_ids, so
|
||||
permission filtering survives the full request path
|
||||
- it does not appear in either the matched or suggested tags
|
||||
"""
|
||||
tag_owner = User.objects.create_user(username="tagowner")
|
||||
invisible_tag = Tag.objects.create(name="restricted", owner=tag_owner)
|
||||
requester = User.objects.create_user(username="requester")
|
||||
requester.user_permissions.add(
|
||||
*Permission.objects.filter(
|
||||
codename__in=["view_document", "change_document", "view_tag"],
|
||||
),
|
||||
)
|
||||
|
||||
mock_get_ai_classification.return_value = {
|
||||
"title": "Untitled",
|
||||
"tags": {"existing_ids": [invisible_tag.pk], "new_names": []},
|
||||
"correspondents": {"existing_ids": [], "new_names": []},
|
||||
"document_types": {"existing_ids": [], "new_names": []},
|
||||
"storage_paths": {"existing_ids": [], "new_names": []},
|
||||
"dates": [],
|
||||
}
|
||||
|
||||
self.client.force_login(user=requester)
|
||||
response = self.client.get(
|
||||
f"/api/documents/{self.document.pk}/ai_suggestions/",
|
||||
)
|
||||
|
||||
self.assertEqual(response.status_code, status.HTTP_200_OK)
|
||||
self.assertEqual(response.json()["tags"], [])
|
||||
self.assertEqual(response.json()["suggested_tags"], [])
|
||||
|
||||
def test_invalidate_suggestions_cache(self) -> None:
|
||||
self.client.force_login(user=self.user)
|
||||
suggestions = {
|
||||
|
||||
+99
-45
@@ -7,6 +7,7 @@ import tempfile
|
||||
import zipfile
|
||||
from collections import defaultdict
|
||||
from collections import deque
|
||||
from collections.abc import Callable
|
||||
from datetime import datetime
|
||||
from datetime import timedelta
|
||||
from http import HTTPStatus
|
||||
@@ -249,6 +250,10 @@ from paperless_ai.matching import match_correspondents_by_name
|
||||
from paperless_ai.matching import match_document_types_by_name
|
||||
from paperless_ai.matching import match_storage_paths_by_name
|
||||
from paperless_ai.matching import match_tags_by_name
|
||||
from paperless_ai.matching import resolve_correspondent_ids
|
||||
from paperless_ai.matching import resolve_document_type_ids
|
||||
from paperless_ai.matching import resolve_storage_path_ids
|
||||
from paperless_ai.matching import resolve_tag_ids
|
||||
from paperless_mail.models import MailAccount
|
||||
from paperless_mail.models import MailRule
|
||||
from paperless_mail.oauth import PaperlessMailOAuth2Manager
|
||||
@@ -258,6 +263,9 @@ from paperless_mail.serialisers import MailRuleSerializer
|
||||
if settings.AUDIT_LOG_ENABLED:
|
||||
from auditlog.models import LogEntry
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from paperless_ai.base_model import TaxonomyChoiceDict
|
||||
|
||||
|
||||
logger = logging.getLogger("paperless.api")
|
||||
|
||||
@@ -1546,80 +1554,126 @@ class DocumentViewSet(
|
||||
)
|
||||
|
||||
if cached_llm_suggestions:
|
||||
# Only the raw model choices are cached, never resolved object
|
||||
# ids. resolve_choice() below still runs permission filtering
|
||||
# freshly for this requester on every request, cache hit or not,
|
||||
# so a resolved id cached for one user's visibility can never be
|
||||
# handed unfiltered to a second, less-privileged requester of
|
||||
# the same (backend-keyed, not user-keyed) cache entry.
|
||||
refresh_suggestions_cache(doc.pk)
|
||||
return Response(cached_llm_suggestions.suggestions)
|
||||
llm_suggestions = cached_llm_suggestions.suggestions
|
||||
else:
|
||||
try:
|
||||
llm_suggestions = get_ai_document_classification(
|
||||
doc,
|
||||
request.user,
|
||||
output_language,
|
||||
)
|
||||
except ValueError as exc:
|
||||
logger.exception(
|
||||
"Invalid AI configuration while generating suggestions for "
|
||||
"document %s: %s",
|
||||
doc.pk,
|
||||
exc,
|
||||
exc_info=True,
|
||||
)
|
||||
raise ValidationError(
|
||||
{"ai": [_("Invalid AI configuration.")]},
|
||||
) from exc
|
||||
except LLMTimeoutError as exc:
|
||||
logger.exception(
|
||||
"AI backend timed out while generating suggestions for "
|
||||
"document %s: %s",
|
||||
doc.pk,
|
||||
exc,
|
||||
exc_info=True,
|
||||
)
|
||||
return Response(
|
||||
{"ai": [_("AI backend request timed out.")]},
|
||||
status=status.HTTP_503_SERVICE_UNAVAILABLE,
|
||||
)
|
||||
set_llm_suggestions_cache(
|
||||
doc.pk,
|
||||
llm_suggestions,
|
||||
backend=llm_cache_backend,
|
||||
)
|
||||
|
||||
try:
|
||||
llm_suggestions = get_ai_document_classification(
|
||||
doc,
|
||||
tags_choice: TaxonomyChoiceDict = llm_suggestions["tags"]
|
||||
correspondents_choice: TaxonomyChoiceDict = llm_suggestions["correspondents"]
|
||||
document_types_choice: TaxonomyChoiceDict = llm_suggestions["document_types"]
|
||||
storage_paths_choice: TaxonomyChoiceDict = llm_suggestions["storage_paths"]
|
||||
|
||||
def resolve_choice(
|
||||
choice: "TaxonomyChoiceDict",
|
||||
resolve_ids: Callable[[list[int], User], list],
|
||||
match_names: Callable[[list[str], User], list],
|
||||
) -> list:
|
||||
"""The ids the model picked from the candidates it was shown, plus
|
||||
name matches for the values it proposed as new. The schema allows
|
||||
the same object to satisfy both an existing_id and a new_name in
|
||||
one valid response, so results are deduplicated by pk (keeping
|
||||
first-seen order) rather than trusting the two lookups to be
|
||||
disjoint.
|
||||
"""
|
||||
matched = resolve_ids(choice["existing_ids"], request.user) + match_names(
|
||||
choice["new_names"],
|
||||
request.user,
|
||||
output_language,
|
||||
)
|
||||
except ValueError as exc:
|
||||
logger.exception(
|
||||
"Invalid AI configuration while generating suggestions for "
|
||||
"document %s: %s",
|
||||
doc.pk,
|
||||
exc,
|
||||
exc_info=True,
|
||||
)
|
||||
raise ValidationError({"ai": [_("Invalid AI configuration.")]}) from exc
|
||||
except LLMTimeoutError as exc:
|
||||
logger.exception(
|
||||
"AI backend timed out while generating suggestions for document %s: %s",
|
||||
doc.pk,
|
||||
exc,
|
||||
exc_info=True,
|
||||
)
|
||||
return Response(
|
||||
{"ai": [_("AI backend request timed out.")]},
|
||||
status=status.HTTP_503_SERVICE_UNAVAILABLE,
|
||||
)
|
||||
seen_ids: set[int] = set()
|
||||
deduped = []
|
||||
for obj in matched:
|
||||
if obj.pk in seen_ids:
|
||||
continue
|
||||
seen_ids.add(obj.pk)
|
||||
deduped.append(obj)
|
||||
return deduped
|
||||
|
||||
matched_tags = match_tags_by_name(
|
||||
llm_suggestions.get("tags", []),
|
||||
request.user,
|
||||
matched_tags = resolve_choice(
|
||||
tags_choice,
|
||||
resolve_tag_ids,
|
||||
match_tags_by_name,
|
||||
)
|
||||
matched_correspondents = match_correspondents_by_name(
|
||||
llm_suggestions.get("correspondents", []),
|
||||
request.user,
|
||||
matched_correspondents = resolve_choice(
|
||||
correspondents_choice,
|
||||
resolve_correspondent_ids,
|
||||
match_correspondents_by_name,
|
||||
)
|
||||
matched_types = match_document_types_by_name(
|
||||
llm_suggestions.get("document_types", []),
|
||||
request.user,
|
||||
matched_types = resolve_choice(
|
||||
document_types_choice,
|
||||
resolve_document_type_ids,
|
||||
match_document_types_by_name,
|
||||
)
|
||||
matched_paths = match_storage_paths_by_name(
|
||||
llm_suggestions.get("storage_paths", []),
|
||||
request.user,
|
||||
matched_paths = resolve_choice(
|
||||
storage_paths_choice,
|
||||
resolve_storage_path_ids,
|
||||
match_storage_paths_by_name,
|
||||
)
|
||||
|
||||
resp_data = {
|
||||
"title": llm_suggestions.get("title"),
|
||||
"title": llm_suggestions["title"],
|
||||
"tags": [t.id for t in matched_tags],
|
||||
"suggested_tags": extract_unmatched_names(
|
||||
llm_suggestions.get("tags", []),
|
||||
tags_choice["new_names"],
|
||||
matched_tags,
|
||||
),
|
||||
"correspondents": [c.id for c in matched_correspondents],
|
||||
"suggested_correspondents": extract_unmatched_names(
|
||||
llm_suggestions.get("correspondents", []),
|
||||
correspondents_choice["new_names"],
|
||||
matched_correspondents,
|
||||
),
|
||||
"document_types": [d.id for d in matched_types],
|
||||
"suggested_document_types": extract_unmatched_names(
|
||||
llm_suggestions.get("document_types", []),
|
||||
document_types_choice["new_names"],
|
||||
matched_types,
|
||||
),
|
||||
"storage_paths": [s.id for s in matched_paths],
|
||||
"suggested_storage_paths": extract_unmatched_names(
|
||||
llm_suggestions.get("storage_paths", []),
|
||||
storage_paths_choice["new_names"],
|
||||
matched_paths,
|
||||
),
|
||||
"dates": llm_suggestions.get("dates", []),
|
||||
"dates": llm_suggestions["dates"],
|
||||
}
|
||||
|
||||
set_llm_suggestions_cache(doc.pk, resp_data, backend=llm_cache_backend)
|
||||
|
||||
return Response(resp_data)
|
||||
|
||||
@action(methods=["get"], detail=True, filter_backends=[])
|
||||
|
||||
Reference in new issue
Block a user