amorfo77/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2026-08-29 14:07:33 +00:00
Code Issues Projects Releases Wiki Activity

tidy up

Browse Source
This commit is contained in:
shamoon
2026-08-26 09:53:27 -07:00
parent 34a01a5bd6
commit 15a5618a6e
5 changed files with 27 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/documents/caching.py
+10 -5
View File
@@ -17,7 +17,6 @@ from django.core.cache import cache
from django.core.cache import caches
from documents.models import Document
from paperless_ai.ai_classifier import get_ai_document_classification
if TYPE_CHECKING:
from django.contrib.auth.models import User
@@ -57,6 +56,9 @@ CLASSIFIER_MODIFIED_KEY: Final[str] = "classifier_modified"
# [...]} per taxonomy field (#13676)
LLM_CACHE_CLASSIFIER_VERSION: Final[int] = 1001
# How often a request waiting on llm generation re-checks the cache
LLM_SUGGESTION_POLL_INTERVAL: Final[float] = 0.5
CACHE_1_MINUTE: Final[int] = 60
CACHE_5_MINUTES: Final[int] = 5 * CACHE_1_MINUTE
CACHE_50_MINUTES: Final[int] = 50 * CACHE_1_MINUTE
@@ -232,18 +234,21 @@ def retrieve_llm_suggestions(
document: Document,
user: User | None,
output_language: str | None,
backend: str,
*,
backend: str,
lock_timeout: int,
) -> dict:
"""Return cached LLM suggestions, generating them once across workers."""
# Lazy import to avoid pulling in the whole AI stuff
from paperless_ai.ai_classifier import get_ai_document_classification
lock_key = (
f"{get_suggestion_cache_key(document.pk)}_llm_lock_"
f"{sha256(backend.encode()).hexdigest()}"
)
while True:
cached = get_llm_suggestion_cache(document.pk, backend)
cached = get_llm_suggestion_cache(document.pk, backend=backend)
if cached is not None:
refresh_suggestions_cache(document.pk)
return cached.suggestions
@@ -252,7 +257,7 @@ def retrieve_llm_suggestions(
if cache.add(lock_key, lock_token, lock_timeout):
try:
# The cache may have been populated while acquiring the lock.
cached = get_llm_suggestion_cache(document.pk, backend)
cached = get_llm_suggestion_cache(document.pk, backend=backend)
if cached is not None:
refresh_suggestions_cache(document.pk)
return cached.suggestions
@@ -275,7 +280,7 @@ def retrieve_llm_suggestions(
cache.delete(lock_key)
# Another worker is generating suggestions, poll to avoid another LLM request
time.sleep(0.1)
time.sleep(LLM_SUGGESTION_POLL_INTERVAL)
def set_llm_suggestions_cache(
src/documents/tests/test_api_documents.py
+1 -1
View File
@@ -2486,7 +2486,7 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
response = self.client.get("/api/documents/34676/suggestions/")
self.assertEqual(response.status_code, status.HTTP_404_NOT_FOUND)
@mock.patch("documents.caching.get_ai_document_classification")
@mock.patch("paperless_ai.ai_classifier.get_ai_document_classification")
@override_settings(AI_ENABLED=True)
def test_suggestions_still_uses_classifier_when_ai_enabled(
self,
src/documents/tests/test_caching.py
+3 -6
View File
@@ -3,8 +3,6 @@ from concurrent.futures import ThreadPoolExecutor
from threading import Event
from threading import Lock
from django.core.cache import cache
from documents.caching import StoredLRUCache
from documents.caching import retrieve_llm_suggestions
@@ -52,7 +50,6 @@ def test_stored_lru_cache_key_ttl(mocker) -> None:
def test_llm_suggestions_are_generated_once_for_concurrent_requests(mocker) -> None:
cache.clear()
generation_started = Event()
finish_generation = Event()
waiter_started = Event()
@@ -75,7 +72,7 @@ def test_llm_suggestions_are_generated_once_for_concurrent_requests(mocker) -> N
assert finish_generation.wait(timeout=2)
mock_get_classification = mocker.patch(
"documents.caching.get_ai_document_classification",
"paperless_ai.ai_classifier.get_ai_document_classification",
side_effect=generate,
)
mocker.patch("documents.caching.time.sleep", side_effect=wait_for_generation)
@@ -86,7 +83,7 @@ def test_llm_suggestions_are_generated_once_for_concurrent_requests(mocker) -> N
document,
user,
None,
"ollama:model",
backend="ollama:model",
lock_timeout=10,
)
assert generation_started.wait(timeout=2)
@@ -95,7 +92,7 @@ def test_llm_suggestions_are_generated_once_for_concurrent_requests(mocker) -> N
document,
user,
None,
"ollama:model",
backend="ollama:model",
lock_timeout=10,
)
assert waiter_started.wait(timeout=2)
src/documents/tests/test_views.py
+9 -9
View File
@@ -441,7 +441,7 @@ class TestAISuggestions(DirectoriesMixin, TestCase):
self.assertEqual(response.json()["tags"], [])
self.assertEqual(response.json()["suggested_tags"], [])
@patch("documents.caching.get_ai_document_classification")
@patch("paperless_ai.ai_classifier.get_ai_document_classification")
@override_settings(
AI_ENABLED=True,
LLM_BACKEND="mock_backend",
@@ -491,7 +491,7 @@ class TestAISuggestions(DirectoriesMixin, TestCase):
None,
)
@patch("documents.caching.get_ai_document_classification")
@patch("paperless_ai.ai_classifier.get_ai_document_classification")
@override_settings(
AI_ENABLED=True,
LLM_BACKEND="mock_backend",
@@ -529,7 +529,7 @@ class TestAISuggestions(DirectoriesMixin, TestCase):
"KI Title",
)
@patch("documents.caching.get_ai_document_classification")
@patch("paperless_ai.ai_classifier.get_ai_document_classification")
@override_settings(
AI_ENABLED=True,
LLM_BACKEND="mock_backend",
@@ -568,7 +568,7 @@ class TestAISuggestions(DirectoriesMixin, TestCase):
"Titre IA",
)
@patch("documents.caching.get_ai_document_classification")
@patch("paperless_ai.ai_classifier.get_ai_document_classification")
@override_settings(
AI_ENABLED=True,
LLM_BACKEND="mock_backend",
@@ -604,7 +604,7 @@ class TestAISuggestions(DirectoriesMixin, TestCase):
),
)
@patch("documents.caching.get_ai_document_classification")
@patch("paperless_ai.ai_classifier.get_ai_document_classification")
@override_settings(
AI_ENABLED=True,
LLM_BACKEND="openai-like",
@@ -633,7 +633,7 @@ class TestAISuggestions(DirectoriesMixin, TestCase):
get_llm_suggestion_cache(self.document.pk, backend="openai-like"),
)
@patch("documents.caching.get_ai_document_classification")
@patch("paperless_ai.ai_classifier.get_ai_document_classification")
@override_settings(
AI_ENABLED=True,
LLM_BACKEND="openai-like",
@@ -660,7 +660,7 @@ class TestAISuggestions(DirectoriesMixin, TestCase):
get_llm_suggestion_cache(self.document.pk, backend="openai-like"),
)
@patch("documents.caching.get_ai_document_classification")
@patch("paperless_ai.ai_classifier.get_ai_document_classification")
@override_settings(
AI_ENABLED=True,
LLM_BACKEND="mock_backend",
@@ -698,7 +698,7 @@ class TestAISuggestions(DirectoriesMixin, TestCase):
self.assertEqual(response.json()["tags"], [self.tag1.pk])
self.assertEqual(response.json()["suggested_tags"], ["Follow-up"])
@patch("documents.caching.get_ai_document_classification")
@patch("paperless_ai.ai_classifier.get_ai_document_classification")
@override_settings(
AI_ENABLED=True,
LLM_BACKEND="mock_backend",
@@ -737,7 +737,7 @@ class TestAISuggestions(DirectoriesMixin, TestCase):
self.assertEqual(response.json()["tags"], [self.tag1.pk])
self.assertEqual(response.json()["suggested_tags"], [])
@patch("documents.caching.get_ai_document_classification")
@patch("paperless_ai.ai_classifier.get_ai_document_classification")
@override_settings(
AI_ENABLED=True,
LLM_BACKEND="mock_backend",
src/documents/views.py
+4 -4
View File
@@ -1560,10 +1560,10 @@ class DocumentViewSet(
else:
try:
llm_suggestions = retrieve_llm_suggestions(
doc,
request.user,
output_language,
llm_cache_backend,
document=doc,
user=request.user,
output_language=output_language,
backend=llm_cache_backend,
# Classification, localization + 30s
lock_timeout=(2 * ai_config.llm_request_timeout) + 30,
)