paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-08-12 00:19:48 +00:00
Code Issues Packages Projects Releases Wiki Activity

Incremental llm index update, add scheduled llm index task

Browse Source
This commit is contained in:
shamoon
2025-04-28 10:29:07 -07:00
parent f6a3882199
commit 2481a66544
8 changed files with 154 additions and 48 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
src/documents/management/commands/document_llmindex.py
View File

@@ -2,20 +2,20 @@ from django.core.management import BaseCommand
from django.db import transaction
from documents.management.commands.mixins import ProgressBarMixin
from documents.tasks import llm_index_rebuild
from documents.tasks import llmindex_index
class Command(ProgressBarMixin, BaseCommand):
help = "Manages the LLM-based vector index for Paperless."
def add_arguments(self, parser):
parser.add_argument("command", choices=["rebuild"])
parser.add_argument("command", choices=["rebuild", "update"])
self.add_argument_progress_bar_mixin(parser)
def handle(self, *args, **options):
self.handle_progress_bar_mixin(**options)
with transaction.atomic():
llm_index_rebuild(
llmindex_index(
progress_bar_disable=self.no_progress_bar,
rebuild=options["command"] == "rebuild",
)

19
src/documents/tasks.py
View File

@@ -56,7 +56,7 @@ from documents.signals.handlers import cleanup_document_deletion
from documents.signals.handlers import run_workflows
from paperless.ai.indexing import llm_index_add_or_update_document
from paperless.ai.indexing import llm_index_remove_document
from paperless.ai.indexing import rebuild_llm_index
from paperless.ai.indexing import update_llm_index
from paperless.config import AIConfig
if settings.AUDIT_LOG_ENABLED:
@@ -532,11 +532,14 @@ def check_scheduled_workflows():
)
def llm_index_rebuild(*, progress_bar_disable=False, rebuild=False):
rebuild_llm_index(
progress_bar_disable=progress_bar_disable,
rebuild=rebuild,
)
@shared_task
def llmindex_index(*, progress_bar_disable=False, rebuild=False):
ai_config = AIConfig()
if ai_config.llm_index_enabled():
update_llm_index(
progress_bar_disable=progress_bar_disable,
rebuild=rebuild,
)
@shared_task
@@ -552,6 +555,6 @@ def remove_document_from_llm_index(document):
# TODO: schedule to run periodically
@shared_task
def rebuild_llm_index_task():
from paperless.ai.indexing import rebuild_llm_index
from paperless.ai.indexing import update_llm_index
rebuild_llm_index(rebuild=True)
update_llm_index(rebuild=True)