mirror of
https://github.com/paperless-ngx/paperless-ngx.git
synced 2026-09-25 10:50:32 +00:00
Feature: Switch all indexing to use rich (#12193)
This commit is contained in:
@@ -1,22 +1,25 @@
|
||||
from django.core.management import BaseCommand
|
||||
from django.db import transaction
|
||||
|
||||
from documents.management.commands.mixins import ProgressBarMixin
|
||||
from documents.management.commands.base import PaperlessCommand
|
||||
from documents.tasks import index_optimize
|
||||
from documents.tasks import index_reindex
|
||||
|
||||
|
||||
class Command(ProgressBarMixin, BaseCommand):
|
||||
class Command(PaperlessCommand):
|
||||
help = "Manages the document index."
|
||||
|
||||
def add_arguments(self, parser):
|
||||
super().add_arguments(parser)
|
||||
parser.add_argument("command", choices=["reindex", "optimize"])
|
||||
self.add_argument_progress_bar_mixin(parser)
|
||||
|
||||
def handle(self, *args, **options):
|
||||
self.handle_progress_bar_mixin(**options)
|
||||
with transaction.atomic():
|
||||
if options["command"] == "reindex":
|
||||
index_reindex(progress_bar_disable=self.no_progress_bar)
|
||||
index_reindex(
|
||||
iter_wrapper=lambda docs: self.track(
|
||||
docs,
|
||||
description="Indexing documents...",
|
||||
),
|
||||
)
|
||||
elif options["command"] == "optimize":
|
||||
index_optimize()
|
||||
|
||||
@@ -1,22 +1,22 @@
|
||||
from django.core.management import BaseCommand
|
||||
from django.db import transaction
|
||||
from typing import Any
|
||||
|
||||
from documents.management.commands.mixins import ProgressBarMixin
|
||||
from documents.management.commands.base import PaperlessCommand
|
||||
from documents.tasks import llmindex_index
|
||||
|
||||
|
||||
class Command(ProgressBarMixin, BaseCommand):
|
||||
class Command(PaperlessCommand):
|
||||
help = "Manages the LLM-based vector index for Paperless."
|
||||
|
||||
def add_arguments(self, parser):
|
||||
def add_arguments(self, parser: Any) -> None:
|
||||
super().add_arguments(parser)
|
||||
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():
|
||||
llmindex_index(
|
||||
progress_bar_disable=self.no_progress_bar,
|
||||
rebuild=options["command"] == "rebuild",
|
||||
scheduled=False,
|
||||
)
|
||||
def handle(self, *args: Any, **options: Any) -> None:
|
||||
llmindex_index(
|
||||
rebuild=options["command"] == "rebuild",
|
||||
scheduled=False,
|
||||
iter_wrapper=lambda docs: self.track(
|
||||
docs,
|
||||
description="Indexing documents...",
|
||||
),
|
||||
)
|
||||
|
||||
+15
-6
@@ -4,11 +4,13 @@ import logging
|
||||
import shutil
|
||||
import uuid
|
||||
import zipfile
|
||||
from collections.abc import Callable
|
||||
from collections.abc import Iterable
|
||||
from pathlib import Path
|
||||
from tempfile import TemporaryDirectory
|
||||
from tempfile import mkstemp
|
||||
from typing import TypeVar
|
||||
|
||||
import tqdm
|
||||
from celery import Task
|
||||
from celery import shared_task
|
||||
from celery import states
|
||||
@@ -66,11 +68,19 @@ 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 update_llm_index
|
||||
|
||||
_T = TypeVar("_T")
|
||||
IterWrapper = Callable[[Iterable[_T]], Iterable[_T]]
|
||||
|
||||
|
||||
if settings.AUDIT_LOG_ENABLED:
|
||||
from auditlog.models import LogEntry
|
||||
logger = logging.getLogger("paperless.tasks")
|
||||
|
||||
|
||||
def _identity(iterable: Iterable[_T]) -> Iterable[_T]:
|
||||
return iterable
|
||||
|
||||
|
||||
@shared_task
|
||||
def index_optimize() -> None:
|
||||
ix = index.open_index()
|
||||
@@ -78,13 +88,13 @@ def index_optimize() -> None:
|
||||
writer.commit(optimize=True)
|
||||
|
||||
|
||||
def index_reindex(*, progress_bar_disable=False) -> None:
|
||||
def index_reindex(*, iter_wrapper: IterWrapper[Document] = _identity) -> None:
|
||||
documents = Document.objects.all()
|
||||
|
||||
ix = index.open_index(recreate=True)
|
||||
|
||||
with AsyncWriter(ix) as writer:
|
||||
for document in tqdm.tqdm(documents, disable=progress_bar_disable):
|
||||
for document in iter_wrapper(documents):
|
||||
index.update_document(writer, document)
|
||||
|
||||
|
||||
@@ -265,7 +275,6 @@ def bulk_update_documents(document_ids) -> None:
|
||||
ai_config = AIConfig()
|
||||
if ai_config.llm_index_enabled:
|
||||
update_llm_index(
|
||||
progress_bar_disable=True,
|
||||
rebuild=False,
|
||||
)
|
||||
|
||||
@@ -606,7 +615,7 @@ def update_document_parent_tags(tag: Tag, new_parent: Tag) -> None:
|
||||
@shared_task
|
||||
def llmindex_index(
|
||||
*,
|
||||
progress_bar_disable=True,
|
||||
iter_wrapper: IterWrapper[Document] = _identity,
|
||||
rebuild=False,
|
||||
scheduled=True,
|
||||
auto=False,
|
||||
@@ -629,7 +638,7 @@ def llmindex_index(
|
||||
|
||||
try:
|
||||
result = update_llm_index(
|
||||
progress_bar_disable=progress_bar_disable,
|
||||
iter_wrapper=iter_wrapper,
|
||||
rebuild=rebuild,
|
||||
)
|
||||
task.status = states.SUCCESS
|
||||
|
||||
Reference in New Issue
Block a user