fix issues:Image file not deleted when a doc is removed #9541 (#10465)

Signed-off-by: root <root@localhost.localdomain>
Co-authored-by: root <root@localhost.localdomain>
This commit is contained in:
liuhaoran
2024-11-11 21:43:37 +08:00
committed by GitHub
parent 9550b884f7
commit 570f10d91c
3 changed files with 38 additions and 0 deletions

View File

@@ -5,6 +5,7 @@ import click
from celery import shared_task
from core.rag.index_processor.index_processor_factory import IndexProcessorFactory
from core.tools.utils.web_reader_tool import get_image_upload_file_ids
from extensions.ext_database import db
from extensions.ext_storage import storage
from models.dataset import (
@@ -67,6 +68,16 @@ def clean_dataset_task(
db.session.delete(document)
for segment in segments:
image_upload_file_ids = get_image_upload_file_ids(segment.content)
for upload_file_id in image_upload_file_ids:
image_file = db.session.query(UploadFile).filter(UploadFile.id == upload_file_id).first()
try:
storage.delete(image_file.key)
except Exception:
logging.exception(
"Delete image_files failed when storage deleted, \
image_upload_file_is: {}".format(upload_file_id)
)
db.session.delete(segment)
db.session.query(DatasetProcessRule).filter(DatasetProcessRule.dataset_id == dataset_id).delete()