Files
dify/api/tasks/clean_notion_document_task.py
T
+40 5bbf685035 feat: fix i18n missing keys and merge upstream/main (#24615)
Signed-off-by: -LAN- <[email protected]>
Signed-off-by: kenwoodjw <[email protected]>
Signed-off-by: Yongtao Huang <[email protected]>
Signed-off-by: yihong0618 <[email protected]>
Signed-off-by: zhanluxianshen <[email protected]>
Co-authored-by: -LAN- <[email protected]>
Co-authored-by: GuanMu <[email protected]>
Co-authored-by: Davide Delbianco <[email protected]>
Co-authored-by: NeatGuyCoding <[email protected]>
Co-authored-by: kenwoodjw <[email protected]>
Co-authored-by: Yongtao Huang <[email protected]>
Co-authored-by: Yongtao Huang <[email protected]>
Co-authored-by: Qiang Lee <[email protected]>
Co-authored-by: 李强04 <[email protected]>
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Co-authored-by: Asuka Minato <[email protected]>
Co-authored-by: Matri Qi <[email protected]>
Co-authored-by: huayaoyue6 <[email protected]>
Co-authored-by: Bowen Liang <[email protected]>
Co-authored-by: znn <[email protected]>
Co-authored-by: crazywoola <[email protected]>
Co-authored-by: crazywoola <[email protected]>
Co-authored-by: Copilot <[email protected]>
Co-authored-by: yihong <[email protected]>
Co-authored-by: Muke Wang <[email protected]>
Co-authored-by: wangmuke <[email protected]>
Co-authored-by: Wu Tianwei <[email protected]>
Co-authored-by: quicksand <[email protected]>
Co-authored-by: 非法操作 <[email protected]>
Co-authored-by: zxhlyh <[email protected]>
Co-authored-by: Eric Guo <[email protected]>
Co-authored-by: Zhedong Cen <[email protected]>
Co-authored-by: jiangbo721 <[email protected]>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: hjlarry <[email protected]>
Co-authored-by: lxsummer <[email protected]>
Co-authored-by: 湛露先生 <[email protected]>
Co-authored-by: Guangdong Liu <[email protected]>
Co-authored-by: QuantumGhost <[email protected]>
Co-authored-by: Claude <[email protected]>
Co-authored-by: Yessenia-d <[email protected]>
Co-authored-by: huangzhuo1949 <[email protected]>
Co-authored-by: huangzhuo <[email protected]>
Co-authored-by: 17hz <[email protected]>
Co-authored-by: Amy <[email protected]>
Co-authored-by: Joel <[email protected]>
Co-authored-by: Nite Knite <[email protected]>
Co-authored-by: Yeuoly <[email protected]>
Co-authored-by: Petrus Han <[email protected]>
Co-authored-by: iamjoel <[email protected]>
Co-authored-by: Kalo Chin <[email protected]>
Co-authored-by: Ujjwal Maurya <[email protected]>
Co-authored-by: Maries <[email protected]>
2025-08-27 15:07:28 +08:00

58 lines
2.0 KiB
Python

import logging
import time
import click
from celery import shared_task
from core.rag.index_processor.index_processor_factory import IndexProcessorFactory
from extensions.ext_database import db
from models.dataset import Dataset, Document, DocumentSegment
logger = logging.getLogger(__name__)
@shared_task(queue="dataset")
def clean_notion_document_task(document_ids: list[str], dataset_id: str):
"""
Clean document when document deleted.
:param document_ids: document ids
:param dataset_id: dataset id
Usage: clean_notion_document_task.delay(document_ids, dataset_id)
"""
logger.info(click.style(f"Start clean document when import form notion document deleted: {dataset_id}", fg="green"))
start_at = time.perf_counter()
try:
dataset = db.session.query(Dataset).where(Dataset.id == dataset_id).first()
if not dataset:
raise Exception("Document has no dataset")
index_type = dataset.doc_form
index_processor = IndexProcessorFactory(index_type).init_index_processor()
for document_id in document_ids:
document = db.session.query(Document).where(Document.id == document_id).first()
db.session.delete(document)
segments = db.session.query(DocumentSegment).where(DocumentSegment.document_id == document_id).all()
index_node_ids = [segment.index_node_id for segment in segments]
index_processor.clean(dataset, index_node_ids, with_keywords=True, delete_child_chunks=True)
for segment in segments:
db.session.delete(segment)
db.session.commit()
end_at = time.perf_counter()
logger.info(
click.style(
"Clean document when import form notion document deleted end :: {} latency: {}".format(
dataset_id, end_at - start_at
),
fg="green",
)
)
except Exception:
logger.exception("Cleaned document when import form notion document deleted failed")
finally:
db.session.close()