dify/api/tasks/clean_document_task.py
Yeuoly 403e2d58b9
Introduce Plugins (#13836)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
Signed-off-by: -LAN- <laipz8200@outlook.com>
Signed-off-by: xhe <xw897002528@gmail.com>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: takatost <takatost@gmail.com>
Co-authored-by: kurokobo <kuro664@gmail.com>
Co-authored-by: Novice Lee <novicelee@NoviPro.local>
Co-authored-by: zxhlyh <jasonapring2015@outlook.com>
Co-authored-by: AkaraChen <akarachen@outlook.com>
Co-authored-by: Yi <yxiaoisme@gmail.com>
Co-authored-by: Joel <iamjoel007@gmail.com>
Co-authored-by: JzoNg <jzongcode@gmail.com>
Co-authored-by: twwu <twwu@dify.ai>
Co-authored-by: Hiroshi Fujita <fujita-h@users.noreply.github.com>
Co-authored-by: AkaraChen <85140972+AkaraChen@users.noreply.github.com>
Co-authored-by: NFish <douxc512@gmail.com>
Co-authored-by: Wu Tianwei <30284043+WTW0313@users.noreply.github.com>
Co-authored-by: 非法操作 <hjlarry@163.com>
Co-authored-by: Novice <857526207@qq.com>
Co-authored-by: Hiroki Nagai <82458324+nagaihiroki-git@users.noreply.github.com>
Co-authored-by: Gen Sato <52241300+halogen22@users.noreply.github.com>
Co-authored-by: eux <euxuuu@gmail.com>
Co-authored-by: huangzhuo1949 <167434202+huangzhuo1949@users.noreply.github.com>
Co-authored-by: huangzhuo <huangzhuo1@xiaomi.com>
Co-authored-by: lotsik <lotsik@mail.ru>
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
Co-authored-by: nite-knite <nkCoding@gmail.com>
Co-authored-by: Jyong <76649700+JohnJyong@users.noreply.github.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: gakkiyomi <gakkiyomi@aliyun.com>
Co-authored-by: CN-P5 <heibai2006@gmail.com>
Co-authored-by: CN-P5 <heibai2006@qq.com>
Co-authored-by: Chuehnone <1897025+chuehnone@users.noreply.github.com>
Co-authored-by: yihong <zouzou0208@gmail.com>
Co-authored-by: Kevin9703 <51311316+Kevin9703@users.noreply.github.com>
Co-authored-by: -LAN- <laipz8200@outlook.com>
Co-authored-by: Boris Feld <lothiraldan@gmail.com>
Co-authored-by: mbo <himabo@gmail.com>
Co-authored-by: mabo <mabo@aeyes.ai>
Co-authored-by: Warren Chen <warren.chen830@gmail.com>
Co-authored-by: JzoNgKVO <27049666+JzoNgKVO@users.noreply.github.com>
Co-authored-by: jiandanfeng <chenjh3@wangsu.com>
Co-authored-by: zhu-an <70234959+xhdd123321@users.noreply.github.com>
Co-authored-by: zhaoqingyu.1075 <zhaoqingyu.1075@bytedance.com>
Co-authored-by: 海狸大師 <86974027+yenslife@users.noreply.github.com>
Co-authored-by: Xu Song <xusong.vip@gmail.com>
Co-authored-by: rayshaw001 <396301947@163.com>
Co-authored-by: Ding Jiatong <dingjiatong@gmail.com>
Co-authored-by: Bowen Liang <liangbowen@gf.com.cn>
Co-authored-by: JasonVV <jasonwangiii@outlook.com>
Co-authored-by: le0zh <newlight@qq.com>
Co-authored-by: zhuxinliang <zhuxinliang@didiglobal.com>
Co-authored-by: k-zaku <zaku99@outlook.jp>
Co-authored-by: luckylhb90 <luckylhb90@gmail.com>
Co-authored-by: hobo.l <hobo.l@binance.com>
Co-authored-by: jiangbo721 <365065261@qq.com>
Co-authored-by: 刘江波 <jiangbo721@163.com>
Co-authored-by: Shun Miyazawa <34241526+miya@users.noreply.github.com>
Co-authored-by: EricPan <30651140+Egfly@users.noreply.github.com>
Co-authored-by: crazywoola <427733928@qq.com>
Co-authored-by: sino <sino2322@gmail.com>
Co-authored-by: Jhvcc <37662342+Jhvcc@users.noreply.github.com>
Co-authored-by: lowell <lowell.hu@zkteco.in>
Co-authored-by: Boris Polonsky <BorisPolonsky@users.noreply.github.com>
Co-authored-by: Ademílson Tonato <ademilsonft@outlook.com>
Co-authored-by: Ademílson Tonato <ademilson.tonato@refurbed.com>
Co-authored-by: IWAI, Masaharu <iwaim.sub@gmail.com>
Co-authored-by: Yueh-Po Peng (Yabi) <94939112+y10ab1@users.noreply.github.com>
Co-authored-by: Jason <ggbbddjm@gmail.com>
Co-authored-by: Xin Zhang <sjhpzx@gmail.com>
Co-authored-by: yjc980121 <3898524+yjc980121@users.noreply.github.com>
Co-authored-by: heyszt <36215648+hieheihei@users.noreply.github.com>
Co-authored-by: Abdullah AlOsaimi <osaimiacc@gmail.com>
Co-authored-by: Abdullah AlOsaimi <189027247+osaimi@users.noreply.github.com>
Co-authored-by: Yingchun Lai <laiyingchun@apache.org>
Co-authored-by: Hash Brown <hi@xzd.me>
Co-authored-by: zuodongxu <192560071+zuodongxu@users.noreply.github.com>
Co-authored-by: Masashi Tomooka <tmokmss@users.noreply.github.com>
Co-authored-by: aplio <ryo.091219@gmail.com>
Co-authored-by: Obada Khalili <54270856+obadakhalili@users.noreply.github.com>
Co-authored-by: Nam Vu <zuzoovn@gmail.com>
Co-authored-by: Kei YAMAZAKI <1715090+kei-yamazaki@users.noreply.github.com>
Co-authored-by: TechnoHouse <13776377+deephbz@users.noreply.github.com>
Co-authored-by: Riddhimaan-Senapati <114703025+Riddhimaan-Senapati@users.noreply.github.com>
Co-authored-by: MaFee921 <31881301+2284730142@users.noreply.github.com>
Co-authored-by: te-chan <t-nakanome@sakura-is.co.jp>
Co-authored-by: HQidea <HQidea@users.noreply.github.com>
Co-authored-by: Joshbly <36315710+Joshbly@users.noreply.github.com>
Co-authored-by: xhe <xw897002528@gmail.com>
Co-authored-by: weiwenyan-dev <154779315+weiwenyan-dev@users.noreply.github.com>
Co-authored-by: ex_wenyan.wei <ex_wenyan.wei@tcl.com>
Co-authored-by: engchina <12236799+engchina@users.noreply.github.com>
Co-authored-by: engchina <atjapan2015@gmail.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: 呆萌闷油瓶 <253605712@qq.com>
Co-authored-by: Kemal <kemalmeler@outlook.com>
Co-authored-by: Lazy_Frog <4590648+lazyFrogLOL@users.noreply.github.com>
Co-authored-by: Yi Xiao <54782454+YIXIAO0@users.noreply.github.com>
Co-authored-by: Steven sun <98230804+Tuyohai@users.noreply.github.com>
Co-authored-by: steven <sunzwj@digitalchina.com>
Co-authored-by: Kalo Chin <91766386+fdb02983rhy@users.noreply.github.com>
Co-authored-by: Katy Tao <34019945+KatyTao@users.noreply.github.com>
Co-authored-by: depy <42985524+h4ckdepy@users.noreply.github.com>
Co-authored-by: 胡春东 <gycm520@gmail.com>
Co-authored-by: Junjie.M <118170653@qq.com>
Co-authored-by: MuYu <mr.muzea@gmail.com>
Co-authored-by: Naoki Takashima <39912547+takatea@users.noreply.github.com>
Co-authored-by: Summer-Gu <37869445+gubinjie@users.noreply.github.com>
Co-authored-by: Fei He <droxer.he@gmail.com>
Co-authored-by: ybalbert001 <120714773+ybalbert001@users.noreply.github.com>
Co-authored-by: Yuanbo Li <ybalbert@amazon.com>
Co-authored-by: douxc <7553076+douxc@users.noreply.github.com>
Co-authored-by: liuzhenghua <1090179900@qq.com>
Co-authored-by: Wu Jiayang <62842862+Wu-Jiayang@users.noreply.github.com>
Co-authored-by: Your Name <you@example.com>
Co-authored-by: kimjion <45935338+kimjion@users.noreply.github.com>
Co-authored-by: AugNSo <song.tiankai@icloud.com>
Co-authored-by: llinvokerl <38915183+llinvokerl@users.noreply.github.com>
Co-authored-by: liusurong.lsr <liusurong.lsr@alibaba-inc.com>
Co-authored-by: Vasu Negi <vasu-negi@users.noreply.github.com>
Co-authored-by: Hundredwz <1808096180@qq.com>
Co-authored-by: Xiyuan Chen <52963600+GareArc@users.noreply.github.com>
2025-02-17 17:05:13 +08:00

79 lines
3.1 KiB
Python

import logging
import time
from typing import Optional
import click
from celery import shared_task # type: ignore
from core.rag.index_processor.index_processor_factory import IndexProcessorFactory
from core.tools.utils.rag_web_reader import get_image_upload_file_ids
from extensions.ext_database import db
from extensions.ext_storage import storage
from models.dataset import Dataset, DocumentSegment
from models.model import UploadFile
@shared_task(queue="dataset")
def clean_document_task(document_id: str, dataset_id: str, doc_form: str, file_id: Optional[str]):
"""
Clean document when document deleted.
:param document_id: document id
:param dataset_id: dataset id
:param doc_form: doc_form
:param file_id: file id
Usage: clean_document_task.delay(document_id, dataset_id)
"""
logging.info(click.style("Start clean document when document deleted: {}".format(document_id), fg="green"))
start_at = time.perf_counter()
try:
dataset = db.session.query(Dataset).filter(Dataset.id == dataset_id).first()
if not dataset:
raise Exception("Document has no dataset")
segments = db.session.query(DocumentSegment).filter(DocumentSegment.document_id == document_id).all()
# check segment is exist
if segments:
index_node_ids = [segment.index_node_id for segment in segments]
index_processor = IndexProcessorFactory(doc_form).init_index_processor()
index_processor.clean(dataset, index_node_ids, with_keywords=True, delete_child_chunks=True)
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()
if image_file is None:
continue
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(image_file)
db.session.delete(segment)
db.session.commit()
if file_id:
file = db.session.query(UploadFile).filter(UploadFile.id == file_id).first()
if file:
try:
storage.delete(file.key)
except Exception:
logging.exception("Delete file failed when document deleted, file_id: {}".format(file_id))
db.session.delete(file)
db.session.commit()
end_at = time.perf_counter()
logging.info(
click.style(
"Cleaned document when document deleted: {} latency: {}".format(document_id, end_at - start_at),
fg="green",
)
)
except Exception:
logging.exception("Cleaned document when document deleted failed")