mirror of
https://github.com/langgenius/dify.git
synced 2026-01-14 06:07:33 +08:00
Signed-off-by: -LAN- <laipz8200@outlook.com> Signed-off-by: kenwoodjw <blackxin55+@gmail.com> Signed-off-by: Yongtao Huang <yongtaoh2022@gmail.com> Signed-off-by: yihong0618 <zouzou0208@gmail.com> Signed-off-by: zhanluxianshen <zhanluxianshen@163.com> Co-authored-by: -LAN- <laipz8200@outlook.com> Co-authored-by: GuanMu <ballmanjq@gmail.com> Co-authored-by: Davide Delbianco <davide.delbianco@outlook.com> Co-authored-by: NeatGuyCoding <15627489+NeatGuyCoding@users.noreply.github.com> Co-authored-by: kenwoodjw <blackxin55+@gmail.com> Co-authored-by: Yongtao Huang <yongtaoh2022@gmail.com> Co-authored-by: Yongtao Huang <99629139+hyongtao-db@users.noreply.github.com> Co-authored-by: Qiang Lee <18018968632@163.com> Co-authored-by: 李强04 <liqiang04@gaotu.cn> Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com> Co-authored-by: Asuka Minato <i@asukaminato.eu.org> Co-authored-by: Matri Qi <matrixdom@126.com> Co-authored-by: huayaoyue6 <huayaoyue@163.com> Co-authored-by: Bowen Liang <liangbowen@gf.com.cn> Co-authored-by: znn <jubinkumarsoni@gmail.com> Co-authored-by: crazywoola <427733928@qq.com> Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: yihong <zouzou0208@gmail.com> Co-authored-by: Muke Wang <shaodwaaron@gmail.com> Co-authored-by: wangmuke <wangmuke@kingsware.cn> Co-authored-by: Wu Tianwei <30284043+WTW0313@users.noreply.github.com> Co-authored-by: quicksand <quicksandzn@gmail.com> Co-authored-by: 非法操作 <hjlarry@163.com> Co-authored-by: zxhlyh <jasonapring2015@outlook.com> Co-authored-by: Eric Guo <eric.guocz@gmail.com> Co-authored-by: Zhedong Cen <cenzhedong2@126.com> Co-authored-by: jiangbo721 <jiangbo721@163.com> Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: hjlarry <25834719+hjlarry@users.noreply.github.com> Co-authored-by: lxsummer <35754229+lxjustdoit@users.noreply.github.com> Co-authored-by: 湛露先生 <zhanluxianshen@163.com> Co-authored-by: Guangdong Liu <liugddx@gmail.com> Co-authored-by: QuantumGhost <obelisk.reg+git@gmail.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Yessenia-d <yessenia.contact@gmail.com> Co-authored-by: huangzhuo1949 <167434202+huangzhuo1949@users.noreply.github.com> Co-authored-by: huangzhuo <huangzhuo1@xiaomi.com> Co-authored-by: 17hz <0x149527@gmail.com> Co-authored-by: Amy <1530140574@qq.com> Co-authored-by: Joel <iamjoel007@gmail.com> Co-authored-by: Nite Knite <nkCoding@gmail.com> Co-authored-by: Yeuoly <45712896+Yeuoly@users.noreply.github.com> Co-authored-by: Petrus Han <petrus.hanks@gmail.com> Co-authored-by: iamjoel <2120155+iamjoel@users.noreply.github.com> Co-authored-by: Kalo Chin <frog.beepers.0n@icloud.com> Co-authored-by: Ujjwal Maurya <ujjwalsbx@gmail.com> Co-authored-by: Maries <xh001x@hotmail.com>
52 lines
1.6 KiB
Python
52 lines
1.6 KiB
Python
import contextlib
|
|
import logging
|
|
import time
|
|
|
|
import click
|
|
from werkzeug.exceptions import NotFound
|
|
|
|
from core.indexing_runner import DocumentIsPausedError, IndexingRunner
|
|
from events.document_index_event import document_index_created
|
|
from extensions.ext_database import db
|
|
from libs.datetime_utils import naive_utc_now
|
|
from models.dataset import Document
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
@document_index_created.connect
|
|
def handle(sender, **kwargs):
|
|
dataset_id = sender
|
|
document_ids = kwargs.get("document_ids", [])
|
|
documents = []
|
|
start_at = time.perf_counter()
|
|
for document_id in document_ids:
|
|
logger.info(click.style(f"Start process document: {document_id}", fg="green"))
|
|
|
|
document = (
|
|
db.session.query(Document)
|
|
.where(
|
|
Document.id == document_id,
|
|
Document.dataset_id == dataset_id,
|
|
)
|
|
.first()
|
|
)
|
|
|
|
if not document:
|
|
raise NotFound("Document not found")
|
|
|
|
document.indexing_status = "parsing"
|
|
document.processing_started_at = naive_utc_now()
|
|
documents.append(document)
|
|
db.session.add(document)
|
|
db.session.commit()
|
|
|
|
with contextlib.suppress(Exception):
|
|
try:
|
|
indexing_runner = IndexingRunner()
|
|
indexing_runner.run(documents)
|
|
end_at = time.perf_counter()
|
|
logger.info(click.style(f"Processed dataset: {dataset_id} latency: {end_at - start_at}", fg="green"))
|
|
except DocumentIsPausedError as ex:
|
|
logger.info(click.style(str(ex), fg="yellow"))
|