mirror of
https://github.com/langgenius/dify.git
synced 2024-11-16 03:32:23 +08:00
52 lines
1.8 KiB
Python
52 lines
1.8 KiB
Python
import datetime
|
|
import logging
|
|
import time
|
|
|
|
import click
|
|
from celery import shared_task
|
|
from werkzeug.exceptions import NotFound
|
|
|
|
from core.indexing_runner import IndexingRunner, DocumentIsPausedException
|
|
from extensions.ext_database import db
|
|
from models.dataset import Document
|
|
|
|
|
|
@shared_task
|
|
def recover_document_indexing_task(dataset_id: str, document_id: str):
|
|
"""
|
|
Async recover document
|
|
:param dataset_id:
|
|
:param document_id:
|
|
|
|
Usage: recover_document_indexing_task.delay(dataset_id, document_id)
|
|
"""
|
|
logging.info(click.style('Recover document: {}'.format(document_id), fg='green'))
|
|
start_at = time.perf_counter()
|
|
|
|
document = db.session.query(Document).filter(
|
|
Document.id == document_id,
|
|
Document.dataset_id == dataset_id
|
|
).first()
|
|
|
|
if not document:
|
|
raise NotFound('Document not found')
|
|
|
|
try:
|
|
indexing_runner = IndexingRunner()
|
|
if document.indexing_status in ["waiting", "parsing", "cleaning"]:
|
|
indexing_runner.run(document)
|
|
elif document.indexing_status == "splitting":
|
|
indexing_runner.run_in_splitting_status(document)
|
|
elif document.indexing_status == "indexing":
|
|
indexing_runner.run_in_indexing_status(document)
|
|
end_at = time.perf_counter()
|
|
logging.info(click.style('Processed document: {} latency: {}'.format(document.id, end_at - start_at), fg='green'))
|
|
except DocumentIsPausedException:
|
|
logging.info(click.style('Document paused, document id: {}'.format(document.id), fg='yellow'))
|
|
except Exception as e:
|
|
logging.exception("consume document failed")
|
|
document.indexing_status = 'error'
|
|
document.error = str(e)
|
|
document.stopped_at = datetime.datetime.utcnow()
|
|
db.session.commit()
|