File size: 2,669 Bytes
4304c6d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 |
import datetime
import logging
import time
import click
from celery import shared_task
from werkzeug.exceptions import NotFound
from core.indexing_runner import DocumentIsPausedException, IndexingRunner
from core.rag.index_processor.index_processor_factory import IndexProcessorFactory
from extensions.ext_database import db
from models.dataset import Dataset, Document, DocumentSegment
@shared_task(queue='dataset')
def document_indexing_update_task(dataset_id: str, document_id: str):
"""
Async update document
:param dataset_id:
:param document_id:
Usage: document_indexing_update_task.delay(dataset_id, document_id)
"""
logging.info(click.style('Start update 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')
document.indexing_status = 'parsing'
document.processing_started_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
db.session.commit()
# delete all document segment and index
try:
dataset = db.session.query(Dataset).filter(Dataset.id == dataset_id).first()
if not dataset:
raise Exception('Dataset not found')
index_type = document.doc_form
index_processor = IndexProcessorFactory(index_type).init_index_processor()
segments = db.session.query(DocumentSegment).filter(DocumentSegment.document_id == document_id).all()
index_node_ids = [segment.index_node_id for segment in segments]
# delete from vector index
index_processor.clean(dataset, index_node_ids)
for segment in segments:
db.session.delete(segment)
db.session.commit()
end_at = time.perf_counter()
logging.info(
click.style('Cleaned document when document update data source or process rule: {} latency: {}'.format(document_id, end_at - start_at), fg='green'))
except Exception:
logging.exception("Cleaned document when document update data source or process rule failed")
try:
indexing_runner = IndexingRunner()
indexing_runner.run([document])
end_at = time.perf_counter()
logging.info(click.style('update document: {} latency: {}'.format(document.id, end_at - start_at), fg='green'))
except DocumentIsPausedException as ex:
logging.info(click.style(str(ex), fg='yellow'))
except Exception:
pass
|