mirror of
https://github.com/langgenius/dify.git
synced 2026-03-26 22:52:38 +08:00
52 lines
1.6 KiB
Python
52 lines
1.6 KiB
Python
import contextlib
|
|
import logging
|
|
import time
|
|
|
|
import click
|
|
from sqlalchemy import select
|
|
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
|
|
from models.enums import IndexingStatus
|
|
|
|
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.scalar(
|
|
select(Document).where(
|
|
Document.id == document_id,
|
|
Document.dataset_id == dataset_id,
|
|
)
|
|
)
|
|
|
|
if not document:
|
|
raise NotFound("Document not found")
|
|
|
|
document.indexing_status = IndexingStatus.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"))
|