dify/api/tasks/create_segment_to_index_task.py

96 lines
3.4 KiB
Python
Raw Normal View History

2023-05-15 08:51:32 +08:00
import datetime
import logging
import time
from typing import Optional
2023-05-15 08:51:32 +08:00
import click
from celery import shared_task
from werkzeug.exceptions import NotFound
from core.rag.index_processor.index_processor_factory import IndexProcessorFactory
from core.rag.models.document import Document
2023-05-15 08:51:32 +08:00
from extensions.ext_database import db
from extensions.ext_redis import redis_client
from models.dataset import DocumentSegment
@shared_task(queue="dataset")
def create_segment_to_index_task(segment_id: str, keywords: Optional[list[str]] = None):
2023-05-15 08:51:32 +08:00
"""
Async create segment to index
2023-05-15 08:51:32 +08:00
:param segment_id:
:param keywords:
Usage: create_segment_to_index_task.delay(segment_id)
2023-05-15 08:51:32 +08:00
"""
logging.info(click.style("Start create segment to index: {}".format(segment_id), fg="green"))
2023-05-15 08:51:32 +08:00
start_at = time.perf_counter()
segment = db.session.query(DocumentSegment).filter(DocumentSegment.id == segment_id).first()
if not segment:
raise NotFound("Segment not found")
2023-05-15 08:51:32 +08:00
if segment.status != "waiting":
2023-05-15 08:51:32 +08:00
return
indexing_cache_key = "segment_{}_indexing".format(segment.id)
2023-05-15 08:51:32 +08:00
try:
# update segment status to indexing
update_params = {
DocumentSegment.status: "indexing",
DocumentSegment.indexing_at: datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None),
}
DocumentSegment.query.filter_by(id=segment.id).update(update_params)
db.session.commit()
document = Document(
page_content=segment.content,
metadata={
"doc_id": segment.index_node_id,
"doc_hash": segment.index_node_hash,
"document_id": segment.document_id,
"dataset_id": segment.dataset_id,
},
2023-05-15 08:51:32 +08:00
)
dataset = segment.dataset
if not dataset:
logging.info(click.style("Segment {} has no dataset, pass.".format(segment.id), fg="cyan"))
return
2023-05-15 08:51:32 +08:00
dataset_document = segment.document
if not dataset_document:
logging.info(click.style("Segment {} has no document, pass.".format(segment.id), fg="cyan"))
return
if not dataset_document.enabled or dataset_document.archived or dataset_document.indexing_status != "completed":
logging.info(click.style("Segment {} document status is invalid, pass.".format(segment.id), fg="cyan"))
return
2023-05-15 08:51:32 +08:00
index_type = dataset.doc_form
index_processor = IndexProcessorFactory(index_type).init_index_processor()
index_processor.load(dataset, [document])
# update segment to completed
update_params = {
DocumentSegment.status: "completed",
DocumentSegment.completed_at: datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None),
}
DocumentSegment.query.filter_by(id=segment.id).update(update_params)
db.session.commit()
2023-05-15 08:51:32 +08:00
end_at = time.perf_counter()
logging.info(
click.style("Segment created to index: {} latency: {}".format(segment.id, end_at - start_at), fg="green")
)
2023-05-15 08:51:32 +08:00
except Exception as e:
logging.exception("create segment to index failed")
2023-05-15 08:51:32 +08:00
segment.enabled = False
segment.disabled_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
segment.status = "error"
2023-05-15 08:51:32 +08:00
segment.error = str(e)
db.session.commit()
finally:
redis_client.delete(indexing_cache_key)