Feat/support parent child chunk (#12092)
This commit is contained in:
@@ -6,48 +6,38 @@ from celery import shared_task # type: ignore
|
||||
|
||||
from core.rag.index_processor.index_processor_factory import IndexProcessorFactory
|
||||
from extensions.ext_database import db
|
||||
from extensions.ext_redis import redis_client
|
||||
from models.dataset import Dataset, Document
|
||||
|
||||
|
||||
@shared_task(queue="dataset")
|
||||
def delete_segment_from_index_task(segment_id: str, index_node_id: str, dataset_id: str, document_id: str):
|
||||
def delete_segment_from_index_task(index_node_ids: list, dataset_id: str, document_id: str):
|
||||
"""
|
||||
Async Remove segment from index
|
||||
:param segment_id:
|
||||
:param index_node_id:
|
||||
:param index_node_ids:
|
||||
:param dataset_id:
|
||||
:param document_id:
|
||||
|
||||
Usage: delete_segment_from_index_task.delay(segment_id)
|
||||
Usage: delete_segment_from_index_task.delay(segment_ids)
|
||||
"""
|
||||
logging.info(click.style("Start delete segment from index: {}".format(segment_id), fg="green"))
|
||||
logging.info(click.style("Start delete segment from index", fg="green"))
|
||||
start_at = time.perf_counter()
|
||||
indexing_cache_key = "segment_{}_delete_indexing".format(segment_id)
|
||||
try:
|
||||
dataset = db.session.query(Dataset).filter(Dataset.id == dataset_id).first()
|
||||
if not dataset:
|
||||
logging.info(click.style("Segment {} has no dataset, pass.".format(segment_id), fg="cyan"))
|
||||
return
|
||||
|
||||
dataset_document = db.session.query(Document).filter(Document.id == document_id).first()
|
||||
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
|
||||
|
||||
index_type = dataset_document.doc_form
|
||||
index_processor = IndexProcessorFactory(index_type).init_index_processor()
|
||||
index_processor.clean(dataset, [index_node_id])
|
||||
index_processor.clean(dataset, index_node_ids, with_keywords=True, delete_child_chunks=True)
|
||||
|
||||
end_at = time.perf_counter()
|
||||
logging.info(
|
||||
click.style("Segment deleted from index: {} latency: {}".format(segment_id, end_at - start_at), fg="green")
|
||||
)
|
||||
logging.info(click.style("Segment deleted from index latency: {}".format(end_at - start_at), fg="green"))
|
||||
except Exception:
|
||||
logging.exception("delete segment from index failed")
|
||||
finally:
|
||||
redis_client.delete(indexing_cache_key)
|
||||
|
Reference in New Issue
Block a user