estel/dify
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

feat: mypy for all type check (#10921)

Browse Source
This commit is contained in:
yihong
2024-12-24 18:38:51 +08:00
committed by GitHub
parent c91e8b1737
commit 56e15d09a9
584 changed files with 3975 additions and 2826 deletions
Download Patch File Download Diff File Expand all files Collapse all files

45
api/tasks/retry_document_indexing_task.py
View File

@@ -3,7 +3,7 @@ import logging
import time
import click
from celery import shared_task
from celery import shared_task # type: ignore
from core.indexing_runner import IndexingRunner
from core.rag.index_processor.index_processor_factory import IndexProcessorFactory
@@ -22,10 +22,13 @@ def retry_document_indexing_task(dataset_id: str, document_ids: list[str]):
Usage: retry_document_indexing_task.delay(dataset_id, document_id)
"""
documents = []
documents: list[Document] = []
start_at = time.perf_counter()
dataset = db.session.query(Dataset).filter(Dataset.id == dataset_id).first()
if not dataset:
raise ValueError("Dataset not found")
for document_id in document_ids:
retry_indexing_cache_key = "document_{}_is_retried".format(document_id)
# check document limit
@@ -55,29 +58,31 @@ def retry_document_indexing_task(dataset_id: str, document_ids: list[str]):
document = (
db.session.query(Document).filter(Document.id == document_id, Document.dataset_id == dataset_id).first()
)
if not document:
logging.info(click.style("Document not found: {}".format(document_id), fg="yellow"))
return
try:
if document:
# clean old data
index_processor = IndexProcessorFactory(document.doc_form).init_index_processor()
# clean old data
index_processor = IndexProcessorFactory(document.doc_form).init_index_processor()
segments = db.session.query(DocumentSegment).filter(DocumentSegment.document_id == document_id).all()
if segments:
index_node_ids = [segment.index_node_id for segment in segments]
# delete from vector index
index_processor.clean(dataset, index_node_ids)
segments = db.session.query(DocumentSegment).filter(DocumentSegment.document_id == document_id).all()
if segments:
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()
document.indexing_status = "parsing"
document.processing_started_at = datetime.datetime.utcnow()
db.session.add(document)
for segment in segments:
db.session.delete(segment)
db.session.commit()
indexing_runner = IndexingRunner()
indexing_runner.run([document])
redis_client.delete(retry_indexing_cache_key)
document.indexing_status = "parsing"
document.processing_started_at = datetime.datetime.utcnow()
db.session.add(document)
db.session.commit()
indexing_runner = IndexingRunner()
indexing_runner.run([document])
redis_client.delete(retry_indexing_cache_key)
except Exception as ex:
document.indexing_status = "error"
document.error = str(ex)