youngkingdom/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-04-21 03:07:39 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'main' into feat/r2

Browse Source
This commit is contained in:
jyong
2025-05-15 15:15:23 +08:00
parent 818eb46a8b 6d7f43b901
commit 360f8a3375
1025 changed files with 17699 additions and 4959 deletions
Download Patch File Download Diff File Expand all files Collapse all files

37
api/core/callback_handler/index_tool_callback_handler.py
View File

@ -1,3 +1,5 @@
import logging
from core.app.apps.base_app_queue_manager import AppQueueManager, PublishFrom
from core.app.entities.app_invoke_entities import InvokeFrom
from core.app.entities.queue_entities import QueueRetrieverResourcesEvent
@ -7,6 +9,8 @@ from extensions.ext_database import db
from models.dataset import ChildChunk, DatasetQuery, DocumentSegment
from models.dataset import Document as DatasetDocument
_logger = logging.getLogger(__name__)
class DatasetIndexToolCallbackHandler:
"""Callback handler for dataset tool."""
@ -42,18 +46,31 @@ class DatasetIndexToolCallbackHandler:
"""Handle tool end."""
for document in documents:
if document.metadata is not None:
dataset_document = DatasetDocument.query.filter(
DatasetDocument.id == document.metadata["document_id"]
).first()
document_id = document.metadata["document_id"]
dataset_document = db.session.query(DatasetDocument).filter(DatasetDocument.id == document_id).first()
if not dataset_document:
_logger.warning(
"Expected DatasetDocument record to exist, but none was found, document_id=%s",
document_id,
)
continue
if dataset_document.doc_form == IndexType.PARENT_CHILD_INDEX:
child_chunk = ChildChunk.query.filter(
ChildChunk.index_node_id == document.metadata["doc_id"],
ChildChunk.dataset_id == dataset_document.dataset_id,
ChildChunk.document_id == dataset_document.id,
).first()
child_chunk = (
db.session.query(ChildChunk)
.filter(
ChildChunk.index_node_id == document.metadata["doc_id"],
ChildChunk.dataset_id == dataset_document.dataset_id,
ChildChunk.document_id == dataset_document.id,
)
.first()
)
if child_chunk:
segment = DocumentSegment.query.filter(DocumentSegment.id == child_chunk.segment_id).update(
{DocumentSegment.hit_count: DocumentSegment.hit_count + 1}, synchronize_session=False
segment = (
db.session.query(DocumentSegment)
.filter(DocumentSegment.id == child_chunk.segment_id)
.update(
{DocumentSegment.hit_count: DocumentSegment.hit_count + 1}, synchronize_session=False
)
)
else:
query = db.session.query(DocumentSegment).filter(