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

fix: replace all dataset.Model.query to db.session.query(Model) (#19509)

Browse Source
This commit is contained in:
非法操作
2025-05-12 13:52:33 +08:00
committed by GitHub
parent 49af07f444
commit b00f94df64
21 changed files with 430 additions and 265 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
api/controllers/console/datasets/datasets.py
View File

@@ -526,14 +526,20 @@ class DatasetIndexingStatusApi(Resource):
)
documents_status = []
for document in documents:
completed_segments = DocumentSegment.query.filter(
DocumentSegment.completed_at.isnot(None),
DocumentSegment.document_id == str(document.id),
DocumentSegment.status != "re_segment",
).count()
total_segments = DocumentSegment.query.filter(
DocumentSegment.document_id == str(document.id), DocumentSegment.status != "re_segment"
).count()
completed_segments = (
db.session.query(DocumentSegment)
.filter(
DocumentSegment.completed_at.isnot(None),
DocumentSegment.document_id == str(document.id),
DocumentSegment.status != "re_segment",
)
.count()
)
total_segments = (
db.session.query(DocumentSegment)
.filter(DocumentSegment.document_id == str(document.id), DocumentSegment.status != "re_segment")
.count()
)
document.completed_segments = completed_segments
document.total_segments = total_segments
documents_status.append(marshal(document, document_status_fields))

74
api/controllers/console/datasets/datasets_document.py
View File

@@ -6,7 +6,7 @@ from typing import cast
from flask import request
from flask_login import current_user
from flask_restful import Resource, fields, marshal, marshal_with, reqparse
from sqlalchemy import asc, desc
from sqlalchemy import asc, desc, select
from werkzeug.exceptions import Forbidden, NotFound
import services
@@ -112,7 +112,7 @@ class GetProcessRuleApi(Resource):
limits = DocumentService.DEFAULT_RULES["limits"]
if document_id:
# get the latest process rule
document = Document.query.get_or_404(document_id)
document = db.get_or_404(Document, document_id)
dataset = DatasetService.get_dataset(document.dataset_id)
@@ -175,7 +175,7 @@ class DatasetDocumentListApi(Resource):
except services.errors.account.NoPermissionError as e:
raise Forbidden(str(e))
query = Document.query.filter_by(dataset_id=str(dataset_id), tenant_id=current_user.current_tenant_id)
query = select(Document).filter_by(dataset_id=str(dataset_id), tenant_id=current_user.current_tenant_id)
if search:
search = f"%{search}%"
@@ -209,18 +209,24 @@ class DatasetDocumentListApi(Resource):
desc(Document.position),
)
paginated_documents = query.paginate(page=page, per_page=limit, max_per_page=100, error_out=False)
paginated_documents = db.paginate(select=query, page=page, per_page=limit, max_per_page=100, error_out=False)
documents = paginated_documents.items
if fetch:
for document in documents:
completed_segments = DocumentSegment.query.filter(
DocumentSegment.completed_at.isnot(None),
DocumentSegment.document_id == str(document.id),
DocumentSegment.status != "re_segment",
).count()
total_segments = DocumentSegment.query.filter(
DocumentSegment.document_id == str(document.id), DocumentSegment.status != "re_segment"
).count()
completed_segments = (
db.session.query(DocumentSegment)
.filter(
DocumentSegment.completed_at.isnot(None),
DocumentSegment.document_id == str(document.id),
DocumentSegment.status != "re_segment",
)
.count()
)
total_segments = (
db.session.query(DocumentSegment)
.filter(DocumentSegment.document_id == str(document.id), DocumentSegment.status != "re_segment")
.count()
)
document.completed_segments = completed_segments
document.total_segments = total_segments
data = marshal(documents, document_with_segments_fields)
@@ -563,14 +569,20 @@ class DocumentBatchIndexingStatusApi(DocumentResource):
documents = self.get_batch_documents(dataset_id, batch)
documents_status = []
for document in documents:
completed_segments = DocumentSegment.query.filter(
DocumentSegment.completed_at.isnot(None),
DocumentSegment.document_id == str(document.id),
DocumentSegment.status != "re_segment",
).count()
total_segments = DocumentSegment.query.filter(
DocumentSegment.document_id == str(document.id), DocumentSegment.status != "re_segment"
).count()
completed_segments = (
db.session.query(DocumentSegment)
.filter(
DocumentSegment.completed_at.isnot(None),
DocumentSegment.document_id == str(document.id),
DocumentSegment.status != "re_segment",
)
.count()
)
total_segments = (
db.session.query(DocumentSegment)
.filter(DocumentSegment.document_id == str(document.id), DocumentSegment.status != "re_segment")
.count()
)
document.completed_segments = completed_segments
document.total_segments = total_segments
if document.is_paused:
@@ -589,14 +601,20 @@ class DocumentIndexingStatusApi(DocumentResource):
document_id = str(document_id)
document = self.get_document(dataset_id, document_id)
completed_segments = DocumentSegment.query.filter(
DocumentSegment.completed_at.isnot(None),
DocumentSegment.document_id == str(document_id),
DocumentSegment.status != "re_segment",
).count()
total_segments = DocumentSegment.query.filter(
DocumentSegment.document_id == str(document_id), DocumentSegment.status != "re_segment"
).count()
completed_segments = (
db.session.query(DocumentSegment)
.filter(
DocumentSegment.completed_at.isnot(None),
DocumentSegment.document_id == str(document_id),
DocumentSegment.status != "re_segment",
)
.count()
)
total_segments = (
db.session.query(DocumentSegment)
.filter(DocumentSegment.document_id == str(document_id), DocumentSegment.status != "re_segment")
.count()
)
document.completed_segments = completed_segments
document.total_segments = total_segments

87
api/controllers/console/datasets/datasets_segments.py
View File

@@ -4,6 +4,7 @@ import pandas as pd
from flask import request
from flask_login import current_user
from flask_restful import Resource, marshal, reqparse
from sqlalchemy import select
from werkzeug.exceptions import Forbidden, NotFound
import services
@@ -26,6 +27,7 @@ from controllers.console.wraps import (
from core.errors.error import LLMBadRequestError, ProviderTokenNotInitError
from core.model_manager import ModelManager
from core.model_runtime.entities.model_entities import ModelType
from extensions.ext_database import db
from extensions.ext_redis import redis_client
from fields.segment_fields import child_chunk_fields, segment_fields
from libs.login import login_required
@@ -74,9 +76,14 @@ class DatasetDocumentSegmentListApi(Resource):
hit_count_gte = args["hit_count_gte"]
keyword = args["keyword"]
query = DocumentSegment.query.filter(
DocumentSegment.document_id == str(document_id), DocumentSegment.tenant_id == current_user.current_tenant_id
).order_by(DocumentSegment.position.asc())
query = (
select(DocumentSegment)
.filter(
DocumentSegment.document_id == str(document_id),
DocumentSegment.tenant_id == current_user.current_tenant_id,
)
.order_by(DocumentSegment.position.asc())
)
if status_list:
query = query.filter(DocumentSegment.status.in_(status_list))
@@ -93,7 +100,7 @@ class DatasetDocumentSegmentListApi(Resource):
elif args["enabled"].lower() == "false":
query = query.filter(DocumentSegment.enabled == False)
segments = query.paginate(page=page, per_page=limit, max_per_page=100, error_out=False)
segments = db.paginate(select=query, page=page, per_page=limit, max_per_page=100, error_out=False)
response = {
"data": marshal(segments.items, segment_fields),
@@ -276,9 +283,11 @@ class DatasetDocumentSegmentUpdateApi(Resource):
raise ProviderNotInitializeError(ex.description)
# check segment
segment_id = str(segment_id)
segment = DocumentSegment.query.filter(
DocumentSegment.id == str(segment_id), DocumentSegment.tenant_id == current_user.current_tenant_id
).first()
segment = (
db.session.query(DocumentSegment)
.filter(DocumentSegment.id == str(segment_id), DocumentSegment.tenant_id == current_user.current_tenant_id)
.first()
)
if not segment:
raise NotFound("Segment not found.")
# The role of the current user in the ta table must be admin, owner, dataset_operator, or editor
@@ -320,9 +329,11 @@ class DatasetDocumentSegmentUpdateApi(Resource):
raise NotFound("Document not found.")
# check segment
segment_id = str(segment_id)
segment = DocumentSegment.query.filter(
DocumentSegment.id == str(segment_id), DocumentSegment.tenant_id == current_user.current_tenant_id
).first()
segment = (
db.session.query(DocumentSegment)
.filter(DocumentSegment.id == str(segment_id), DocumentSegment.tenant_id == current_user.current_tenant_id)
.first()
)
if not segment:
raise NotFound("Segment not found.")
# The role of the current user in the ta table must be admin, owner, dataset_operator, or editor
@@ -423,9 +434,11 @@ class ChildChunkAddApi(Resource):
raise NotFound("Document not found.")
# check segment
segment_id = str(segment_id)
segment = DocumentSegment.query.filter(
DocumentSegment.id == str(segment_id), DocumentSegment.tenant_id == current_user.current_tenant_id
).first()
segment = (
db.session.query(DocumentSegment)
.filter(DocumentSegment.id == str(segment_id), DocumentSegment.tenant_id == current_user.current_tenant_id)
.first()
)
if not segment:
raise NotFound("Segment not found.")
if not current_user.is_dataset_editor:
@@ -478,9 +491,11 @@ class ChildChunkAddApi(Resource):
raise NotFound("Document not found.")
# check segment
segment_id = str(segment_id)
segment = DocumentSegment.query.filter(
DocumentSegment.id == str(segment_id), DocumentSegment.tenant_id == current_user.current_tenant_id
).first()
segment = (
db.session.query(DocumentSegment)
.filter(DocumentSegment.id == str(segment_id), DocumentSegment.tenant_id == current_user.current_tenant_id)
.first()
)
if not segment:
raise NotFound("Segment not found.")
parser = reqparse.RequestParser()
@@ -523,9 +538,11 @@ class ChildChunkAddApi(Resource):
raise NotFound("Document not found.")
# check segment
segment_id = str(segment_id)
segment = DocumentSegment.query.filter(
DocumentSegment.id == str(segment_id), DocumentSegment.tenant_id == current_user.current_tenant_id
).first()
segment = (
db.session.query(DocumentSegment)
.filter(DocumentSegment.id == str(segment_id), DocumentSegment.tenant_id == current_user.current_tenant_id)
.first()
)
if not segment:
raise NotFound("Segment not found.")
# The role of the current user in the ta table must be admin, owner, dataset_operator, or editor
@@ -567,16 +584,20 @@ class ChildChunkUpdateApi(Resource):
raise NotFound("Document not found.")
# check segment
segment_id = str(segment_id)
segment = DocumentSegment.query.filter(
DocumentSegment.id == str(segment_id), DocumentSegment.tenant_id == current_user.current_tenant_id
).first()
segment = (
db.session.query(DocumentSegment)
.filter(DocumentSegment.id == str(segment_id), DocumentSegment.tenant_id == current_user.current_tenant_id)
.first()
)
if not segment:
raise NotFound("Segment not found.")
# check child chunk
child_chunk_id = str(child_chunk_id)
child_chunk = ChildChunk.query.filter(
ChildChunk.id == str(child_chunk_id), ChildChunk.tenant_id == current_user.current_tenant_id
).first()
child_chunk = (
db.session.query(ChildChunk)
.filter(ChildChunk.id == str(child_chunk_id), ChildChunk.tenant_id == current_user.current_tenant_id)
.first()
)
if not child_chunk:
raise NotFound("Child chunk not found.")
# The role of the current user in the ta table must be admin, owner, dataset_operator, or editor
@@ -612,16 +633,20 @@ class ChildChunkUpdateApi(Resource):
raise NotFound("Document not found.")
# check segment
segment_id = str(segment_id)
segment = DocumentSegment.query.filter(
DocumentSegment.id == str(segment_id), DocumentSegment.tenant_id == current_user.current_tenant_id
).first()
segment = (
db.session.query(DocumentSegment)
.filter(DocumentSegment.id == str(segment_id), DocumentSegment.tenant_id == current_user.current_tenant_id)
.first()
)
if not segment:
raise NotFound("Segment not found.")
# check child chunk
child_chunk_id = str(child_chunk_id)
child_chunk = ChildChunk.query.filter(
ChildChunk.id == str(child_chunk_id), ChildChunk.tenant_id == current_user.current_tenant_id
).first()
child_chunk = (
db.session.query(ChildChunk)
.filter(ChildChunk.id == str(child_chunk_id), ChildChunk.tenant_id == current_user.current_tenant_id)
.first()
)
if not child_chunk:
raise NotFound("Child chunk not found.")
# The role of the current user in the ta table must be admin, owner, dataset_operator, or editor

30
api/controllers/service_api/dataset/document.py
View File

@@ -2,10 +2,10 @@ import json
from flask import request
from flask_restful import marshal, reqparse
from sqlalchemy import desc
from sqlalchemy import desc, select
from werkzeug.exceptions import NotFound
import services.dataset_service
import services
from controllers.common.errors import FilenameNotExistsError
from controllers.service_api import api
from controllers.service_api.app.error import (
@@ -337,7 +337,7 @@ class DocumentListApi(DatasetApiResource):
if not dataset:
raise NotFound("Dataset not found.")
query = Document.query.filter_by(dataset_id=str(dataset_id), tenant_id=tenant_id)
query = select(Document).filter_by(dataset_id=str(dataset_id), tenant_id=tenant_id)
if search:
search = f"%{search}%"
@@ -345,7 +345,7 @@ class DocumentListApi(DatasetApiResource):
query = query.order_by(desc(Document.created_at), desc(Document.position))
paginated_documents = query.paginate(page=page, per_page=limit, max_per_page=100, error_out=False)
paginated_documents = db.paginate(select=query, page=page, per_page=limit, max_per_page=100, error_out=False)
documents = paginated_documents.items
response = {
@@ -374,14 +374,20 @@ class DocumentIndexingStatusApi(DatasetApiResource):
raise NotFound("Documents not found.")
documents_status = []
for document in documents:
completed_segments = DocumentSegment.query.filter(
DocumentSegment.completed_at.isnot(None),
DocumentSegment.document_id == str(document.id),
DocumentSegment.status != "re_segment",
).count()
total_segments = DocumentSegment.query.filter(
DocumentSegment.document_id == str(document.id), DocumentSegment.status != "re_segment"
).count()
completed_segments = (
db.session.query(DocumentSegment)
.filter(
DocumentSegment.completed_at.isnot(None),
DocumentSegment.document_id == str(document.id),
DocumentSegment.status != "re_segment",
)
.count()
)
total_segments = (
db.session.query(DocumentSegment)
.filter(DocumentSegment.document_id == str(document.id), DocumentSegment.status != "re_segment")
.count()
)
document.completed_segments = completed_segments
document.total_segments = total_segments
if document.is_paused: