suguo
/
dify
mirror of https://github.com/langgenius/dify.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

perf: optimize dataset api query speed (#32847) 

Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
This commit is contained in:
wangxiaolei 2026-03-02 18:49:21 +08:00 committed by GitHub
parent c917838f9c
commit e985e73bdc
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 14 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
api/controllers/console/datasets/datasets.py
View File

@ -53,7 +53,7 @@ from fields.dataset_fields import (
from fields.document_fields import document_status_fields from fields.document_fields import document_status_fields
from libs.login import current_account_with_tenant, login_required from libs.login import current_account_with_tenant, login_required
from models import ApiToken, Dataset, Document, DocumentSegment, UploadFile from models import ApiToken, Dataset, Document, DocumentSegment, UploadFile
from models.dataset import DatasetPermissionEnum from models.dataset import DatasetPermission, DatasetPermissionEnum
from models.provider_ids import ModelProviderID from models.provider_ids import ModelProviderID
from services.api_token_service import ApiTokenCache from services.api_token_service import ApiTokenCache
from services.dataset_service import DatasetPermissionService, DatasetService, DocumentService from services.dataset_service import DatasetPermissionService, DatasetService, DocumentService
@ -323,6 +323,18 @@ class DatasetListApi(Resource):
model_names.append(f"{embedding_model.model}:{embedding_model.provider.provider}") model_names.append(f"{embedding_model.model}:{embedding_model.provider.provider}")
data = cast(list[dict[str, Any]], marshal(datasets, dataset_detail_fields)) data = cast(list[dict[str, Any]], marshal(datasets, dataset_detail_fields))
dataset_ids = [item["id"] for item in data if item.get("permission") == "partial_members"]
partial_members_map: dict[str, list[str]] = {}
if dataset_ids:
permissions = db.session.execute(
select(DatasetPermission.dataset_id, DatasetPermission.account_id).where(
DatasetPermission.dataset_id.in_(dataset_ids)
)
).all()
for dataset_id, account_id in permissions:
partial_members_map.setdefault(dataset_id, []).append(account_id)
for item in data: for item in data:
# convert embedding_model_provider to plugin standard format # convert embedding_model_provider to plugin standard format
if item["indexing_technique"] == "high_quality" and item["embedding_model_provider"]: if item["indexing_technique"] == "high_quality" and item["embedding_model_provider"]:
@ -336,8 +348,7 @@ class DatasetListApi(Resource):
item["embedding_available"] = True item["embedding_available"] = True
if item.get("permission") == "partial_members": if item.get("permission") == "partial_members":
part_users_list = DatasetPermissionService.get_dataset_partial_member_list(item["id"]) item.update({"partial_member_list": partial_members_map.get(item["id"], [])})
item.update({"partial_member_list": part_users_list})
else: else:
item.update({"partial_member_list": []}) item.update({"partial_member_list": []})