youngkingdom/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-03-28 09:30:55 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'feat/queue-based-graph-engine' into feat/rag-2

Browse Source 
# Conflicts:
#	api/core/memory/token_buffer_memory.py
#	api/core/rag/extractor/notion_extractor.py
#	api/core/repositories/sqlalchemy_workflow_node_execution_repository.py
#	api/core/variables/variables.py
#	api/core/workflow/graph/graph.py
#	api/core/workflow/graph_engine/entities/event.py
#	api/services/dataset_service.py
#	web/app/components/app-sidebar/index.tsx
#	web/app/components/base/tag-management/selector.tsx
#	web/app/components/base/toast/index.tsx
#	web/app/components/datasets/create/website/index.tsx
#	web/app/components/datasets/create/website/jina-reader/base/options-wrap.tsx
#	web/app/components/workflow/header/version-history-button.tsx
#	web/app/components/workflow/hooks/use-inspect-vars-crud-common.ts
#	web/app/components/workflow/hooks/use-workflow-interactions.ts
#	web/app/components/workflow/panel/version-history-panel/index.tsx
#	web/service/base.ts
This commit is contained in:
jyong
2025-09-03 15:01:06 +08:00
parent c422d732d2 8c97937cae
commit d4aed3df5c
572 changed files with 16030 additions and 7973 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
api/controllers/console/datasets/datasets_document.py
View File

@ -41,6 +41,7 @@ from core.model_manager import ModelManager
from core.model_runtime.entities.model_entities import ModelType
from core.model_runtime.errors.invoke import InvokeAuthorizationError
from core.plugin.impl.exc import PluginDaemonClientSideError
from core.rag.extractor.entity.datasource_type import DatasourceType
from core.rag.extractor.entity.extract_setting import ExtractSetting
from extensions.ext_database import db
from fields.document_fields import (
@ -356,9 +357,6 @@ class DatasetInitApi(Resource):
parser.add_argument("embedding_model_provider", type=str, required=False, nullable=True, location="json")
args = parser.parse_args()
# The role of the current user in the ta table must be admin, owner, or editor, or dataset_operator
if not current_user.is_dataset_editor:
raise Forbidden()
knowledge_config = KnowledgeConfig(**args)
if knowledge_config.indexing_technique == "high_quality":
if knowledge_config.embedding_model is None or knowledge_config.embedding_model_provider is None:
@ -430,7 +428,7 @@ class DocumentIndexingEstimateApi(DocumentResource):
raise NotFound("File not found.")
extract_setting = ExtractSetting(
datasource_type="upload_file", upload_file=file, document_model=document.doc_form
datasource_type=DatasourceType.FILE.value, upload_file=file, document_model=document.doc_form
)
indexing_runner = IndexingRunner()
@ -490,13 +488,13 @@ class DocumentBatchIndexingEstimateApi(DocumentResource):
raise NotFound("File not found.")
extract_setting = ExtractSetting(
datasource_type="upload_file", upload_file=file_detail, document_model=document.doc_form
datasource_type=DatasourceType.FILE.value, upload_file=file_detail, document_model=document.doc_form
)
extract_settings.append(extract_setting)
elif document.data_source_type == "notion_import":
extract_setting = ExtractSetting(
datasource_type="notion_import",
datasource_type=DatasourceType.NOTION.value,
notion_info={
"credential_id": data_source_info["credential_id"],
"notion_workspace_id": data_source_info["notion_workspace_id"],
@ -509,7 +507,7 @@ class DocumentBatchIndexingEstimateApi(DocumentResource):
extract_settings.append(extract_setting)
elif document.data_source_type == "website_crawl":
extract_setting = ExtractSetting(
datasource_type="website_crawl",
datasource_type=DatasourceType.WEBSITE.value,
website_info={
"provider": data_source_info["provider"],
"job_id": data_source_info["job_id"],