refactor(api): continue decoupling dify_graph from API concerns (#33580)

Signed-off-by: -LAN- <laipz8200@outlook.com>
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Co-authored-by: WH-2099 <wh2099@pm.me>

api/controllers/console/datasets/datasets.py

@@ -25,7 +25,7 @@ from controllers.console.wraps import (
 )
 from core.errors.error import LLMBadRequestError, ProviderTokenNotInitError
 from core.indexing_runner import IndexingRunner
-from core.provider_manager import ProviderManager
+from core.plugin.impl.model_runtime_factory import create_plugin_provider_manager
 from core.rag.datasource.vdb.vector_type import VectorType
 from core.rag.extractor.entity.datasource_type import DatasourceType
 from core.rag.extractor.entity.extract_setting import ExtractSetting, NotionInfo, WebsiteInfo
@@ -332,7 +332,7 @@ class DatasetListApi(Resource):
             )
 
         # check embedding setting
-        provider_manager = ProviderManager()
+        provider_manager = create_plugin_provider_manager(tenant_id=current_tenant_id)
         configurations = provider_manager.get_configurations(tenant_id=current_tenant_id)
 
         embedding_models = configurations.get_models(model_type=ModelType.TEXT_EMBEDDING, only_active=True)
@@ -446,7 +446,7 @@ class DatasetApi(Resource):
             data.update({"partial_member_list": part_users_list})
 
         # check embedding setting
-        provider_manager = ProviderManager()
+        provider_manager = create_plugin_provider_manager(tenant_id=current_tenant_id)
         configurations = provider_manager.get_configurations(tenant_id=current_tenant_id)
 
         embedding_models = configurations.get_models(model_type=ModelType.TEXT_EMBEDDING, only_active=True)

api/controllers/console/datasets/datasets_document.py

@@ -454,7 +454,7 @@ class DatasetInitApi(Resource):
             if knowledge_config.embedding_model is None or knowledge_config.embedding_model_provider is None:
                 raise ValueError("embedding model and embedding model provider are required for high quality indexing.")
             try:
-                model_manager = ModelManager()
+                model_manager = ModelManager.for_tenant(tenant_id=current_tenant_id)
                 model_manager.get_model_instance(
                     tenant_id=current_tenant_id,
                     provider=knowledge_config.embedding_model_provider,

api/controllers/console/datasets/datasets_segments.py

@@ -283,7 +283,7 @@ class DatasetDocumentSegmentApi(Resource):
         if dataset.indexing_technique == IndexTechniqueType.HIGH_QUALITY:
             # check embedding model setting
             try:
-                model_manager = ModelManager()
+                model_manager = ModelManager.for_tenant(tenant_id=current_tenant_id)
                 model_manager.get_model_instance(
                     tenant_id=current_tenant_id,
                     provider=dataset.embedding_model_provider,
@@ -336,7 +336,7 @@ class DatasetDocumentSegmentAddApi(Resource):
         # check embedding model setting
         if dataset.indexing_technique == IndexTechniqueType.HIGH_QUALITY:
             try:
-                model_manager = ModelManager()
+                model_manager = ModelManager.for_tenant(tenant_id=current_tenant_id)
                 model_manager.get_model_instance(
                     tenant_id=current_tenant_id,
                     provider=dataset.embedding_model_provider,
@@ -387,7 +387,7 @@ class DatasetDocumentSegmentUpdateApi(Resource):
         if dataset.indexing_technique == IndexTechniqueType.HIGH_QUALITY:
             # check embedding model setting
             try:
-                model_manager = ModelManager()
+                model_manager = ModelManager.for_tenant(tenant_id=current_tenant_id)
                 model_manager.get_model_instance(
                     tenant_id=current_tenant_id,
                     provider=dataset.embedding_model_provider,
@@ -572,7 +572,7 @@ class ChildChunkAddApi(Resource):
         # check embedding model setting
         if dataset.indexing_technique == IndexTechniqueType.HIGH_QUALITY:
             try:
-                model_manager = ModelManager()
+                model_manager = ModelManager.for_tenant(tenant_id=current_tenant_id)
                 model_manager.get_model_instance(
                     tenant_id=current_tenant_id,
                     provider=dataset.embedding_model_provider,

api/controllers/console/datasets/rag_pipeline/rag_pipeline_draft_variable.py

@@ -21,7 +21,8 @@ from controllers.console.app.workflow_draft_variable import (
 from controllers.console.datasets.wraps import get_rag_pipeline
 from controllers.console.wraps import account_initialization_required, setup_required
 from controllers.web.error import InvalidArgumentError, NotFoundError
-from dify_graph.constants import CONVERSATION_VARIABLE_NODE_ID, SYSTEM_VARIABLE_NODE_ID
+from core.app.file_access import DatabaseFileAccessController
+from core.workflow.variable_prefixes import CONVERSATION_VARIABLE_NODE_ID, SYSTEM_VARIABLE_NODE_ID
 from dify_graph.variables.types import SegmentType
 from extensions.ext_database import db
 from factories.file_factory import build_from_mapping, build_from_mappings
@@ -33,6 +34,7 @@ from services.rag_pipeline.rag_pipeline import RagPipelineService
 from services.workflow_draft_variable_service import WorkflowDraftVariableList, WorkflowDraftVariableService
 
 logger = logging.getLogger(__name__)
+_file_access_controller = DatabaseFileAccessController()
 
 
 def _create_pagination_parser():
@@ -223,13 +225,21 @@ class RagPipelineVariableApi(Resource):
             if variable.value_type == SegmentType.FILE:
                 if not isinstance(raw_value, dict):
                     raise InvalidArgumentError(description=f"expected dict for file, got {type(raw_value)}")
-                raw_value = build_from_mapping(mapping=raw_value, tenant_id=pipeline.tenant_id)
+                raw_value = build_from_mapping(
+                    mapping=raw_value,
+                    tenant_id=pipeline.tenant_id,
+                    access_controller=_file_access_controller,
+                )
             elif variable.value_type == SegmentType.ARRAY_FILE:
                 if not isinstance(raw_value, list):
                     raise InvalidArgumentError(description=f"expected list for files, got {type(raw_value)}")
                 if len(raw_value) > 0 and not isinstance(raw_value[0], dict):
                     raise InvalidArgumentError(description=f"expected dict for files[0], got {type(raw_value)}")
-                raw_value = build_from_mappings(mappings=raw_value, tenant_id=pipeline.tenant_id)
+                raw_value = build_from_mappings(
+                    mappings=raw_value,
+                    tenant_id=pipeline.tenant_id,
+                    access_controller=_file_access_controller,
+                )
             new_value = build_segment_with_type(variable.value_type, raw_value)
         draft_var_srv.update_variable(variable, name=new_name, value=new_value)
         db.session.commit()