feat: extract model runtime

Signed-off-by: -LAN- <laipz8200@outlook.com>

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
@@ -331,7 +331,7 @@ 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)
@@ -445,7 +445,7 @@ 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

@@ -452,7 +452,7 @@ 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

@@ -282,7 +282,7 @@ class DatasetDocumentSegmentApi(Resource):
         if dataset.indexing_technique == "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,
@@ -335,7 +335,7 @@ class DatasetDocumentSegmentAddApi(Resource):
         # check embedding model setting
         if dataset.indexing_technique == "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,
@@ -386,7 +386,7 @@ class DatasetDocumentSegmentUpdateApi(Resource):
         if dataset.indexing_technique == "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,
@@ -571,7 +571,7 @@ class ChildChunkAddApi(Resource):
         # check embedding model setting
         if dataset.indexing_technique == "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/workspace/models.py

@@ -282,14 +282,18 @@ class ModelProviderModelCredentialApi(Resource):
         )
 
         if args.config_from == "predefined-model":
-            available_credentials = model_provider_service.provider_manager.get_provider_available_credentials(
-                tenant_id=tenant_id, provider_name=provider
+            available_credentials = model_provider_service.get_provider_available_credentials(
+                tenant_id=tenant_id,
+                provider=provider,
             )
         else:
             # Normalize model_type to the origin value stored in DB (e.g., "text-generation" for LLM)
             normalized_model_type = args.model_type.to_origin_model_type()
-            available_credentials = model_provider_service.provider_manager.get_provider_model_available_credentials(
-                tenant_id=tenant_id, provider_name=provider, model_type=normalized_model_type, model_name=args.model
+            available_credentials = model_provider_service.get_provider_model_available_credentials(
+                tenant_id=tenant_id,
+                provider=provider,
+                model_type=normalized_model_type,
+                model=args.model,
             )
 
         return jsonable_encoder(

api/controllers/service_api/dataset/dataset.py

@@ -14,7 +14,7 @@ from controllers.service_api.wraps import (
     DatasetApiResource,
     cloud_edition_billing_rate_limit_check,
 )
-from core.provider_manager import ProviderManager
+from core.plugin.impl.model_runtime_factory import create_plugin_provider_manager
 from dify_graph.model_runtime.entities.model_entities import ModelType
 from fields.dataset_fields import dataset_detail_fields
 from fields.tag_fields import DataSetTag
@@ -139,10 +139,10 @@ class DatasetListApi(DatasetApiResource):
             query.page, query.limit, tenant_id, current_user, query.keyword, query.tag_ids, query.include_all
         )
         # check embedding setting
-        provider_manager = ProviderManager()
         assert isinstance(current_user, Account)
         cid = current_user.current_tenant_id
         assert cid is not None
+        provider_manager = create_plugin_provider_manager(tenant_id=cid)
         configurations = provider_manager.get_configurations(tenant_id=cid)
 
         embedding_models = configurations.get_models(model_type=ModelType.TEXT_EMBEDDING, only_active=True)
@@ -253,10 +253,10 @@ class DatasetApi(DatasetApiResource):
             raise Forbidden(str(e))
         data = cast(dict[str, Any], marshal(dataset, dataset_detail_fields))
         # check embedding setting
-        provider_manager = ProviderManager()
         assert isinstance(current_user, Account)
         cid = current_user.current_tenant_id
         assert cid is not None
+        provider_manager = create_plugin_provider_manager(tenant_id=cid)
         configurations = provider_manager.get_configurations(tenant_id=cid)
 
         embedding_models = configurations.get_models(model_type=ModelType.TEXT_EMBEDDING, only_active=True)

api/controllers/service_api/dataset/segment.py

@@ -105,7 +105,7 @@ class SegmentApi(DatasetApiResource):
         # check embedding model setting
         if dataset.indexing_technique == "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,
@@ -159,7 +159,7 @@ class SegmentApi(DatasetApiResource):
         # check embedding model setting
         if dataset.indexing_technique == "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,
@@ -265,7 +265,7 @@ class DatasetSegmentApi(DatasetApiResource):
         if dataset.indexing_technique == "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,
@@ -360,7 +360,7 @@ class ChildChunkApi(DatasetApiResource):
         # check embedding model setting
         if dataset.indexing_technique == "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,