feat: backend model load balancing support (#4927)

This commit is contained in:
takatost
2024-06-05 00:13:04 +08:00
committed by GitHub
parent 52ec152dd3
commit d1dbbc1e33
47 changed files with 2191 additions and 256 deletions

View File

@@ -16,6 +16,7 @@ class ModelStatus(Enum):
NO_CONFIGURE = "no-configure"
QUOTA_EXCEEDED = "quota-exceeded"
NO_PERMISSION = "no-permission"
DISABLED = "disabled"
class SimpleModelProviderEntity(BaseModel):
@@ -43,12 +44,19 @@ class SimpleModelProviderEntity(BaseModel):
)
class ModelWithProviderEntity(ProviderModel):
class ProviderModelWithStatusEntity(ProviderModel):
"""
Model class for model response.
"""
status: ModelStatus
load_balancing_enabled: bool = False
class ModelWithProviderEntity(ProviderModelWithStatusEntity):
"""
Model with provider entity.
"""
provider: SimpleModelProviderEntity
status: ModelStatus
class DefaultModelProviderEntity(BaseModel):