hz/ebiz-dify-ai
1
0
Fork 0
mirror of http://112.124.100.131/huang.ze/ebiz-dify-ai.git synced 2025-12-10 11:26:52 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: backend model load balancing support (#4927)

Browse Source
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
Download Patch File Download Diff File Expand all files Collapse all files

37
api/services/feature_service.py
View File

@@ -29,6 +29,7 @@ class FeatureModel(BaseModel):
documents_upload_quota: LimitationModel = LimitationModel(size=0, limit=50)
docs_processing: str = 'standard'
can_replace_logo: bool = False
model_load_balancing_enabled: bool = False
class SystemFeatureModel(BaseModel):
@@ -63,6 +64,7 @@ class FeatureService:
@classmethod
def _fulfill_params_from_env(cls, features: FeatureModel):
features.can_replace_logo = current_app.config['CAN_REPLACE_LOGO']
features.model_load_balancing_enabled = current_app.config['MODEL_LB_ENABLED']
@classmethod
def _fulfill_params_from_billing_api(cls, features: FeatureModel, tenant_id: str):
@@ -72,23 +74,34 @@ class FeatureService:
features.billing.subscription.plan = billing_info['subscription']['plan']
features.billing.subscription.interval = billing_info['subscription']['interval']
features.members.size = billing_info['members']['size']
features.members.limit = billing_info['members']['limit']
if 'members' in billing_info:
features.members.size = billing_info['members']['size']
features.members.limit = billing_info['members']['limit']
features.apps.size = billing_info['apps']['size']
features.apps.limit = billing_info['apps']['limit']
if 'apps' in billing_info:
features.apps.size = billing_info['apps']['size']
features.apps.limit = billing_info['apps']['limit']
features.vector_space.size = billing_info['vector_space']['size']
features.vector_space.limit = billing_info['vector_space']['limit']
if 'vector_space' in billing_info:
features.vector_space.size = billing_info['vector_space']['size']
features.vector_space.limit = billing_info['vector_space']['limit']
features.documents_upload_quota.size = billing_info['documents_upload_quota']['size']
features.documents_upload_quota.limit = billing_info['documents_upload_quota']['limit']
if 'documents_upload_quota' in billing_info:
features.documents_upload_quota.size = billing_info['documents_upload_quota']['size']
features.documents_upload_quota.limit = billing_info['documents_upload_quota']['limit']
features.annotation_quota_limit.size = billing_info['annotation_quota_limit']['size']
features.annotation_quota_limit.limit = billing_info['annotation_quota_limit']['limit']
if 'annotation_quota_limit' in billing_info:
features.annotation_quota_limit.size = billing_info['annotation_quota_limit']['size']
features.annotation_quota_limit.limit = billing_info['annotation_quota_limit']['limit']
features.docs_processing = billing_info['docs_processing']
features.can_replace_logo = billing_info['can_replace_logo']
if 'docs_processing' in billing_info:
features.docs_processing = billing_info['docs_processing']
if 'can_replace_logo' in billing_info:
features.can_replace_logo = billing_info['can_replace_logo']
if 'model_load_balancing_enabled' in billing_info:
features.model_load_balancing_enabled = billing_info['model_load_balancing_enabled']
@classmethod
def _fulfill_params_from_enterprise(cls, features):