chore: update config and docker-compose to use volc_limit_sync handler
Updates config.yaml to use the new volc_limit_sync.proxy_handler_instance callback. Adds volc_limit_sync.py to docker-compose.yml volumes to ensure it is available in the container.
This commit is contained in:
+2
-1
@@ -287,7 +287,8 @@ litellm_settings:
|
|||||||
# supported_call_types: ["completion", "embedding", "acompletion"] # 支持的类型
|
# supported_call_types: ["completion", "embedding", "acompletion"] # 支持的类型
|
||||||
allowed_fails: 3 # cooldown model if it fails > 1 call in a minute.
|
allowed_fails: 3 # cooldown model if it fails > 1 call in a minute.
|
||||||
# 关键配置:注册自定义回调,实现单上游模型每日token限制的关键
|
# 关键配置:注册自定义回调,实现单上游模型每日token限制的关键
|
||||||
callbacks: ["daily_limit.proxy_handler_instance"]
|
#callbacks: ["daily_limit.proxy_handler_instance"]
|
||||||
|
callbacks: ["volc_limit_sync.proxy_handler_instance"]
|
||||||
|
|
||||||
router_settings: # router_settings are optional
|
router_settings: # router_settings are optional
|
||||||
routing_strategy: simple-shuffle # Literal["simple-shuffle", "least-busy", "usage-based-routing","latency-based-routing"], default="simple-shuffle"
|
routing_strategy: simple-shuffle # Literal["simple-shuffle", "least-busy", "usage-based-routing","latency-based-routing"], default="simple-shuffle"
|
||||||
|
|||||||
+2
-1
@@ -6,7 +6,8 @@ services:
|
|||||||
volumes:
|
volumes:
|
||||||
- ./config.yaml:/app/config.yaml
|
- ./config.yaml:/app/config.yaml
|
||||||
# 【关键】挂载自定义脚本到容器根目录
|
# 【关键】挂载自定义脚本到容器根目录
|
||||||
- ./daily_limit.py:/app/daily_limit.py
|
- ./daily_limit.py:/app/daily_limit.py
|
||||||
|
- ./volc_limit_sync.py:/app/volc_limit_sync.py
|
||||||
command:
|
command:
|
||||||
- "--config=/app/config.yaml"
|
- "--config=/app/config.yaml"
|
||||||
ports:
|
ports:
|
||||||
|
|||||||
Reference in New Issue
Block a user