doc: add ai-token-ratelimit example (#245)

higress-group · Jul 2, 2024 · 6beabbd · 6beabbd
1 parent 46cbc5a
commit 6beabbd
Show file tree

Hide file tree

Showing 2 changed files with 209 additions and 3 deletions.
diff --git a/i18n/zh-cn/docusaurus-plugin-content-docs/current/plugins/ai/ai-token-ratelimit.md b/i18n/zh-cn/docusaurus-plugin-content-docs/current/plugins/ai/ai-token-ratelimit.md
@@ -182,3 +182,208 @@ rejected_msg: '{"code":-1,"msg":"Too many requests"}'
 redis:
  service_name: redis.static
 ```
+
+## 完整示例
+
+AI Token 限流插件依赖 Redis 记录剩余可用的 token 数，因此首先需要部署 Redis 服务。
+
+```yaml
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+ name: redis
+ labels:
+ app: redis
+spec:
+ replicas: 1
+ selector:
+ matchLabels:
+ app: redis
+ template:
+ metadata:
+ labels:
+ app: redis
+ spec:
+ containers:
+ - name: redis
+ image: redis
+ ports:
+ - containerPort: 6379
+---
+apiVersion: v1
+kind: Service
+metadata:
+ name: redis
+ labels:
+ app: redis
+spec:
+ ports:
+ - port: 6379
+ targetPort: 6379
+ selector:
+ app: redis
+---
+```
+
+在本例中，使用通义千问作为 AI 服务提供商。另外还需要设置 AI 统计插件，因为 AI Token 限流插件依赖 AI 统计插件计算每次请求消耗的 token 数，以下配置限制每分钟的 input 和 output token 总数为 200 个。
+
+```yaml
+apiVersion: extensions.higress.io/v1alpha1
+kind: WasmPlugin
+metadata:
+ name: ai-proxy
+ namespace: higress-system
+spec:
+ matchRules:
+ - config:
+ provider:
+ type: qwen
+ apiTokens:
+ - "<YOUR_API_TOKEN>"
+ modelMapping:
+ 'gpt-3': "qwen-turbo"
+ 'gpt-35-turbo': "qwen-plus"
+ 'gpt-4-turbo': "qwen-max"
+ '*': "qwen-turbo"
+ ingress:
+ - qwen
+ url: oci://higress-registry.cn-hangzhou.cr.aliyuncs.com/plugins/wasm-go-ai-proxy:v1.0.0
+ phase: UNSPECIFIED_PHASE
+ priority: 100
+---
+apiVersion: extensions.higress.io/v1alpha1
+kind: WasmPlugin
+metadata:
+ name: ai-statistics
+ namespace: higress-system
+spec:
+ defaultConfig:
+ enable: true
+ url: oci://higress-registry.cn-hangzhou.cr.aliyuncs.com/plugins/wasm-go-ai-token-statistics:v1.0.0
+ phase: UNSPECIFIED_PHASE
+ priority: 200
+---
+apiVersion: extensions.higress.io/v1alpha1
+kind: WasmPlugin
+metadata:
+ name: ai-token-ratelimit
+ namespace: higress-system
+spec:
+ defaultConfig:
+ rule_name: default_limit_by_param_apikey
+ rule_items:
+ - limit_by_param: apikey
+ limit_keys:
+ - key: 123456
+ token_per_minute: 200
+ redis:
+ # 默认情况下，为了减轻数据面的压力，Higress 的 global.onlyPushRouteCluster 配置参数被设置为 true，意味着不会自动发现 Kubernetes Service
+ # 如果需要使用 Kubernetes Service 作为服务发现，可以将 global.onlyPushRouteCluster 参数设置为 false，
+ # 这样就可以直接将 service_name 设置为 Kubernetes Service, 而无须为 Redis 创建 McpBridge 以及 Ingress 路由
+ # service_name: redis.default.svc.cluster.local
+ service_name: redis.dns
+ service_port: 6379
+ url: oci://higress-registry.cn-hangzhou.cr.aliyuncs.com/plugins/wasm-go-ai-token-ratelimit:v1.0.0
+ phase: UNSPECIFIED_PHASE
+ priority: 600
+```
+
+注意，AI Token 限流插件中的 Redis 配置项 `service_name` 来自 McpBridge 中配置的服务来源，另外我们还需要在 McpBridge 中配置通义千问服务的访问地址。
+
+```yaml
+apiVersion: networking.higress.io/v1
+kind: McpBridge
+metadata:
+ name: default
+ namespace: higress-system
+spec:
+ registries:
+ - domain: dashscope.aliyuncs.com
+ name: qwen
+ port: 443
+ type: dns
+ - domain: redis.default.svc.cluster.local # Kubernetes Service
+ name: redis
+ type: dns
+ port: 6379
+```
+
+分别创建两条路由规则。
+
+```yaml
+apiVersion: networking.k8s.io/v1
+kind: Ingress
+metadata:
+ annotations:
+ higress.io/backend-protocol: HTTPS
+ higress.io/destination: qwen.dns
+ higress.io/proxy-ssl-name: dashscope.aliyuncs.com
+ higress.io/proxy-ssl-server-name: "on"
+ labels:
+ higress.io/resource-definer: higress
+ name: qwen
+ namespace: higress-system
+spec:
+ ingressClassName: higress
+ rules:
+ - host: qwen-test.com
+ http:
+ paths:
+ - backend:
+ resource:
+ apiGroup: networking.higress.io
+ kind: McpBridge
+ name: default
+ path: /
+ pathType: Prefix
+---
+apiVersion: networking.k8s.io/v1
+kind: Ingress
+metadata:
+ annotations:
+ higress.io/destination: redis.dns
+ higress.io/ignore-path-case: "false"
+ labels:
+ higress.io/resource-definer: higress
+ name: redis
+spec:
+ ingressClassName: higress
+ rules:
+ - http:
+ paths:
+ - backend:
+ resource:
+ apiGroup: networking.higress.io
+ kind: McpBridge
+ name: default
+ path: /
+ pathType: Prefix
+```
+
+触发限流效果如下：
+
+```bash
+curl "http://qwen-test.com:18000/v1/chat/completions?apikey=123456" -H "Content-Type: application/json" -d '{
+ "model": "gpt-3",
+ "messages": [
+ {
+ "role": "user",
+ "content": "你好，你是谁？"
+ }
+ ],
+ "stream": false
+}'
+{"id":"88cfa80f-545d-93b4-8ff3-3f5245ca33ba","choices":[{"index":0,"message":{"role":"assistant","content":"我是通义千问，由阿里云开发的AI助手。我可以回答各种问题、提供信息和与用户进行对话。有什么我可以帮助你的吗？"},"finish_reason":"stop"}],"created":1719909825,"model":"qwen-turbo","object":"chat.completion","usage":{"prompt_tokens":13,"completion_tokens":33,"total_tokens":46}}
+
+curl "http://qwen-test.com:18000/v1/chat/completions?apikey=123456" -H "Content-Type: application/json" -d '{
+ "model": "gpt-3",
+ "messages": [
+ {
+ "role": "user",
+ "content": "你好，你是谁？"
+ }
+ ],
+ "stream": false
+}'
+Too many requests # 限流成功
+```
diff --git a/i18n/zh-cn/docusaurus-plugin-content-docs/current/user/mcp-bridge.md b/i18n/zh-cn/docusaurus-plugin-content-docs/current/user/mcp-bridge.md
@@ -8,9 +8,10 @@ custom_edit_url: https://github.com/higress-group/higress-group.github.io/blob/m
 # Mcp Bridge 配置说明
 
 ## McpBridge 字段说明
-| 字段 | 类型 | 说明 | 示例值 | 是否必填 |
-| --- | --- | --- | --- | --- |
-| registries | RegistryConfig 数组 | 支持配置多个不同注册中心的服务来源 | [] | 否 |
+| 字段 | 类型 | 说明 | 示例值 | 是否必填 |
+|------------| --- |-------------------|---------|-------------------|
+| registries | RegistryConfig 数组 | 支持配置多个不同注册中心的服务来源 | [] | 否 |
+| name | 字符串 | McpBridge 名称 | default | 是，当前该值只能是 default |
 
 ## RegistryConfig 字段说明
 | 字段 | 类型 | 说明 | 示例值 | 是否必填 |