docs: add llm token rate limit adapter usage

Author: dancing-ui

core/llm_token_ratelimit/README_en.md

@@ -178,6 +178,10 @@ sentinel:
       maxRetries: 3
 ```
 
+#### LLM Framework Adaptation
+Currently, it supports non-intrusive integration of Langchaingo and Eino frameworks into the Token rate limiting capability provided by Sentinel, which is mainly applicable to text generation scenarios. For usage details, refer to:
+- pkg/adapters/langchaingo/wrapper.go
+- pkg/adapters/eino/wrapper.go
 
 #### Notes
 

core/llm_token_ratelimit/README_zh.md

@@ -176,6 +176,12 @@ sentinel:
       minIdleConns: 5
       maxRetries: 3
 ```
+#### LLM框架适配
+
+目前支持Langchaingo和Eino框架无侵入式接入Sentinel提供的Token限流能力，主要适用于文本生成方面，使用方法详见
+
+- pkg/adapters/langchaingo/wrapper.go
+- pkg/adapters/eino/wrapper.go
 
 #### 注意事项