feat(docs): add structured output example and details

README.md

@@ -12,6 +12,7 @@ A professional, type-safe TypeScript package that provides a unified interface f
 - 🔧 **Configurable**: Extensive configuration options for each provider
 - 📦 **Zero Dependencies**: Lightweight with minimal external dependencies
 - 🌐 **Local Support**: OpenWebUI integration for local/private AI models
+- 🎨 **Structured Output**: Define custom response types for type-safe AI outputs
 
 ## 🚀 Quick Start
 
@@ -83,6 +84,69 @@ const openwebui = createOpenWebUIProvider({ apiKey: 'your-key', baseUrl: 'http:/
 const provider = createProvider('claude', { apiKey: 'your-key' });
 ```
 
+## 🎨 Structured Response Types
+
+Define custom response types for type-safe, structured AI outputs:
+
+```typescript
+import { createResponseType, validateResponseType } from 'simple-ai-provider';
+
+// Define your response type
+interface UserProfile {
+  name: string;
+  age: number;
+  email: string;
+  preferences: {
+    theme: 'light' | 'dark';
+    notifications: boolean;
+  };
+}
+
+const userProfileType = createResponseType<UserProfile>(
+  `{
+    name: string;
+    age: number;
+    email: string;
+    preferences: {
+      theme: 'light' | 'dark';
+      notifications: boolean;
+    };
+  }`,
+  'A user profile with personal information and preferences',
+  {
+    name: 'John Doe',
+    age: 30,
+    email: 'john@example.com',
+    preferences: { theme: 'dark', notifications: true }
+  }
+);
+
+// Use with any provider
+const response = await claude.complete({
+  messages: [
+    { role: 'user', content: 'Generate a user profile for a software developer' }
+  ],
+  responseType: userProfileType,
+  maxTokens: 500
+});
+
+// Validate and get typed response
+const validation = validateResponseType(response.content, userProfileType);
+if (validation.isValid) {
+  const userProfile = validation.data as UserProfile;
+  console.log(`Name: ${userProfile.name}`);
+  console.log(`Theme: ${userProfile.preferences.theme}`);
+}
+```
+
+### Key Benefits
+
+- **Type Safety**: Get fully typed responses from AI providers
+- **Automatic Prompting**: System prompts are automatically generated
+- **Validation**: Built-in response validation and parsing
+- **Consistency**: Ensures AI outputs match your expected format
+- **Developer Experience**: IntelliSense and compile-time type checking
+
 ## 📝 Environment Variables
 
 Set up your API keys: