Initial commit: Llama API Client with full documentation

- Added complete Python client for Llama AI models
- Support for internal network endpoints (tested and working)
- Support for external network endpoints (configured)
- Interactive chat interface with multiple models
- Automatic endpoint testing and failover
- Response cleaning for special markers
- Full documentation in English and Chinese
- Complete test suite and examples
- MIT License and contribution guidelines

demo_chat.py

@@ -0,0 +1,124 @@
+"""
+Llama API 對話程式 (示範版本)
+當 API 伺服器恢復後，可以使用此程式進行對話
+"""
+
+from openai import OpenAI
+import time
+
+# API 設定
+API_KEY = "paVrIT+XU1NhwCAOb0X4aYi75QKogK5YNMGvQF1dCyo="
+BASE_URL = "https://llama.theaken.com/v1"
+
+def simulate_chat():
+    """模擬對話功能（用於展示）"""
+    print("\n" + "="*50)
+    print("Llama AI 對話系統 - 示範模式")
+    print("="*50)
+    print("\n[注意] API 伺服器目前離線，以下為模擬對話")
+    print("當伺服器恢復後，將自動連接真實 API\n")
+    
+    # 模擬回應
+    demo_responses = [
+        "你好！我是 Llama AI 助手，很高興為你服務。",
+        "這是一個示範回應。當 API 伺服器恢復後，你將收到真實的 AI 回應。",
+        "我可以回答問題、協助編程、翻譯文字等多種任務。",
+        "請問有什麼我可以幫助你的嗎？"
+    ]
+    
+    response_index = 0
+    print("輸入 'exit' 結束對話\n")
+    
+    while True:
+        user_input = input("你: ").strip()
+        
+        if user_input.lower() in ['exit', 'quit']:
+            print("\n再見！")
+            break
+            
+        if not user_input:
+            continue
+        
+        # 模擬思考時間
+        print("\nAI 思考中", end="")
+        for _ in range(3):
+            time.sleep(0.3)
+            print(".", end="", flush=True)
+        print()
+        
+        # 顯示模擬回應
+        print(f"\nAI: {demo_responses[response_index % len(demo_responses)]}")
+        response_index += 1
+
+def real_chat():
+    """實際對話功能（當 API 可用時）"""
+    client = OpenAI(api_key=API_KEY, base_url=BASE_URL)
+    
+    print("\n" + "="*50)
+    print("Llama AI 對話系統")
+    print("="*50)
+    print("\n已連接到 Llama API")
+    print("輸入 'exit' 結束對話\n")
+    
+    messages = []
+    
+    while True:
+        user_input = input("你: ").strip()
+        
+        if user_input.lower() in ['exit', 'quit']:
+            print("\n再見！")
+            break
+            
+        if not user_input:
+            continue
+            
+        messages.append({"role": "user", "content": user_input})
+        
+        try:
+            print("\nAI 思考中...")
+            response = client.chat.completions.create(
+                model="gpt-oss-120b",
+                messages=messages,
+                temperature=0.7,
+                max_tokens=1000
+            )
+            
+            ai_response = response.choices[0].message.content
+            print(f"\nAI: {ai_response}")
+            messages.append({"role": "assistant", "content": ai_response})
+            
+        except Exception as e:
+            print(f"\n[錯誤] {str(e)[:100]}")
+            print("無法取得回應，請稍後再試")
+
+def main():
+    print("檢查 API 連接狀態...")
+    
+    # 嘗試連接 API
+    try:
+        client = OpenAI(api_key=API_KEY, base_url=BASE_URL)
+        
+        # 快速測試
+        response = client.chat.completions.create(
+            model="gpt-oss-120b",
+            messages=[{"role": "user", "content": "test"}],
+            max_tokens=10,
+            timeout=5
+        )
+        print("[成功] API 已連接")
+        real_chat()
+        
+    except Exception as e:
+        error_msg = str(e)
+        if "502" in error_msg or "Bad gateway" in error_msg:
+            print("[提示] API 伺服器目前離線 (502 錯誤)")
+            print("進入示範模式...")
+            simulate_chat()
+        else:
+            print(f"[錯誤] 無法連接: {error_msg[:100]}")
+            print("\n是否要進入示範模式? (y/n): ", end="")
+            if input().lower() == 'y':
+                simulate_chat()
+
+if __name__ == "__main__":
+    main()