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

test_with_timeout.py

@@ -0,0 +1,111 @@
+import requests
+import json
+from datetime import datetime
+
+# API 配置
+API_KEY = "paVrIT+XU1NhwCAOb0X4aYi75QKogK5YNMGvQF1dCyo="
+BASE_URL = "https://llama.theaken.com/v1"
+
+def test_endpoints():
+    """測試不同的 API 端點和模型"""
+    
+    print("="*60)
+    print(f"Llama API 測試 - {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}")
+    print("="*60)
+    
+    headers = {
+        "Authorization": f"Bearer {API_KEY}",
+        "Content-Type": "application/json"
+    }
+    
+    # 測試配置
+    tests = [
+        {
+            "name": "GPT-OSS-120B",
+            "model": "gpt-oss-120b",
+            "prompt": "Say hello in one word"
+        },
+        {
+            "name": "DeepSeek-R1-671B", 
+            "model": "deepseek-r1-671b",
+            "prompt": "Say hello in one word"
+        },
+        {
+            "name": "Qwen3-Embedding-8B",
+            "model": "qwen3-embedding-8b",
+            "prompt": "Say hello in one word"
+        }
+    ]
+    
+    success_count = 0
+    
+    for test in tests:
+        print(f"\n[測試 {test['name']}]")
+        print("-"*40)
+        
+        data = {
+            "model": test["model"],
+            "messages": [
+                {"role": "user", "content": test["prompt"]}
+            ],
+            "temperature": 0.5,
+            "max_tokens": 20
+        }
+        
+        try:
+            # 使用較短的超時時間
+            response = requests.post(
+                f"{BASE_URL}/chat/completions",
+                headers=headers,
+                json=data,
+                timeout=15
+            )
+            
+            print(f"HTTP 狀態: {response.status_code}")
+            
+            if response.status_code == 200:
+                result = response.json()
+                if 'choices' in result:
+                    content = result['choices'][0]['message']['content']
+                    print(f"[SUCCESS] 成功回應: {content}")
+                    success_count += 1
+                else:
+                    print("[ERROR] 回應格式錯誤")
+            elif response.status_code == 502:
+                print("[ERROR] 502 Bad Gateway - 伺服器無法回應")
+            elif response.status_code == 401:
+                print("[ERROR] 401 Unauthorized - API 金鑰可能錯誤")
+            elif response.status_code == 404:
+                print("[ERROR] 404 Not Found - 模型或端點不存在")
+            else:
+                print(f"[ERROR] 錯誤 {response.status_code}")
+                if not response.text.startswith('<!DOCTYPE'):
+                    print(f"詳情: {response.text[:200]}")
+                    
+        except requests.exceptions.Timeout:
+            print("[TIMEOUT] 請求超時 (15秒)")
+        except requests.exceptions.ConnectionError as e:
+            print(f"[CONNECTION ERROR] 無法連接到伺服器")
+        except Exception as e:
+            print(f"[UNKNOWN ERROR]: {str(e)[:100]}")
+    
+    # 總結
+    print("\n" + "="*60)
+    print(f"測試結果: {success_count}/{len(tests)} 成功")
+    
+    if success_count == 0:
+        print("\n診斷資訊:")
+        print("• 網路連接: 正常 (可 ping 通)")
+        print("• API 端點: https://llama.theaken.com/v1")
+        print("• 錯誤類型: 502 Bad Gateway")
+        print("• 可能原因: 後端 API 服務暫時離線")
+        print("\n建議行動:")
+        print("1. 稍後再試 (建議 10-30 分鐘後)")
+        print("2. 聯繫 API 管理員確認服務狀態")
+        print("3. 檢查是否有服務維護公告")
+    else:
+        print(f"\n[OK] API 服務正常運作中!")
+        print(f"[OK] 可使用的模型數: {success_count}")
+
+if __name__ == "__main__":
+    test_endpoints()