aken1023
c6cc91da7f
- 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
99 lines
2.6 KiB
Python
99 lines
2.6 KiB
Python
from openai import OpenAI
|
||
import sys
|
||
|
||
API_KEY = "paVrIT+XU1NhwCAOb0X4aYi75QKogK5YNMGvQF1dCyo="
|
||
BASE_URL = "https://llama.theaken.com/v1"
|
||
|
||
AVAILABLE_MODELS = [
|
||
"gpt-oss-120b",
|
||
"deepseek-r1-671b",
|
||
"qwen3-embedding-8b"
|
||
]
|
||
|
||
def chat_with_llama(model_name="gpt-oss-120b"):
|
||
client = OpenAI(
|
||
api_key=API_KEY,
|
||
base_url=BASE_URL
|
||
)
|
||
|
||
print(f"\n使用模型: {model_name}")
|
||
print("-" * 50)
|
||
print("輸入 'exit' 或 'quit' 來結束對話")
|
||
print("-" * 50)
|
||
|
||
messages = []
|
||
|
||
while True:
|
||
user_input = input("\n你: ").strip()
|
||
|
||
if user_input.lower() in ['exit', 'quit']:
|
||
print("對話結束")
|
||
break
|
||
|
||
if not user_input:
|
||
continue
|
||
|
||
messages.append({"role": "user", "content": user_input})
|
||
|
||
try:
|
||
response = client.chat.completions.create(
|
||
model=model_name,
|
||
messages=messages,
|
||
temperature=0.7,
|
||
max_tokens=2000
|
||
)
|
||
|
||
assistant_reply = response.choices[0].message.content
|
||
print(f"\nAI: {assistant_reply}")
|
||
|
||
messages.append({"role": "assistant", "content": assistant_reply})
|
||
|
||
except Exception as e:
|
||
print(f"\n錯誤: {str(e)}")
|
||
print("請檢查網路連接和 API 設定")
|
||
|
||
def test_connection():
|
||
print("測試連接到 Llama API...")
|
||
|
||
client = OpenAI(
|
||
api_key=API_KEY,
|
||
base_url=BASE_URL
|
||
)
|
||
|
||
try:
|
||
response = client.chat.completions.create(
|
||
model="gpt-oss-120b",
|
||
messages=[{"role": "user", "content": "Hello, this is a test message."}],
|
||
max_tokens=50
|
||
)
|
||
print("[OK] 連接成功!")
|
||
print(f"測試回應: {response.choices[0].message.content}")
|
||
return True
|
||
except Exception as e:
|
||
print(f"[ERROR] 連接失敗: {str(e)[:200]}")
|
||
return False
|
||
|
||
def main():
|
||
print("=" * 50)
|
||
print("Llama 模型對話測試程式")
|
||
print("=" * 50)
|
||
|
||
print("\n可用的模型:")
|
||
for i, model in enumerate(AVAILABLE_MODELS, 1):
|
||
print(f" {i}. {model}")
|
||
|
||
if test_connection():
|
||
print("\n選擇要使用的模型 (輸入數字 1-3，預設: 1):")
|
||
choice = input().strip()
|
||
|
||
if choice == "2":
|
||
model = AVAILABLE_MODELS[1]
|
||
elif choice == "3":
|
||
model = AVAILABLE_MODELS[2]
|
||
else:
|
||
model = AVAILABLE_MODELS[0]
|
||
|
||
chat_with_llama(model)
|
||
|
||
if __name__ == "__main__":
|
||
main() |