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
This commit is contained in:
293
llama_full_api.py
Normal file
293
llama_full_api.py
Normal file
@@ -0,0 +1,293 @@
|
||||
#!/usr/bin/env python
|
||||
# -*- coding: utf-8 -*-
|
||||
"""
|
||||
Llama API 完整對話程式
|
||||
支援內網和外網端點
|
||||
"""
|
||||
|
||||
from openai import OpenAI
|
||||
import requests
|
||||
import sys
|
||||
import re
|
||||
from datetime import datetime
|
||||
|
||||
# API 金鑰
|
||||
API_KEY = "paVrIT+XU1NhwCAOb0X4aYi75QKogK5YNMGvQF1dCyo="
|
||||
|
||||
# API 端點配置
|
||||
ENDPOINTS = {
|
||||
"內網": [
|
||||
{
|
||||
"name": "內網端點 1 (21180)",
|
||||
"url": "http://192.168.0.6:21180/v1",
|
||||
"models": ["gpt-oss-120b", "deepseek-r1-671b", "qwen3-embedding-8b"]
|
||||
},
|
||||
{
|
||||
"name": "內網端點 2 (21181)",
|
||||
"url": "http://192.168.0.6:21181/v1",
|
||||
"models": ["gpt-oss-120b", "deepseek-r1-671b", "qwen3-embedding-8b"]
|
||||
},
|
||||
{
|
||||
"name": "內網端點 3 (21182)",
|
||||
"url": "http://192.168.0.6:21182/v1",
|
||||
"models": ["gpt-oss-120b", "deepseek-r1-671b", "qwen3-embedding-8b"]
|
||||
}
|
||||
],
|
||||
"外網": [
|
||||
{
|
||||
"name": "外網 GPT-OSS-120B",
|
||||
"url": "https://llama.theaken.com/v1/gpt-oss-120b",
|
||||
"models": ["gpt-oss-120b"]
|
||||
},
|
||||
{
|
||||
"name": "外網 DeepSeek-R1-671B",
|
||||
"url": "https://llama.theaken.com/v1/deepseek-r1-671b",
|
||||
"models": ["deepseek-r1-671b"]
|
||||
},
|
||||
{
|
||||
"name": "外網通用端點",
|
||||
"url": "https://llama.theaken.com/v1",
|
||||
"models": ["gpt-oss-120b", "deepseek-r1-671b", "qwen3-embedding-8b"]
|
||||
}
|
||||
]
|
||||
}
|
||||
|
||||
def clean_response(text):
|
||||
"""清理 AI 回應中的特殊標記"""
|
||||
# 移除思考標記
|
||||
if "<think>" in text:
|
||||
text = re.sub(r'<think>.*?</think>', '', text, flags=re.DOTALL)
|
||||
|
||||
# 移除 channel 標記
|
||||
if "<|channel|>" in text:
|
||||
parts = text.split("<|message|>")
|
||||
if len(parts) > 1:
|
||||
text = parts[-1]
|
||||
|
||||
# 移除結束標記
|
||||
text = text.replace("<|end|>", "").replace("<|start|>", "")
|
||||
|
||||
# 清理多餘空白
|
||||
text = text.strip()
|
||||
|
||||
return text
|
||||
|
||||
def test_endpoint(endpoint_info):
|
||||
"""測試端點是否可用"""
|
||||
url = endpoint_info["url"]
|
||||
model = endpoint_info["models"][0] # 使用第一個模型測試
|
||||
|
||||
try:
|
||||
# 對於特定模型的 URL，需要特殊處理
|
||||
if "/gpt-oss-120b" in url or "/deepseek-r1-671b" in url:
|
||||
# 這些可能是特定模型的端點
|
||||
base_url = url.rsplit("/", 1)[0] # 移除模型名稱部分
|
||||
else:
|
||||
base_url = url
|
||||
|
||||
client = OpenAI(api_key=API_KEY, base_url=base_url)
|
||||
response = client.chat.completions.create(
|
||||
model=model,
|
||||
messages=[{"role": "user", "content": "test"}],
|
||||
max_tokens=5,
|
||||
timeout=8
|
||||
)
|
||||
return True
|
||||
except Exception as e:
|
||||
# 也嘗試使用 requests 直接測試
|
||||
try:
|
||||
headers = {
|
||||
"Authorization": f"Bearer {API_KEY}",
|
||||
"Content-Type": "application/json"
|
||||
}
|
||||
|
||||
test_url = f"{url}/chat/completions" if not url.endswith("/chat/completions") else url
|
||||
data = {
|
||||
"model": model,
|
||||
"messages": [{"role": "user", "content": "test"}],
|
||||
"max_tokens": 5
|
||||
}
|
||||
|
||||
response = requests.post(test_url, headers=headers, json=data, timeout=8)
|
||||
return response.status_code == 200
|
||||
except:
|
||||
return False
|
||||
|
||||
def test_all_endpoints():
|
||||
"""測試所有端點"""
|
||||
print("\n" + "="*60)
|
||||
print("測試 API 端點連接")
|
||||
print("="*60)
|
||||
|
||||
available_endpoints = []
|
||||
|
||||
# 測試內網端點
|
||||
print("\n[內網端點測試]")
|
||||
for endpoint in ENDPOINTS["內網"]:
|
||||
print(f" 測試 {endpoint['name']}...", end="", flush=True)
|
||||
if test_endpoint(endpoint):
|
||||
print(" [OK]")
|
||||
available_endpoints.append(("內網", endpoint))
|
||||
else:
|
||||
print(" [FAIL]")
|
||||
|
||||
# 測試外網端點
|
||||
print("\n[外網端點測試]")
|
||||
for endpoint in ENDPOINTS["外網"]:
|
||||
print(f" 測試 {endpoint['name']}...", end="", flush=True)
|
||||
if test_endpoint(endpoint):
|
||||
print(" [OK]")
|
||||
available_endpoints.append(("外網", endpoint))
|
||||
else:
|
||||
print(" [FAIL]")
|
||||
|
||||
return available_endpoints
|
||||
|
||||
def chat_session(endpoint_info):
|
||||
"""對話主程式"""
|
||||
print("\n" + "="*60)
|
||||
print("Llama AI 對話系統")
|
||||
print("="*60)
|
||||
print(f"端點: {endpoint_info['name']}")
|
||||
print(f"URL: {endpoint_info['url']}")
|
||||
print(f"可用模型: {', '.join(endpoint_info['models'])}")
|
||||
print("\n指令:")
|
||||
print(" exit/quit - 結束對話")
|
||||
print(" clear - 清空對話歷史")
|
||||
print(" model - 切換模型")
|
||||
print("-"*60)
|
||||
|
||||
# 處理 URL
|
||||
url = endpoint_info["url"]
|
||||
if "/gpt-oss-120b" in url or "/deepseek-r1-671b" in url:
|
||||
base_url = url.rsplit("/", 1)[0]
|
||||
else:
|
||||
base_url = url
|
||||
|
||||
client = OpenAI(api_key=API_KEY, base_url=base_url)
|
||||
|
||||
# 選擇初始模型
|
||||
if len(endpoint_info['models']) == 1:
|
||||
current_model = endpoint_info['models'][0]
|
||||
else:
|
||||
print("\n選擇模型:")
|
||||
for i, model in enumerate(endpoint_info['models'], 1):
|
||||
print(f" {i}. {model}")
|
||||
choice = input("選擇 (預設: 1): ").strip()
|
||||
if choice.isdigit() and 1 <= int(choice) <= len(endpoint_info['models']):
|
||||
current_model = endpoint_info['models'][int(choice)-1]
|
||||
else:
|
||||
current_model = endpoint_info['models'][0]
|
||||
|
||||
print(f"\n使用模型: {current_model}")
|
||||
messages = []
|
||||
|
||||
while True:
|
||||
try:
|
||||
user_input = input("\n你: ").strip()
|
||||
|
||||
if not user_input:
|
||||
continue
|
||||
|
||||
if user_input.lower() in ['exit', 'quit']:
|
||||
print("再見！")
|
||||
break
|
||||
|
||||
if user_input.lower() == 'clear':
|
||||
messages = []
|
||||
print("[系統] 對話歷史已清空")
|
||||
continue
|
||||
|
||||
if user_input.lower() == 'model':
|
||||
if len(endpoint_info['models']) == 1:
|
||||
print(f"[系統] 此端點只支援 {endpoint_info['models'][0]}")
|
||||
else:
|
||||
print("\n可用模型:")
|
||||
for i, m in enumerate(endpoint_info['models'], 1):
|
||||
print(f" {i}. {m}")
|
||||
choice = input("選擇: ").strip()
|
||||
if choice.isdigit() and 1 <= int(choice) <= len(endpoint_info['models']):
|
||||
current_model = endpoint_info['models'][int(choice)-1]
|
||||
print(f"[系統] 已切換到 {current_model}")
|
||||
continue
|
||||
|
||||
messages.append({"role": "user", "content": user_input})
|
||||
|
||||
print("\nAI 思考中...", end="", flush=True)
|
||||
|
||||
try:
|
||||
response = client.chat.completions.create(
|
||||
model=current_model,
|
||||
messages=messages,
|
||||
temperature=0.7,
|
||||
max_tokens=1000
|
||||
)
|
||||
|
||||
ai_response = response.choices[0].message.content
|
||||
ai_response = clean_response(ai_response)
|
||||
|
||||
print("\r" + " "*20 + "\r", end="")
|
||||
print(f"AI: {ai_response}")
|
||||
|
||||
messages.append({"role": "assistant", "content": ai_response})
|
||||
|
||||
except Exception as e:
|
||||
print(f"\r[錯誤] {str(e)[:100]}")
|
||||
messages.pop()
|
||||
|
||||
except KeyboardInterrupt:
|
||||
print("\n\n[中斷] 使用 exit 命令正常退出")
|
||||
continue
|
||||
except EOFError:
|
||||
print("\n再見！")
|
||||
break
|
||||
|
||||
def main():
|
||||
print("="*60)
|
||||
print("Llama API 完整對話程式")
|
||||
print(f"時間: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}")
|
||||
print("="*60)
|
||||
|
||||
# 測試所有端點
|
||||
available = test_all_endpoints()
|
||||
|
||||
if not available:
|
||||
print("\n[錯誤] 沒有可用的端點")
|
||||
print("\n可能的原因:")
|
||||
print("1. 網路連接問題")
|
||||
print("2. API 服務離線")
|
||||
print("3. 防火牆阻擋")
|
||||
sys.exit(1)
|
||||
|
||||
# 顯示可用端點
|
||||
print("\n" + "="*60)
|
||||
print(f"找到 {len(available)} 個可用端點:")
|
||||
print("="*60)
|
||||
|
||||
for i, (network_type, endpoint) in enumerate(available, 1):
|
||||
print(f"{i}. [{network_type}] {endpoint['name']}")
|
||||
print(f" URL: {endpoint['url']}")
|
||||
print(f" 模型: {', '.join(endpoint['models'])}")
|
||||
|
||||
# 選擇端點
|
||||
print("\n選擇端點 (預設: 1): ", end="")
|
||||
choice = input().strip()
|
||||
|
||||
if choice.isdigit() and 1 <= int(choice) <= len(available):
|
||||
selected = available[int(choice)-1][1]
|
||||
else:
|
||||
selected = available[0][1]
|
||||
|
||||
# 開始對話
|
||||
chat_session(selected)
|
||||
|
||||
if __name__ == "__main__":
|
||||
try:
|
||||
main()
|
||||
except KeyboardInterrupt:
|
||||
print("\n\n程式已退出")
|
||||
except Exception as e:
|
||||
print(f"\n[錯誤] {e}")
|
||||
import traceback
|
||||
traceback.print_exc()
|
||||
sys.exit(1)
|
||||
Reference in New Issue
Block a user