# 請求體結(jié)構(gòu)
data = {
    "model": "/models/Qwen2___5-32B-Instruct-AWQ",
    "messages": [
        {"role": "user", "content": "分析當(dāng)前全球經(jīng)濟(jì)形勢，并提出你的見解"}
    ],
    "max_tokens": 2048,
    "temperature": 0.7,
    "top_k": 1,
    "top_p": 0.75,
}

import requests
import json
 
# 本地服務(wù)的 API 端點(diǎn)
url = "http://127.0.0.1:6790/v1/chat/completions"
 
# 請求頭
headers = {
    "Content-Type": "application/json",
    #"Authorization": "Bearer your_api_key"  # 如果需要的話
}
 
# 請求體
data = {
    "model": "/models/Qwen2___5-32B-Instruct-AWQ",
    "messages": [
        {"role": "user", "content": "分析當(dāng)前全球經(jīng)濟(jì)形勢，并提出你的見解"}
    ],
    "max_tokens": 2048,
    "temperature": 0.7,
    "top_k": 1,
    "top_p": 0.75,
}
 
# 發(fā)送 POST 請求
response = requests.post(url, headers=headers, data=json.dumps(data))
 
# 解析并打印回復(fù)內(nèi)容
if response.status_code == 200:
    response_data = response.json()
    print(response_data['choices'][0]['message']['content'])
else:
    print(f"請求失敗，狀態(tài)碼：{response.status_code}")
    print(response.text)

def llm_inference(prompt_list: list, model_name: str):
    # 根據(jù)模型名稱選擇不同的服務(wù)器配置
    if model_name == "qwen2.5_32b_awq":
        llm_server = {"server_url": "http://127.0.0.1:6790/v1/completions",
                      "path": "/psd/models/Qwen2___5-32B-Instruct-AWQ"}

# -*- coding: utf-8 -*-            
# @Author : yuan
# @Time : 2025/7/22 5:20

import requests
import json

def llm_inference(prompt_list: list, model_name: str):
    if model_name == "qwen2.5_32b_awq":
        llm_server = {"server_url": "http://127.0.0.1:6790/v1/completions",
                      "path": "/models/Qwen2___5-32B-Instruct-AWQ"}

    elif model_name == "qwen2.5_7b_awq":
        llm_server = {"server_url": "http://127.0.0.1:6791/v1/completions",
                      "path": "/models/Qwen2___5-7B-Instruct-AWQ"}
    else:
        llm_server = {"server_url": "http://127.0.0.1:6790/v1/completions",
                      "path": "/models/Qwen2___5-32B-Instruct-AWQ"}

    # system_text = ""
    # prompt = f"<|im_start|>system\n{system_text}<|im_end|>\n<|im_start|>user\n{query_text}<|im_end|><|im_start|>assistant\n"
    rewrite_server_url = llm_server["server_url"]
    rewrite_server_headers = {
        'Content-Type': 'application/json'
    }
    rewrite_server_data = {
        'model': llm_server["path"],
        'prompt': prompt_list,
        'max_tokens': 4096, # 生成長度
        'top_k': 1,
        'top_p': 0.75,
        'temperature': 0,
        'stop': ["<|im_end|>"]
    }
    response = requests.post(rewrite_server_url, headers=rewrite_server_headers, data=json.dumps(rewrite_server_data))
    # return response.json()['choices'][0]['text']
    return response.json()

if __name__ == "__main__":
    prompt_list = [f"<|im_start|>system\n{'你是圍城智能機(jī)器人'}<|im_end|>\n<|im_start|>user\n{'你是誰'}<|im_end|><|im_start|>assistant\n"]

    answer = llm_inference(prompt_list, "qwen2.5_32b_awq")
    # print(answer)
    for i in range(len(prompt_list)):
        print(answer['choices'][i]['text'])

client = OpenAI(
    api_key=openai_api_key,
    base_url=openai_api_base,
)
response = client.chat.completions.create(
    model=model_name,
    messages=messages,
    temperature=0.0
)

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
極簡化的API請求測試腳本
只保留發(fā)送請求的核心功能
"""

from openai import OpenAI


def send_test_request(client, model_name, test_message="im testing, response me latter 'test' only"):
    """
    發(fā)送測試請求
    Args:
        client: OpenAI客戶端
        model_name: 模型名稱
        test_message: 測試消息
    Returns:
        str: 響應(yīng)內(nèi)容
    """
    # messages = [
    #     {"role": "user", "content": [
    #         {"type": "text", "text": test_message}
    #     ]}
    # ]
    # 構(gòu)建消息列表
    messages = [{"role": "user", "content": "你叫什么名字！"}]
    response = client.chat.completions.create(
        model=model_name,
        messages=messages,
        temperature=0.0
    )

    print(f"Response: {response}")
    return response.choices[0].message.content


if __name__ == "__main__":
    # API配置
    openai_api_key = "sk-WVoD66MR7b"
    openai_api_base = "https://www.api.com/v1"
    model_name = "gpt-4o"  # gemini-2.5-pro  gpt-4o  Claude 3.5 Sonnet  o3-mini

    # 初始化客戶端
    client = OpenAI(
        api_key=openai_api_key,
        base_url=openai_api_base,
    )
    test_message = "你好"
    # 發(fā)送測試請求
    try:
        response_content = send_test_request(client, model_name, test_message)
        print(f"Success! Response content: {response_content}")
    except Exception as e:
        print(f"Error: {e}")

openai.api_key = "sk-WVoD66MR"
openai.api_base = "https://www.api.com/v1"

response = openai.ChatCompletion.create(
    model=model_name,
    messages=[{"role": "user", "content": "你叫什么名字！"}],
    max_tokens=512,
    temperature=0.7
)

import openai

# 設(shè)置 API 密鑰（如果本地服務(wù)需要）
openai.api_key = "sk-WVoD66MR7bx"

# 設(shè)置 API 基礎(chǔ) URL 為本地模型服務(wù)的地址
# openai.api_base = "http://127.0.0.1:6790/v1"
openai.api_base = "https://www.chataiapi.com/v1"

# 指定要使用的模型名稱
# model_name = "/models/Qwen2___5-32B-Instruct-AWQ"
model_name = "gemini-2.5-pro"

# 創(chuàng)建聊天完成請求
response = openai.ChatCompletion.create(
    model=model_name,
    messages=[{"role": "user", "content": "你叫什么名字！"}],
    max_tokens=512,
    temperature=0.7
)
print("response:",response)
# 打印生成的回復(fù)內(nèi)容
print(response['choices'][0]['message']['content'])