WeLM微信AI语言模型接入教程

前言说明

WeLM是微信推出的一个能够理解和生成文本的通用语言模型(类似ChatGPT)，提供了API来解决各种文本任务。在本教程中，我们将展示如何利用PHP和Python来接入微信AI语言模型WeLM。

使用方法

一、申请微信AI·WELM密钥

1、打开官网，填写问卷，会自动发送Key到邮箱，点击下面按钮直达

2、问卷最好不要使用QQ邮箱，使用其他邮箱（其他邮箱几分钟就发放Token了，qq邮箱一直都没收到token发放记录）

二、PHP对接微信AI-Welm

1、不废话直接上代码（第45行换成你们在welm官网申请的key）

<?php
function query_api($prompt, $model, $max_tokens, $temperature, $top_p, $top_k, $n, $echo, $stop, $token) {
/**
* Welm 微信AI
* Author：360模板吧
*/
$url = "https://welm.weixin.qq.com/v1/completions";
$data = array(
"prompt" => $prompt,
"model" => $model,
"max_tokens" => $max_tokens,
"temperature" => $temperature,
"top_p" => $top_p,
"top_k" => $top_k,
"n" => $n,
"echo" => $echo,
"stop" => $stop
);
$data = json_encode($data);
 
$headers = array(
"Content-Type: application/json",
"Authorization: Bearer " . $token
);
 
$curl = curl_init();
 
curl_setopt_array($curl, array(
CURLOPT_URL => $url,
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => $data,
CURLOPT_HTTPHEADER => $headers,
));
 
$response = curl_exec($curl);
$err = curl_error($curl);
 
curl_close($curl);
 
if ($err) {
echo "请求失败: " . $err;
return null;
} else {
$result = json_decode($response, true);
return $result;
}
}
 
if (isset($_POST["submit"])) {
$prompt = "测试";
$model = "xl";
$max_tokens = 16;
$temperature = 0.0;
$top_p = 0.0;
$top_k = 10;
$n = 1;
$echo = false;
$stop = ",，.。";
$token = "你的token";
 
$result = query_api($prompt, $model, $max_tokens, $temperature, $top_p, $top_k, $n, $echo, $stop, $token);
 
if ($result) {
echo "<pre>";
print_r($result);
echo "</pre>";
}
}
?>
<form method="post">
<input type="submit" name="submit" value="获取结果">
</form>

三、Python对接微信AI-Welm

1、不废话直接上代码，直接上代码（第45行换成你们在welm官网申请的key）

import requests
import json
 
def query_api(prompt, model, max_tokens, temperature, top_p, top_k, n, echo, stop, token):
    """
    查询API接口
    """
    url = 'https://welm.weixin.qq.com/v1/completions'
    headers = {
        'Content-Type': 'application/json',
        'Authorization': f'Bearer {token}'
    }
    data = {
        "prompt": prompt,
        "model": model,
        "max_tokens": max_tokens,
        "temperature": temperature,
        "top_p": top_p,
        "top_k": top_k,
        "n": n,
        "echo": echo,
        "stop": stop
    }
 
    try:
        response = requests.post(url, headers=headers, data=json.dumps(data))
        response.raise_for_status()
    except requests.exceptions.HTTPError as err:
        print(f"请求失败: {err}")
        return None
 
    result = json.loads(response.text)
    return result
 
if __name__ == '__main__':
    prompt = "测试"
    model = "xl"
    max_tokens = 16
    temperature = 0.0
    top_p = 0.0
    top_k = 10
    n = 1
    echo = False
    stop = ",，.。"
    token = "你的token"
 
    result = query_api(prompt, model, max_tokens, temperature, top_p, top_k, n, echo, stop, token)
    if result:
        print(result)