ChatGPTNextChat项目重构计划（三）：NextChat API 文档测试总结-CSDN博客

本文链接：https://blog.csdn.net/qq_33489955/article/details/147982309

🚀大模型落地开发实战指南！请关注微信公众号：「AGI启程号」 深入浅出，助你轻松入门！
📚 数据分析、深度学习、大模型与算法的综合进阶，尽在CSDN博客主页

本篇文章是上一篇文章基础上补充总结，可以跳过直接到下一篇。

NextChat API 文档测试总结

1. 主要API端点

1.1 聊天接口 - `/api/openai/v1/chat/completions`

请求方法: POST

请求格式:

{
  "messages": [
    {"role": "system", "content": "你是一个助手"},
    {"role": "user", "content": "你好"}
  ],
  "model": "gpt-4o-mini",
  "stream": true,
  "temperature": 0.5,
  "presence_penalty": 0,
  "frequency_penalty": 0,
  "top_p": 1,
  "max_tokens": 4000
}

响应格式:

流式响应 (stream=true):

data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","choices":[{"delta":{"content":"你好"},"index":0}]}
data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","choices":[{"delta":{"content":"！"},"index":0}]}
...
data: [DONE]

非流式响应 (stream=false):

{
  "id": "chatcmpl-xxx",
  "object": "chat.completion",
  "choices": [{
    "message": {"role": "assistant", "content": "你好！有什么可以帮助你的吗？"},
    "index": 0
  }]
}

1.2 获取模型列表 - `/api/openai/v1/models`

请求方法: GET

响应格式:

{ 
  "object": "list",
  "data": [
    {"id": "gpt-4o-mini", "object": "model", "created": 1721172741, "owned_by": "system"},
    {"id": "gpt-3.5-turbo", "object": "model", "created": 1677610602, "owned_by": "openai"}
  ] 
}

1.3 获取系统配置 - `/api/config`

请求方法: GET

响应格式:

{
  "needCode": false,
  "hideUserApiKey": false,
  "disableGPT4": false,
  "hideBalanceQuery": true,
  "disableFastLink": false,
  "customModels": "",
  "defaultModel": "",
  "visionModels": ""
}

2. 测试命令

2.1 测试模型列表端点

Invoke-WebRequest -Uri "http://localhost:3000/api/openai/v1/models" -Method GET | 
  Select-Object -ExpandProperty Content | 
  ConvertFrom-Json | 
  Format-List

2.2 测试配置端点

Invoke-WebRequest -Uri "http://localhost:3000/api/config" -Method GET | 
  Select-Object -ExpandProperty Content | 
  ConvertFrom-Json | 
  Format-List

2.3 测试聊天接口 (非流式)

$body = @{
    messages = @(
        @{role = "user"; content = "你好"}
    )
    model = "gpt-4o-mini"
    stream = $false
} | ConvertTo-Json

Invoke-WebRequest -Uri "http://localhost:3000/api/openai/v1/chat/completions" -Method POST -Body $body -ContentType "application/json" | 
  Select-Object -ExpandProperty Content

2.4 浏览器Console测试

// 测试配置
fetch('/api/config').then(res => res.json()).then(console.log)

// 测试模型列表
fetch('/api/openai/v1/models').then(res => res.json()).then(console.log)

// 测试聊天接口
fetch('/api/openai/v1/chat/completions', {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
    messages: [{role: 'user', content: '你好'}],
    model: 'gpt-4o-mini',
    stream: false
  })
}).then(res => res.json()).then(console.log)