GPT API开发文档

openAI API接口文档查看地址 https://platform.openai.com/docs/api-reference/making-requests

如果打不开open AI 的链接，就勉强看看下面的例子吧，附件为API文档

1. 聊天接口
请求JSON
curl https://api.openai.com/v1/chat/completions 
  -H “Content-Type: application/json” 
  -H “Authorization: Bearer $OPENAI_API_KEY” 
  -d ‘{
     “model”: “gpt-3.5-turbo”,
     “messages”: [{“role”: “user”, “content”: “Say this is a test!”}],
     “temperature”: 0.7
   }’

响应JSON
{
   “id”:”chatcmpl-abc123″,
   “object”:”chat.completion”,
   “created”:1677858242,
   “model”:”gpt-3.5-turbo-0301″,
   “usage”:{
      “prompt_tokens”:13,
      “completion_tokens”:7,
      “total_tokens”:20
   },
   “choices”:[
      {
         “message”:{
            “role”:”assistant”,
            “content”:”nnThis is a test!”
         },
         “finish_reason”:”stop”,
         “index”:0
      }
   ]
}

2. 列出可用的模型
curl https://api.openai.com/v1/models
  -H “Authorization: Bearer $OPENAI_API_KEY”

响应JSON
{
  “data”: [
    {
      “id”: “model-id-0”,
      “object”: “model”,
      “owned_by”: “organization-owner”,
      “permission”: […]
    },
    {
      “id”: “model-id-1”,
      “object”: “model”,
      “owned_by”: “organization-owner”,
      “permission”: […]
    },
    {
      “id”: “model-id-2”,
      “object”: “model”,
      “owned_by”: “openai”,
      “permission”: […]
    },
  ],
  “object”: “list”
}

3. 检索模型
curl https://api.openai.com/v1/models/text-davinci-003
  -H “Authorization: Bearer $OPENAI_API_KEY”

响应JSON
{
  “id”: “text-davinci-003”,
  “object”: “model”,
  “owned_by”: “openai”,
  “permission”: […]
}

 
 
4. 一般的请求接口
curl https://api.openai.com/v1/completions
  -H “Content-Type: application/json”
  -H “Authorization: Bearer $OPENAI_API_KEY”
  -d ‘{
    “model”: “text-davinci-003”,
    “prompt”: “Say this is a test”,
    “max_tokens”: 7,
    “temperature”: 0
  }’
  
响应示例
{
  “id”: “cmpl-uqkvlQyYK7bGYrRHQ0eXlWi7”,
  “object”: “text_completion”,
  “created”: 1589478378,
  “model”: “text-davinci-003”,
  “choices”: [
    {
      “text”: “nnThis is indeed a test”,
      “index”: 0,
      “logprobs”: null,
      “finish_reason”: “length”
    }
  ],
  “usage”: {
    “prompt_tokens”: 5,
    “completion_tokens”: 7,
    “total_tokens”: 12
  }
}
 
  
 5. 聊天接口
curl https://api.openai.com/v1/chat/completions
  -H “Content-Type: application/json”
  -H “Authorization: Bearer $OPENAI_API_KEY”
  -d ‘{
    “model”: “gpt-3.5-turbo”,
    “messages”: [{“role”: “user”, “content”: “Hello!”}]
  }’

响应示例
{
  “id”: “chatcmpl-123”,
  “object”: “chat.completion”,
  “created”: 1677652288,
  “choices”: [{
    “index”: 0,
    “message”: {
      “role”: “assistant”,
      “content”: “nnHello there, how may I assist you today?”,
    },
    “finish_reason”: “stop”
  }],
  “usage”: {
    “prompt_tokens”: 9,
    “completion_tokens”: 12,
    “total_tokens”: 21
  }
}

6. 图像
curl https://api.openai.com/v1/images/variations
  -H “Authorization: Bearer $OPENAI_API_KEY”
  -F image=”@otter.png”
  -F n=2
  -F size=”1024×1024″

响应示例
{
  “created”: 1589478378,
  “data”: [
    {
      “url”: “https://…”
    },
    {
      “url”: “https://…”
    }
  ]
}
 

服务器托管，北京服务器托管，服务器租用 http://www.fwqtg.net

相关推荐: 揭秘Karmada百倍集群规模多云基础设施体系

摘要：本文结合Karmada社区对大规模场景的思考，揭示Karmada稳定支持100个大规模集群、管理超过50万个节点和200万个Pod背后的原理 本文分享自华为云社区《Karmada百倍集群规模多云基础设施体系揭秘》，作者： 云容器大未来 。 随着云原生技术…