API 目录

官方 Function Calling 调用

POST
/v1/chat/completions

Function Calling 调用

POST https://www.vortapapi.com/v1/chat/completions

使用 Chat Completions 接口向模型发送对话消息,并可通过 tools 参数声明可调用的函数。模型会根据上下文判断是否需要调用函数,并在响应中返回对应的工具调用信息。

该接口兼容 OpenAI API 格式。

请求头

名称必填说明
Content-Type请求体格式,通常为 application/json
Accept响应格式,通常为 application/json
AuthorizationAPI Key 鉴权信息,格式为 Bearer sk-***

请求示例

curl https://www.vortapapi.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -H "Authorization: Bearer sk-***" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [
      {
        "role": "user",
        "content": "北京今天的天气怎么样?"
      }
    ],
    "tools": [
      {
        "type": "function",
        "function": {
          "name": "get_weather",
          "description": "获取指定城市的天气信息",
          "parameters": {
            "type": "object",
            "properties": {
              "city": {
                "type": "string",
                "description": "城市名称"
              }
            },
            "required": ["city"]
          }
        }
      }
    ]
  }'

响应示例

普通文本回复示例:

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

当模型决定调用函数时,响应中的 message 可能包含 tool_calls

{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": null,
        "tool_calls": [
          {
            "id": "call_abc123",
            "type": "function",
            "function": {
              "name": "get_weather",
              "arguments": "{\"city\":\"北京\"}"
            }
          }
        ]
      },
      "finish_reason": "tool_calls"
    }
  ],
  "usage": {
    "prompt_tokens": 60,
    "completion_tokens": 18,
    "total_tokens": 78
  }
}

字段说明

字段说明
id本次补全结果的唯一标识
object对象类型,通常为 chat.completion
created响应创建时间,Unix 时间戳
choices模型生成的候选结果列表
choices[].index当前候选结果的序号
choices[].message模型返回的消息内容
choices[].message.role消息角色,通常为 assistant
choices[].message.content模型生成的文本内容;如果触发工具调用,可能为 null
choices[].message.tool_calls模型请求调用的工具列表
choices[].finish_reason生成结束原因,例如 stoptool_calls
usage.prompt_tokens输入消耗的 token 数
usage.completion_tokens输出消耗的 token 数
usage.total_tokens本次请求总 token 数