Gemini (OpenAI格式)-可文件分析

POST

/v1/chat/completions

文件分析支持的文件类型

mimeTypes := map[string]string{
	".pdf":  "application/pdf",
	".mp3":  "audio/mp3",
	".mp4":  "video/mp4",
	".wav":  "audio/wav",
	".png":  "image/png",
	".jpg":  "image/jpeg",
	".jpeg": "image/jpeg",
	".txt":  "text/plain",
	".mov":  "video/mov",
	".mpeg": "video/mpeg",
	".mpg":  "video/mpg",
	".avi":  "video/avi",
	".wmv":  "video/wmv",
	".flv":  "video/flv",
}

请求参数

Authorization

在 Header 添加参数

Authorization

，其值为在 Bearer 之后拼接 Token

示例：

Authorization: Bearer ********************

Header 参数

Body 参数application/json

示例

// 聊天示例
{
    "model": "gemini-2.5-pro",
    "messages": [
        {
            "role": "user",
            "content": "你好，你是？"
        }
    ],
    "max_tokens": 1688,
    "temperature": 0.5,
    "stream": false
}

// 文件分析示例:一

{
  "model": "gemini-2.5-pro",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "总结一下文档内容"
        },
        {
          "type": "file",
          "file": {
            "filename": "api-doc.pdf",
            "file_data": "https://www.bt.cn/data/api-doc.pdf"
          }
        }
      ]
    }
  ],
  "max_tokens": 1000,
  "stream": false
}

// 文件分析示例:二

{
  "model": "gemini-2.5-pro",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "总结一下文档内容"
        },
        {
          "type": "file_url",
          "file_url": {
            "url": "https://www.bt.cn/data/api-doc.pdf"
          }
        }
      ]
    }
  ],
  "max_tokens": 1000,
  "stream": false
}

// 联网搜索

{
    "model": "gemini-2.5-flash",
    "messages": [
        {
            "role": "user",
            "content": "今天几号？"
        }
    ],
    "max_tokens": 1688,
    "temperature": 0.5,
    "stream": false,
    "tools": [
        {
            "type": "function",
            "function": {
                "name": "googleSearch"
            }
        }
    ]
}

示例代码

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location --request POST 'https://api.gpt.ge/v1/chat/completions' \
--header 'Content-Type: application/json' \
--data-raw '// 聊天示例
{
    "model": "gemini-2.5-pro",
    "messages": [
        {
            "role": "user",
            "content": "你好，你是？"
        }
    ],
    "max_tokens": 1688,
    "temperature": 0.5,
    "stream": false
}

// 文件分析示例:一

{
  "model": "gemini-2.5-pro",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "总结一下文档内容"
        },
        {
          "type": "file",
          "file": {
            "filename": "api-doc.pdf",
            "file_data": "https://www.bt.cn/data/api-doc.pdf"
          }
        }
      ]
    }
  ],
  "max_tokens": 1000,
  "stream": false
}

// 文件分析示例:二

{
  "model": "gemini-2.5-pro",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "总结一下文档内容"
        },
        {
          "type": "file_url",
          "file_url": {
            "url": "https://www.bt.cn/data/api-doc.pdf"
          }
        }
      ]
    }
  ],
  "max_tokens": 1000,
  "stream": false
}

// 联网搜索

{
    "model": "gemini-2.5-flash",
    "messages": [
        {
            "role": "user",
            "content": "今天几号？"
        }
    ],
    "max_tokens": 1688,
    "temperature": 0.5,
    "stream": false,
    "tools": [
        {
            "type": "function",
            "function": {
                "name": "googleSearch"
            }
        }
    ]
}'

返回响应

🟢200成功

application/json

Body

示例

{"id":"chatcmpl-e75b12fad68f41bc8dc9f3820152ec9b","object":"chat.completion","created":1724998489,"choices":[{"index":0,"message":{"role":"assistant","content":"你好！我是一个大型语言模型，由 Google 训练。很高兴认识你！你想聊些什么呢？ \n"},"finish_reason":"stop"}],"usage":{"prompt_tokens":5,"completion_tokens":23,"total_tokens":28}}

修改于 2025-08-02 03:25:09

Claude (原生格式)-可PDF分析

GPTs

Gemini (OpenAI格式)-可文件分析

文件分析支持的文件类型#

请求参数

示例代码

返回响应

文件分析支持的文件类型