通义千问VL模型API详情

Python

示例代码

from openai import OpenAI
import os


def get_response():
    client = OpenAI(
        api_key=os.getenv("DASHSCOPE_API_KEY"),
        base_url="https://dashscope.aliyuncs.com/compatible-mode/v1",
    )
    completion = client.chat.completions.create(
        model="qwen-vl-max",
        messages=[
            {
              "role": "user",
              "content": [
                {
                  "type": "image_url",
                  "image_url": {
                    "url": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"
                  }
                },
                {
                  "type": "image_url",
                  "image_url": {
                    "url": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/tiger.png"
                  }
                },
                {
                  "type": "text",
                  "text": "这些是什么"
                }
              ]
            }
          ]
        )
    print(completion.model_dump_json())

if __name__=='__main__':
    get_response()

返回结果

{
  "id": "chatcmpl-4b5a3bb9-221f-9687-bdd7-a7d56aae44df",
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "logprobs": null,
      "message": {
        "content": "图1中是一位女士和一只拉布拉多犬在海滩上互动的场景。女士穿着格子衬衫，坐在沙滩上，与狗进行握手的动作，背景是海浪和天空，整个画面充满了温馨和愉快的氛围。\n\n图2中是一只老虎在森林中行走的场景。老虎的毛色是橙色和黑色相间的条纹，它正向前迈步，周围是茂密的树木和植被，地面上覆盖着落叶，整个画面给人一种野生自然的感觉。",
        "role": "assistant",
        "function_call": null,
        "tool_calls": null
      }
    }
  ],
  "created": 1725948492,
  "model": "qwen-vl-max",
  "object": "chat.completion",
  "service_tier": null,
  "system_fingerprint": null,
  "usage": {
    "completion_tokens": 106,
    "prompt_tokens": 2497,
    "total_tokens": 2603
  }
}

curl

示例代码

curl --location 'https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
  "model": "qwen-vl-max",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "image_url",
          "image_url": {
            "url": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"
          }
        },
        {
          "type": "image_url",
          "image_url": {
            "url": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/tiger.png"
          }
        },
        {
          "type": "text",
          "text": "这些是什么"
        }
      ]
    }
  ]
}'

返回结果

{
  "choices": [
    {
      "message": {
        "content": "图1中是一位女士和一只拉布拉多犬在海滩上互动的场景。女士穿着格子衬衫，坐在沙滩上，与狗进行握手的动作，背景是海景和日落的天空，整个画面显得非常温馨和谐。\n\n图2中是一只老虎在森林中行走的场景。老虎的毛色是橙色和黑色条纹相间，它正向前迈步，周围是茂密的树木和植被，地面上覆盖着落叶，整个画面充满了自然的野性和生机。",
        "role": "assistant"
      },
      "finish_reason": "stop",
      "index": 0,
      "logprobs": null
    }
  ],
  "object": "chat.completion",
  "usage": {
    "prompt_tokens": 2497,
    "completion_tokens": 109,
    "total_tokens": 2606
  },
  "created": 1725948561,
  "system_fingerprint": null,
  "model": "qwen-vl-max",
  "id": "chatcmpl-0fd66f46-b09e-9164-a84f-3ebbbedbac15"
}

Python

示例代码

from http import HTTPStatus
import dashscope


def simple_multimodal_conversation_call():
    messages = [
        {
            "role": "user",
            "content": [
                {"image": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"},
                {"image": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/tiger.png"},
                {"image": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/rabbit.png"},
                {"text": "这些是什么?"}
            ]
        }
    ]
    response = dashscope.MultiModalConversation.call(
        model='qwen-vl-plus',
        messages=messages
        )
    if response.status_code == HTTPStatus.OK:
        print(response)
    else:
        print(response.code)
        print(response.message)


if __name__ == '__main__':
    simple_multimodal_conversation_call()

返回结果

{
    "status_code": 200,
    "request_id": "3a031529-707f-9b7d-968c-172e7533debc",
    "code": "",
    "message": "",
    "output": {
        "text": null,
        "finish_reason": null,
        "choices": [
            {
                "finish_reason": "stop",
                "message": {
                    "role": "assistant",
                    "content": [
                        {
                            "text": "图1中是一名女子和狗在沙滩上玩耍。\n图2是孟加拉虎的插画，它正向镜头走来。\n图3里是一只可爱的小白兔。"
                        }
                    ]
                }
            }
        ]
    },
    "usage": {
        "input_tokens": 3743,
        "output_tokens": 41,
        "image_tokens": 3697
    }
}

Java

示例代码

// Copyright (c) Alibaba, Inc. and its affiliates.

import java.util.Arrays;
import java.util.Collections;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversation;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationParam;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationResult;
import com.alibaba.dashscope.common.MultiModalMessage;
import com.alibaba.dashscope.common.Role;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.exception.UploadFileException;
import com.alibaba.dashscope.utils.JsonUtils;
public class Main {
    public static void simpleMultiModalConversationCall()
            throws ApiException, NoApiKeyException, UploadFileException {
        MultiModalConversation conv = new MultiModalConversation();
        MultiModalMessage userMessage = MultiModalMessage.builder().role(Role.USER.getValue())
                .content(Arrays.asList(
                        Collections.singletonMap("image", "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"),
                        Collections.singletonMap("image", "https://dashscope.oss-cn-beijing.aliyuncs.com/images/tiger.png"),
                        Collections.singletonMap("image", "https://dashscope.oss-cn-beijing.aliyuncs.com/images/rabbit.png"),
                        Collections.singletonMap("text", "这些是什么?"))).build();
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                .model("qwen-vl-plus")
                .message(userMessage)
                .build();
        MultiModalConversationResult result = conv.call(param);
        System.out.println(JsonUtils.toJson(result));
    }

    public static void main(String[] args) {
        try {
            simpleMultiModalConversationCall();
        } catch (ApiException | NoApiKeyException | UploadFileException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }
}

返回结果

{
  "requestId": "dcb38a0f-fd69-9071-bcde-c4530f9a7559",
  "usage": {
    "input_tokens": 3740,
    "output_tokens": 48
  },
  "output": {
    "choices": [
      {
        "finish_reason": "stop",
        "message": {
          "role": "assistant",
          "content": [
            {
              "text": "图1中是一名女子和一只大金毛在沙滩上玩耍。\n图2是孟加拉虎的写实照片，老虎正向镜头走来。\n图3是一幅插画，主要展示了一只兔子。"
            }
          ]
        }
      }
    ]
  }
}

curl

示例代码

curl --location 'https://dashscope.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
    "model": "qwen-vl-plus",
    "input":{
        "messages":[
            {
                "role": "user",
                "content": [
                    {"image": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"},
                    {"image": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/tiger.png"},
                    {"image": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/rabbit.png"},
                    {"text": "这些是什么?"}
                ]
            }
        ]
    }
}'

返回结果

{
  "output": {
    "choices": [
      {
        "finish_reason": "stop",
        "message": {
          "role": "assistant",
          "content": [
            {
              "text": "这张图片显示了一位女士和她的狗在海滩上。她们似乎正在享受彼此的陪伴，狗狗坐在沙滩上伸出爪子与女士握手或互动。背景是美丽的日落景色，海浪轻轻拍打着海岸线。\n\n请注意，我提供的描述基于图像中可见的内容，并不包括任何超出视觉信息之外的信息。如果您需要更多关于这个场景的具体细节，请告诉我！"
            }
          ]
        }
      }
    ]
  },
  "usage": {
    "output_tokens": 81,
    "input_tokens": 1277,
    "image_tokens": 1247
  },
  "request_id": "ccf845a3-dc33-9cda-b581-20fe7dc23f70"
}

Python

示例代码

from openai import OpenAI
import os
import base64

#  base 64 编码格式
def encode_image(image_path):
    with open(image_path, "rb") as image_file:
        return base64.b64encode(image_file.read()).decode('utf-8')

def get_response(image_path):
    base64_image = encode_image(image_path)
    client = OpenAI(
        api_key=os.getenv("DASHSCOPE_API_KEY"),
        base_url="https://dashscope.aliyuncs.com/compatible-mode/v1",
    )
    completion = client.chat.completions.create(
        model="qwen-vl-plus",
        messages=[
            {
              "role": "user",
              "content": [
                {
                  "type": "image_url",
                  "image_url": {
                    "url": f"data:image/jpeg;base64,{base64_image}"
                  }
                },
                {
                  "type": "text",
                  "text": "这是什么"
                }
              ]
            }
          ]
        )
    print(completion.model_dump_json())

if __name__=='__main__':
    get_response("test.png")

返回结果

{
  "id": "chatcmpl-7399dbeb-af0c-9fcb-9083-0a836669476d",
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "logprobs": null,
      "message": {
        "content": "这是一只在天空中飞翔的鹰。它有着广阔的翅膀，正在翱翔于云层之间。这种鸟类通常与自由、力量和高瞻远瞩等概念相关联。",
        "role": "assistant",
        "function_call": null,
        "tool_calls": null
      }
    }
  ],
  "created": 1725948726,
  "model": "qwen-vl-plus",
  "object": "chat.completion",
  "service_tier": null,
  "system_fingerprint": null,
  "usage": {
    "completion_tokens": 41,
    "prompt_tokens": 1253,
    "total_tokens": 1294
  }
}

HTTP

示例代码

import os
import base64
import requests

#  base 64 编码格式
def encode_image(image_path):
  with open(image_path, "rb") as image_file:
    return base64.b64encode(image_file.read()).decode('utf-8')

def get_response(image_path):
    base64_image = encode_image(image_path)
    api_key = os.getenv("DASHSCOPE_API_KEY")
    headers = {
       "Content-Type": "application/json",
       "Authorization": f"Bearer {api_key}"
       }
    payload = {
        "model": "qwen-vl-plus",
        "messages": [
            {
            "role": "user",
            "content": [
                {
                "type": "image_url",
                "image_url": {
                    "url": f"data:image/jpeg;base64,{base64_image}"
                }
                },
                {
                "type": "text",
                "text": "这是什么"
                }
            ]
            }
        ]
        }
    response = requests.post("https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions", headers=headers, json=payload)
    print(response.json()) 

if __name__=='__main__':
    get_response(image_path="test.png")

返回结果

{
  "choices": [
    {
      "message": {
        "content": "这是一只在天空中飞翔的鹰。它有着广阔的翅膀，正在翱翔于云层之间。这种鸟类通常被认为是力量、自由和雄心壮志的象征，在各种文化中有重要的地位。",
        "role": "assistant"
      },
      "finish_reason": "stop",
      "index": 0,
      "logprobs": None
    }
  ],
  "object": "chat.completion",
  "usage": {
    "prompt_tokens": 1254,
    "completion_tokens": 45,
    "total_tokens": 1299
  },
  "created": 1721732005,
  "system_fingerprint": None,
  "model": "qwen-vl-plus",
  "id": "chatcmpl-13b925d1-ef79-9c15-b890-0079a096d7d3"
}

Python

示例代码

from dashscope import MultiModalConversation


def call_with_local_file(local_path):
    image_path = f"file://{local_path}"
    messages = [{'role': 'system',
                 'content': [{'text': 'You are a helpful assistant.'}]}, 
                 {'role':'user',
                  'content': [{'image': image_path},
                              {'text': '这是什么'}]}]
    response = MultiModalConversation.call(model='qwen-vl-plus', messages=messages)
    print(response)


if __name__ == '__main__':
    call_with_local_file("test.png")

返回结果

{
  "status_code": 200,
  "request_id": "65061d9a-d4d9-9d31-9caa-d1c5d9eb3d54",
  "code": "",
  "message": "",
  "output": {
    "text": null,
    "finish_reason": null,
    "choices": [
      {
        "finish_reason": "stop",
        "message": {
          "role": "assistant",
          "content": [
            {
              "text": "这是一只在天空中飞翔的鹰。它有着广阔的翅膀，正在翱翔于云层之间。这种鸟类通常被认为是力量、自由和雄心壮志的象征，在各种文化中有重要的地位。"
            }
          ]
        }
      }
    ]
  },
  "usage": {
    "input_tokens": 1254,
    "output_tokens": 45,
    "image_tokens": 1225
  }
}

Java

示例代码

// Copyright (c) Alibaba, Inc. and its affiliates.

import java.util.Arrays;
import java.util.HashMap;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversation;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationParam;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationResult;
import com.alibaba.dashscope.common.MultiModalMessage;
import com.alibaba.dashscope.common.Role;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.exception.UploadFileException;
import com.alibaba.dashscope.utils.JsonUtils;

public class Main {
    public static void callWithLocalFile(String localPath)
            throws ApiException, NoApiKeyException, UploadFileException {
        String filePath = "file://"+localPath;
        MultiModalConversation conv = new MultiModalConversation();
        MultiModalMessage userMessage = MultiModalMessage.builder().role(Role.USER.getValue())
                .content(Arrays.asList(new HashMap<String, Object>(){{put("image", filePath);}},
                        new HashMap<String, Object>(){{put("text", "这是什么?");}})).build();
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                .model("qwen-vl-plus")
                .message(userMessage)
                .build();
        MultiModalConversationResult result = conv.call(param);
        System.out.println(JsonUtils.toJson(result));
    }

    public static void main(String[] args) {
        try {
            callWithLocalFile("test.png");
        } catch (ApiException | NoApiKeyException | UploadFileException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }
}

返回结果

{
  "requestId": "c1fde568-c7fe-951c-a7fd-0c356fe04c1d",
  "usage": {
    "input_tokens": 1255,
    "output_tokens": 38
  },
  "output": {
    "choices": [
      {
        "finish_reason": "stop",
        "message": {
          "role": "assistant",
          "content": [
            {
              "text": "这是一只在天空中飞翔的鹰。它有着广阔的翅膀，正在翱翔于云层之间。这种景象常常象征着自由、力量和勇气等正面意义。"
            }
          ]
        }
      }
    ]
  }
}

Python

示例代码

from openai import OpenAI
import os


def get_response():
    client = OpenAI(
        api_key=os.getenv("DASHSCOPE_API_KEY"),
        base_url="https://dashscope.aliyuncs.com/compatible-mode/v1"
    )
    messages=[
        {
            "role": "user",
            "content": [
            {
                "type": "image_url",
                "image_url": {
                "url": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"
                }
            },
            {
                "type": "text",
                "text": "这是什么"
            }
            ]
        }
        ]
    completion = client.chat.completions.create(
        model="qwen-vl-plus",
        messages=messages,
        )
    print(f"模型第一轮输出：\n{completion.model_dump()}")
    assistant_message = completion.choices[0].message
    messages.append(assistant_message.model_dump())
    messages.append({
            "role": "user",
            "content": [
            {
                "type": "text",
                "text": "做一首诗描述这个场景"
            }
            ]
        })
    completion = client.chat.completions.create(
        model="qwen-vl-plus",
        messages=messages,
        )
    print(f"模型第二轮输出：\n{completion.model_dump()}")

if __name__=='__main__':
    get_response()

返回结果

模型第一轮输出：
{
  "id": "chatcmpl-afcdac19-9bbf-942b-91ad-04252fe1722c",
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "logprobs": None,
      "message": {
        "content": "图中是一名女子和她的狗在沙滩上互动。狗狗坐在地上，伸出爪子像是要握手或者击掌的样子。这名女士穿着格子衬衫，似乎正在与狗狗进行亲密的接触，并且面带微笑。背景是海洋和日出或日落时分的天空。这是一幅描绘人与宠物之间温馨时刻的画面。",
        "role": "assistant",
        "function_call": None,
        "tool_calls": None
      }
    }
  ],
  "created": 1721820065,
  "model": "qwen-vl-plus",
  "object": "chat.completion",
  "service_tier": None,
  "system_fingerprint": None,
  "usage": {
    "completion_tokens": 75,
    "prompt_tokens": 1276,
    "total_tokens": 1351
  }
}
模型第二轮输出：
{
  "id": "chatcmpl-3090adc4-91da-95d9-8482-49240d47099a",
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "logprobs": None,
      "message": {
        "content": "朝阳照海涛，\n沙岸女伴犬。\n欢笑共此时，\n友情深似海。\n\n手握同游步，\n默契心间留。\n潮起潮又落，\n此景久难忘。",
        "role": "assistant",
        "function_call": None,
        "tool_calls": None
      }
    }
  ],
  "created": 1721820068,
  "model": "qwen-vl-plus",
  "object": "chat.completion",
  "service_tier": None,
  "system_fingerprint": None,
  "usage": {
    "completion_tokens": 44,
    "prompt_tokens": 1366,
    "total_tokens": 1410
  }
}

curl

示例代码

curl -X POST https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
  "model": "qwen-vl-max",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "image_url",
          "image_url": {
            "url": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"
          }
        },
        {
          "type": "text",
          "text": "这是什么"
        }
      ]
    },
    {
      "role": "assistant",
      "content": [
        {
          "type": "text",
          "text": "这是一个女孩和一只狗。"
        }
      ]
    },
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "写一首七言绝句描述这个场景"
        }
      ]
    }
  ]
}'

返回结果

{
    "choices": [
        {
            "message": {
                "content": "海风轻拂笑颜开，  \n沙滩上与犬相陪。  \n夕阳斜照人影短，  \n欢乐时光心自醉。",
                "role": "assistant"
            },
            "finish_reason": "stop",
            "index": 0,
            "logprobs": null
        }
    ],
    "object": "chat.completion",
    "usage": {
        "prompt_tokens": 1295,
        "completion_tokens": 32,
        "total_tokens": 1327
    },
    "created": 1726324976,
    "system_fingerprint": null,
    "model": "qwen-vl-max",
    "id": "chatcmpl-3c953977-6107-96c5-9a13-c01e328b24ca"
}

Python

示例代码

from dashscope import MultiModalConversation


def conversation_call():
    messages = [
        {
            "role": "user",
            "content": [
                {"image": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"},
                {"text": "这是什么?"},
            ]
        }
    ]
    response = MultiModalConversation.call(
        model='qwen-vl-plus',
        messages=messages
        )
    print(f"模型第一轮输出：{response}")
    messages.append(response['output']['choices'][0]['message'])
    user_msg = {
                "role": "user",
                "content": [
                    {
                    "text": "做一首诗描述这个场景"
                    }
                ]
                }
    messages.append(user_msg)
    response = MultiModalConversation.call(
        model='qwen-vl-plus',
        messages=messages
        )
    print(f"模型第二轮输出：{response}")

if __name__ == '__main__':
    conversation_call()

返回结果

模型第一轮输出：
{
  "status_code": 200,
  "request_id": "0468708b-85fb-95d8-a502-bb9098b31b37",
  "code": "",
  "message": "",
  "output": {
    "text": null,
    "finish_reason": null,
    "choices": [
      {
        "finish_reason": "stop",
        "message": {
          "role": "assistant",
          "content": [
            {
              "text": "这张图片显示了一位女士和她的狗在海滩上。她们似乎正在享受彼此的陪伴，狗狗坐在沙滩上伸出爪子与女士握手或互动。背景是美丽的日落景色，海浪轻轻拍打着海岸线。\n\n请注意，我提供的描述基于图像中可见的内容，并不包括任何超出视觉信息之外的信息。如果您需要更多关于这个场景的具体细节，请告诉我！"
            }
          ]
        }
      }
    ]
  },
  "usage": {
    "input_tokens": 1277,
    "output_tokens": 81,
    "image_tokens": 1247
  }
}
模型第二轮输出：
{
  "status_code": 200,
  "request_id": "8f236443-7b01-9bad-87be-abff5d3887de",
  "code": "",
  "message": "",
  "output": {
    "text": null,
    "finish_reason": null,
    "choices": [
      {
        "finish_reason": "stop",
        "message": {
          "role": "assistant",
          "content": [
            {
              "text": "夕阳染红了天边，\n波涛轻抚着沙岸。\n人犬共坐此情深，\n\n手握着手心相牵。\n欢笑回荡于风间，\n这一刻永恒不变。\n爱意如潮水般涌动，\n在这片金色的大地上蔓延。"
            }
          ]
        }
      }
    ]
  },
  "usage": {
    "input_tokens": 1373,
    "output_tokens": 59,
    "image_tokens": 1247
  }
}

Java

示例代码

// Copyright (c) Alibaba, Inc. and its affiliates.

import java.util.ArrayList;
import java.util.Arrays;
import java.util.Collections;
import java.util.List;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversation;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationParam;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationResult;
import com.alibaba.dashscope.common.MultiModalMessage;
import com.alibaba.dashscope.common.Role;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.exception.UploadFileException;
import com.alibaba.dashscope.utils.JsonUtils;
public class Main {
    private static final String modelName = "qwen-vl-plus";
    public static void MultiRoundConversationCall() throws ApiException, NoApiKeyException, UploadFileException {
        MultiModalConversation conv = new MultiModalConversation();
        MultiModalMessage systemMessage = MultiModalMessage.builder().role(Role.SYSTEM.getValue())
                .content(Arrays.asList(Collections.singletonMap("text", "You are a helpful assistant."))).build();
        MultiModalMessage userMessage = MultiModalMessage.builder().role(Role.USER.getValue())
                .content(Arrays.asList(Collections.singletonMap("image", "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"),
                        Collections.singletonMap("text", "这是什么?"))).build();
        List<MultiModalMessage> messages = new ArrayList<>();
        messages.add(systemMessage);
        messages.add(userMessage);
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                .model(modelName)
                .messages(messages)
                .build();
        MultiModalConversationResult result = conv.call(param);
        System.out.println(JsonUtils.toJson(result));
        // add the result to conversation
        messages.add(result.getOutput().getChoices().get(0).getMessage());
        MultiModalMessage msg = MultiModalMessage.builder().role(Role.USER.getValue())
                .content(Arrays.asList(Collections.singletonMap("text", "做一首诗描述这个场景"))).build();
        messages.add(msg);
        // new messages
        param.setMessages((List)messages);
        result = conv.call(param);
        System.out.println(JsonUtils.toJson(result));
    }

    public static void main(String[] args) {
        try {
            MultiRoundConversationCall();
        } catch (ApiException | NoApiKeyException | UploadFileException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }
}

返回结果

{
  "requestId": "1239e1de-dbd3-9b46-b508-421023ed3053",
  "usage": {
    "input_tokens": 1277,
    "output_tokens": 81
  },
  "output": {
    "choices": [
      {
        "finish_reason": "stop",
        "message": {
          "role": "assistant",
          "content": [
            {
              "text": "这张图片显示了一位女士和她的狗在海滩上。她们似乎正在享受彼此的陪伴，狗狗坐在沙滩上伸出爪子与女士握手或互动。背景是美丽的日落景色，海浪轻轻拍打着海岸线。\n\n请注意，我提供的描述基于图像中可见的内容，并不包括任何超出视觉信息之外的信息。如果您需要更多关于这个场景的具体细节，请告诉我！"
            }
          ]
        }
      }
    ]
  }
}
{
  "requestId": "045fe96f-26c4-9cfd-b0ad-ec5f1f4033ce",
  "usage": {
    "input_tokens": 1373,
    "output_tokens": 59
  },
  "output": {
    "choices": [
      {
        "finish_reason": "stop",
        "message": {
          "role": "assistant",
          "content": [
            {
              "text": "夕阳染红了天边，\n波涛轻抚着沙岸。\n人犬共坐此情深，\n\n手握着手心相牵。\n欢笑回荡于风间，\n这一刻永恒不变。\n爱意如潮水般涌动，\n在这片金色的大地上蔓延。"
            }
          ]
        }
      }
    ]
  }
}

curl

curl -X POST https://dashscope.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
    "model": "qwen-vl-max",
    "input":{
        "messages":[
            {
                "role": "user",
                "content": [
                    {"image": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"},
                    {"text": "这是什么?"}
                ]
            },
            {
                "role": "assistant",
                "content": [
                    {"text": "这是一只狗和一只女孩。"}
                ]
            },
            {
                "role": "user",
                "content": [
                    {"text": "写一首七言绝句描述这个场景"}
                ]
            }
        ]
    }
}'

{
    "output": {
        "choices": [
            {
                "finish_reason": "stop",
                "message": {
                    "role": "assistant",
                    "content": [
                        {
                            "text": "海浪轻拍沙滩边，女孩与狗同嬉戏。阳光洒落笑颜开，快乐时光永铭记。"
                        }
                    ]
                }
            }
        ]
    },
    "usage": {
        "output_tokens": 27,
        "input_tokens": 1298,
        "image_tokens": 1247
    },
    "request_id": "bdf5ef59-c92e-92a6-9d69-a738ecee1590"
}

Python

示例代码

from openai import OpenAI
import os


def get_response():
    client = OpenAI(
        api_key=os.getenv("DASHSCOPE_API_KEY"),
        base_url="https://dashscope.aliyuncs.com/compatible-mode/v1",
    )
    completion = client.chat.completions.create(
        model="qwen-vl-plus",
        messages=[
            {
              "role": "user",
              "content": [
                {
                  "type": "image_url",
                  "image_url": {
                    "url": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"
                  }
                },
                {
                  "type": "text",
                  "text": "这是什么"
                }
              ]
            }
          ],
        stream=True,
        stream_options={"include_usage":True}
        )
    for chunk in completion:
        print(chunk.model_dump())

if __name__=='__main__':
    get_response()

返回结果

{'id': 'chatcmpl-6cf91cc7-1121-9977-b4bc-5e7d1fbfd693', 'choices': [{'delta': {'content': '', 'function_call': None, 'role': 'assistant', 'tool_calls': None}, 'finish_reason': None, 'index': 0, 'logprobs': None}], 'created': 1721823365, 'model': 'qwen-vl-plus', 'object': 'chat.completion.chunk', 'service_tier': None, 'system_fingerprint': None, 'usage': None}
{'id': 'chatcmpl-6cf91cc7-1121-9977-b4bc-5e7d1fbfd693', 'choices': [{'delta': {'content': '图', 'function_call': None, 'role': None, 'tool_calls': None}, 'finish_reason': None, 'index': 0, 'logprobs': None}], 'created': 1721823365, 'model': 'qwen-vl-plus', 'object': 'chat.completion.chunk', 'service_tier': None, 'system_fingerprint': None, 'usage': None}
{'id': 'chatcmpl-6cf91cc7-1121-9977-b4bc-5e7d1fbfd693', 'choices': [{'delta': {'content': '中', 'function_call': None, 'role': None, 'tool_calls': None}, 'finish_reason': None, 'index': 0, 'logprobs': None}], 'created': 1721823365, 'model': 'qwen-vl-plus', 'object': 'chat.completion.chunk', 'service_tier': None, 'system_fingerprint': None, 'usage': None}
{'id': 'chatcmpl-6cf91cc7-1121-9977-b4bc-5e7d1fbfd693', 'choices': [{'delta': {'content': '是一名', 'function_call': None, 'role': None, 'tool_calls': None}, 'finish_reason': None, 'index': 0, 'logprobs': None}], 'created': 1721823365, 'model': 'qwen-vl-plus', 'object': 'chat.completion.chunk', 'service_tier': None, 'system_fingerprint': None, 'usage': None}
{'id': 'chatcmpl-6cf91cc7-1121-9977-b4bc-5e7d1fbfd693', 'choices': [{'delta': {'content': '女子和她的狗在', 'function_call': None, 'role': None, 'tool_calls': None}, 'finish_reason': None, 'index': 0, 'logprobs': None}], 'created': 1721823365, 'model': 'qwen-vl-plus', 'object': 'chat.completion.chunk', 'service_tier': None, 'system_fingerprint': None, 'usage': None}
{'id': 'chatcmpl-6cf91cc7-1121-9977-b4bc-5e7d1fbfd693', 'choices': [{'delta': {'content': '沙滩上互动。狗狗坐在地上，', 'function_call': None, 'role': None, 'tool_calls': None}, 'finish_reason': None, 'index': 0, 'logprobs': None}], 'created': 1721823365, 'model': 'qwen-vl-plus', 'object': 'chat.completion.chunk', 'service_tier': None, 'system_fingerprint': None, 'usage': None}
{'id': 'chatcmpl-6cf91cc7-1121-9977-b4bc-5e7d1fbfd693', 'choices': [{'delta': {'content': '伸出爪子像是要握手或者击', 'function_call': None, 'role': None, 'tool_calls': None}, 'finish_reason': None, 'index': 0, 'logprobs': None}], 'created': 1721823365, 'model': 'qwen-vl-plus', 'object': 'chat.completion.chunk', 'service_tier': None, 'system_fingerprint': None, 'usage': None}
{'id': 'chatcmpl-6cf91cc7-1121-9977-b4bc-5e7d1fbfd693', 'choices': [{'delta': {'content': '掌的样子。这名女士穿着格子', 'function_call': None, 'role': None, 'tool_calls': None}, 'finish_reason': None, 'index': 0, 'logprobs': None}], 'created': 1721823365, 'model': 'qwen-vl-plus', 'object': 'chat.completion.chunk', 'service_tier': None, 'system_fingerprint': None, 'usage': None}
{'id': 'chatcmpl-6cf91cc7-1121-9977-b4bc-5e7d1fbfd693', 'choices': [{'delta': {'content': '衬衫，似乎正在与狗狗进行亲密', 'function_call': None, 'role': None, 'tool_calls': None}, 'finish_reason': None, 'index': 0, 'logprobs': None}], 'created': 1721823365, 'model': 'qwen-vl-plus', 'object': 'chat.completion.chunk', 'service_tier': None, 'system_fingerprint': None, 'usage': None}
{'id': 'chatcmpl-6cf91cc7-1121-9977-b4bc-5e7d1fbfd693', 'choices': [{'delta': {'content': '的接触，并且面带微笑。', 'function_call': None, 'role': None, 'tool_calls': None}, 'finish_reason': None, 'index': 0, 'logprobs': None}], 'created': 1721823365, 'model': 'qwen-vl-plus', 'object': 'chat.completion.chunk', 'service_tier': None, 'system_fingerprint': None, 'usage': None}
{'id': 'chatcmpl-6cf91cc7-1121-9977-b4bc-5e7d1fbfd693', 'choices': [{'delta': {'content': '背景是海洋和日出或日', 'function_call': None, 'role': None, 'tool_calls': None}, 'finish_reason': None, 'index': 0, 'logprobs': None}], 'created': 1721823365, 'model': 'qwen-vl-plus', 'object': 'chat.completion.chunk', 'service_tier': None, 'system_fingerprint': None, 'usage': None}
{'id': 'chatcmpl-6cf91cc7-1121-9977-b4bc-5e7d1fbfd693', 'choices': [{'delta': {'content': '落时分的天空。这是一', 'function_call': None, 'role': None, 'tool_calls': None}, 'finish_reason': None, 'index': 0, 'logprobs': None}], 'created': 1721823365, 'model': 'qwen-vl-plus', 'object': 'chat.completion.chunk', 'service_tier': None, 'system_fingerprint': None, 'usage': None}
{'id': 'chatcmpl-6cf91cc7-1121-9977-b4bc-5e7d1fbfd693', 'choices': [{'delta': {'content': '幅描绘人与宠物之间温馨时刻', 'function_call': None, 'role': None, 'tool_calls': None}, 'finish_reason': None, 'index': 0, 'logprobs': None}], 'created': 1721823365, 'model': 'qwen-vl-plus', 'object': 'chat.completion.chunk', 'service_tier': None, 'system_fingerprint': None, 'usage': None}
{'id': 'chatcmpl-6cf91cc7-1121-9977-b4bc-5e7d1fbfd693', 'choices': [{'delta': {'content': '的画面。', 'function_call': None, 'role': None, 'tool_calls': None}, 'finish_reason': 'stop', 'index': 0, 'logprobs': None}], 'created': 1721823365, 'model': 'qwen-vl-plus', 'object': 'chat.completion.chunk', 'service_tier': None, 'system_fingerprint': None, 'usage': None}
{'id': 'chatcmpl-6cf91cc7-1121-9977-b4bc-5e7d1fbfd693', 'choices': [], 'created': 1721823365, 'model': 'qwen-vl-plus', 'object': 'chat.completion.chunk', 'service_tier': None, 'system_fingerprint': None, 'usage': {'completion_tokens': 75, 'prompt_tokens': 1276, 'total_tokens': 1351}}

curl

示例代码

curl --location 'https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
    "model": "qwen-vl-plus",
    "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "image_url",
          "image_url": {
            "url": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"
          }
        },
        {
          "type": "text",
          "text": "这是什么"
        }
      ]
    }
  ],
    "stream":true,
    "stream_options":{"include_usage":true}
}'

返回结果

data: {"choices":[{"delta":{"content":"","role":"assistant"},"index":0,"logprobs":null,"finish_reason":null}],"object":"chat.completion.chunk","usage":null,"created":1721823635,"system_fingerprint":null,"model":"qwen-vl-plus","id":"chatcmpl-9a9ec75a-3109-9910-b79e-7bcbce81c8f9"}

data: {"choices":[{"finish_reason":null,"delta":{"content":"图"},"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1721823635,"system_fingerprint":null,"model":"qwen-vl-plus","id":"chatcmpl-9a9ec75a-3109-9910-b79e-7bcbce81c8f9"}

data: {"choices":[{"delta":{"content":"中"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1721823635,"system_fingerprint":null,"model":"qwen-vl-plus","id":"chatcmpl-9a9ec75a-3109-9910-b79e-7bcbce81c8f9"}

data: {"choices":[{"delta":{"content":"是一名"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1721823635,"system_fingerprint":null,"model":"qwen-vl-plus","id":"chatcmpl-9a9ec75a-3109-9910-b79e-7bcbce81c8f9"}

data: {"choices":[{"delta":{"content":"女子和她的狗在"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1721823635,"system_fingerprint":null,"model":"qwen-vl-plus","id":"chatcmpl-9a9ec75a-3109-9910-b79e-7bcbce81c8f9"}

data: {"choices":[{"delta":{"content":"沙滩上互动。狗狗坐在地上，"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1721823635,"system_fingerprint":null,"model":"qwen-vl-plus","id":"chatcmpl-9a9ec75a-3109-9910-b79e-7bcbce81c8f9"}

data: {"choices":[{"delta":{"content":"伸出爪子像是要握手或者击"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1721823635,"system_fingerprint":null,"model":"qwen-vl-plus","id":"chatcmpl-9a9ec75a-3109-9910-b79e-7bcbce81c8f9"}

data: {"choices":[{"delta":{"content":"掌的样子。这名女士穿着格子"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1721823635,"system_fingerprint":null,"model":"qwen-vl-plus","id":"chatcmpl-9a9ec75a-3109-9910-b79e-7bcbce81c8f9"}

data: {"choices":[{"delta":{"content":"衬衫，似乎正在与狗狗进行亲密"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1721823635,"system_fingerprint":null,"model":"qwen-vl-plus","id":"chatcmpl-9a9ec75a-3109-9910-b79e-7bcbce81c8f9"}

data: {"choices":[{"delta":{"content":"的接触，并且面带微笑。"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1721823635,"system_fingerprint":null,"model":"qwen-vl-plus","id":"chatcmpl-9a9ec75a-3109-9910-b79e-7bcbce81c8f9"}

data: {"choices":[{"delta":{"content":"他们背后的海浪拍打着海岸线"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1721823635,"system_fingerprint":null,"model":"qwen-vl-plus","id":"chatcmpl-9a9ec75a-3109-9910-b79e-7bcbce81c8f9"}

data: {"choices":[{"delta":{"content":"，天空看起来很明亮但有些模糊"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1721823635,"system_fingerprint":null,"model":"qwen-vl-plus","id":"chatcmpl-9a9ec75a-3109-9910-b79e-7bcbce81c8f9"}

data: {"choices":[{"delta":{"content":"，可能是日出或日落时"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1721823635,"system_fingerprint":null,"model":"qwen-vl-plus","id":"chatcmpl-9a9ec75a-3109-9910-b79e-7bcbce81c8f9"}

data: {"choices":[{"delta":{"content":"分拍摄的照片。整体氛围显得非常"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1721823635,"system_fingerprint":null,"model":"qwen-vl-plus","id":"chatcmpl-9a9ec75a-3109-9910-b79e-7bcbce81c8f9"}

data: {"choices":[{"finish_reason":"stop","delta":{"content":"和谐而温馨。"},"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1721823635,"system_fingerprint":null,"model":"qwen-vl-plus","id":"chatcmpl-9a9ec75a-3109-9910-b79e-7bcbce81c8f9"}

data: {"choices":[],"object":"chat.completion.chunk","usage":{"prompt_tokens":1276,"completion_tokens":85,"total_tokens":1361},"created":1721823635,"system_fingerprint":null,"model":"qwen-vl-plus","id":"chatcmpl-9a9ec75a-3109-9910-b79e-7bcbce81c8f9"}

data: [DONE]

Python

示例代码

from dashscope import MultiModalConversation


def simple_multimodal_conversation_call():
    """Simple single round multimodal conversation call.
    """
    messages = [
        {
            "role": "user",
            "content": [
                {"image": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"},
                {"text": "这是什么?"}
            ]
        }
    ]
    responses = MultiModalConversation.call(model='qwen-vl-plus',
                                           messages=messages,
                                           stream=True)
    for response in responses:
        print(response)


if __name__ == '__main__':
    simple_multimodal_conversation_call()

返回结果

{"status_code": 200, "request_id": "9a752a53-00b4-9241-a61d-bed94f55bd21", "code": "", "message": "", "output": {"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": [{"text": "这张"}]}}]}, "usage": {"input_tokens": 1277, "output_tokens": 1, "image_tokens": 1247}}
{"status_code": 200, "request_id": "9a752a53-00b4-9241-a61d-bed94f55bd21", "code": "", "message": "", "output": {"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": [{"text": "这张图片"}]}}]}, "usage": {"input_tokens": 1277, "output_tokens": 2, "image_tokens": 1247}}
{"status_code": 200, "request_id": "9a752a53-00b4-9241-a61d-bed94f55bd21", "code": "", "message": "", "output": {"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": [{"text": "这张图片显示"}]}}]}, "usage": {"input_tokens": 1277, "output_tokens": 3, "image_tokens": 1247}}
{"status_code": 200, "request_id": "9a752a53-00b4-9241-a61d-bed94f55bd21", "code": "", "message": "", "output": {"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": [{"text": "这张图片显示了一位女士和她的"}]}}]}, "usage": {"input_tokens": 1277, "output_tokens": 8, "image_tokens": 1247}}
{"status_code": 200, "request_id": "9a752a53-00b4-9241-a61d-bed94f55bd21", "code": "", "message": "", "output": {"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": [{"text": "这张图片显示了一位女士和她的狗在海滩上。她们似乎正在"}]}}]}, "usage": {"input_tokens": 1277, "output_tokens": 16, "image_tokens": 1247}}
{"status_code": 200, "request_id": "9a752a53-00b4-9241-a61d-bed94f55bd21", "code": "", "message": "", "output": {"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": [{"text": "这张图片显示了一位女士和她的狗在海滩上。她们似乎正在享受彼此的陪伴，狗狗坐在沙滩"}]}}]}, "usage": {"input_tokens": 1277, "output_tokens": 24, "image_tokens": 1247}}
{"status_code": 200, "request_id": "9a752a53-00b4-9241-a61d-bed94f55bd21", "code": "", "message": "", "output": {"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": [{"text": "这张图片显示了一位女士和她的狗在海滩上。她们似乎正在享受彼此的陪伴，狗狗坐在沙滩上伸出爪子与女士握手或"}]}}]}, "usage": {"input_tokens": 1277, "output_tokens": 32, "image_tokens": 1247}}
{"status_code": 200, "request_id": "9a752a53-00b4-9241-a61d-bed94f55bd21", "code": "", "message": "", "output": {"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": [{"text": "这张图片显示了一位女士和她的狗在海滩上。她们似乎正在享受彼此的陪伴，狗狗坐在沙滩上伸出爪子与女士握手或互动。背景是美丽的日落景色"}]}}]}, "usage": {"input_tokens": 1277, "output_tokens": 40, "image_tokens": 1247}}
{"status_code": 200, "request_id": "9a752a53-00b4-9241-a61d-bed94f55bd21", "code": "", "message": "", "output": {"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": [{"text": "这张图片显示了一位女士和她的狗在海滩上。她们似乎正在享受彼此的陪伴，狗狗坐在沙滩上伸出爪子与女士握手或互动。背景是美丽的日落景色，海浪轻轻拍打着海岸线"}]}}]}, "usage": {"input_tokens": 1277, "output_tokens": 48, "image_tokens": 1247}}
{"status_code": 200, "request_id": "9a752a53-00b4-9241-a61d-bed94f55bd21", "code": "", "message": "", "output": {"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": [{"text": "这张图片显示了一位女士和她的狗在海滩上。她们似乎正在享受彼此的陪伴，狗狗坐在沙滩上伸出爪子与女士握手或互动。背景是美丽的日落景色，海浪轻轻拍打着海岸线。\n\n请注意，这个描述基于图像中"}]}}]}, "usage": {"input_tokens": 1277, "output_tokens": 56, "image_tokens": 1247}}
{"status_code": 200, "request_id": "9a752a53-00b4-9241-a61d-bed94f55bd21", "code": "", "message": "", "output": {"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": [{"text": "这张图片显示了一位女士和她的狗在海滩上。她们似乎正在享受彼此的陪伴，狗狗坐在沙滩上伸出爪子与女士握手或互动。背景是美丽的日落景色，海浪轻轻拍打着海岸线。\n\n请注意，这个描述基于图像中可见的内容，并不包括任何超出视觉"}]}}]}, "usage": {"input_tokens": 1277, "output_tokens": 64, "image_tokens": 1247}}
{"status_code": 200, "request_id": "9a752a53-00b4-9241-a61d-bed94f55bd21", "code": "", "message": "", "output": {"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": [{"text": "这张图片显示了一位女士和她的狗在海滩上。她们似乎正在享受彼此的陪伴，狗狗坐在沙滩上伸出爪子与女士握手或互动。背景是美丽的日落景色，海浪轻轻拍打着海岸线。\n\n请注意，这个描述基于图像中可见的内容，并不包括任何超出视觉信息之外的推测性解释。如果您"}]}}]}, "usage": {"input_tokens": 1277, "output_tokens": 72, "image_tokens": 1247}}
{"status_code": 200, "request_id": "9a752a53-00b4-9241-a61d-bed94f55bd21", "code": "", "message": "", "output": {"text": null, "finish_reason": null, "choices": [{"finish_reason": "stop", "message": {"role": "assistant", "content": [{"text": "这张图片显示了一位女士和她的狗在海滩上。她们似乎正在享受彼此的陪伴，狗狗坐在沙滩上伸出爪子与女士握手或互动。背景是美丽的日落景色，海浪轻轻拍打着海岸线。\n\n请注意，这个描述基于图像中可见的内容，并不包括任何超出视觉信息之外的推测性解释。如果您需要更多关于场景的信息，请告诉我！"}]}}]}, "usage": {"input_tokens": 1277, "output_tokens": 80, "image_tokens": 1247}}

Java

示例代码

// Copyright (c) Alibaba, Inc. and its affiliates.

import java.util.Arrays;
import java.util.HashMap;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversation;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationParam;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationResult;
import com.alibaba.dashscope.common.MultiModalMessage;
import com.alibaba.dashscope.common.Role;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.exception.UploadFileException;
import io.reactivex.Flowable;

public class Main {
    public static void streamCall()
            throws ApiException, NoApiKeyException, UploadFileException {
        MultiModalConversation conv = new MultiModalConversation();
        // must create mutable map.
        MultiModalMessage userMessage = MultiModalMessage.builder().role(Role.USER.getValue())
                .content(Arrays.asList(new HashMap<String, Object>(){{put("image", "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg");}},
                        new HashMap<String, Object>(){{put("text", "这是什么");}})).build();
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                .model("qwen-vl-plus")
                .message(userMessage)
                .build();
        Flowable<MultiModalConversationResult> result = conv.streamCall(param);
        result.blockingForEach(item -> {
            System.out.println(item);
        });
    }

    public static void main(String[] args) {
        try {
            streamCall();
        } catch (ApiException | NoApiKeyException | UploadFileException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }
}

返回结果

MultiModalConversationResult(requestId=ea2bdb31-604e-9237-a55c-9e3230a10962, usage=MultiModalConversationUsage(inputTokens=1276, outputTokens=1), output=MultiModalConversationOutput(choices=[MultiModalConversationOutput.Choice(finishReason=null, message=MultiModalMessage(role=assistant, content=[{text=图}]))]))
MultiModalConversationResult(requestId=ea2bdb31-604e-9237-a55c-9e3230a10962, usage=MultiModalConversationUsage(inputTokens=1276, outputTokens=2), output=MultiModalConversationOutput(choices=[MultiModalConversationOutput.Choice(finishReason=null, message=MultiModalMessage(role=assistant, content=[{text=图中}]))]))
MultiModalConversationResult(requestId=ea2bdb31-604e-9237-a55c-9e3230a10962, usage=MultiModalConversationUsage(inputTokens=1276, outputTokens=3), output=MultiModalConversationOutput(choices=[MultiModalConversationOutput.Choice(finishReason=null, message=MultiModalMessage(role=assistant, content=[{text=图中是一名}]))]))
MultiModalConversationResult(requestId=ea2bdb31-604e-9237-a55c-9e3230a10962, usage=MultiModalConversationUsage(inputTokens=1276, outputTokens=8), output=MultiModalConversationOutput(choices=[MultiModalConversationOutput.Choice(finishReason=null, message=MultiModalMessage(role=assistant, content=[{text=图中是一名女子和她的狗在}]))]))
MultiModalConversationResult(requestId=ea2bdb31-604e-9237-a55c-9e3230a10962, usage=MultiModalConversationUsage(inputTokens=1276, outputTokens=16), output=MultiModalConversationOutput(choices=[MultiModalConversationOutput.Choice(finishReason=null, message=MultiModalMessage(role=assistant, content=[{text=图中是一名女子和她的狗在沙滩上互动。狗狗坐在地上，}]))]))
MultiModalConversationResult(requestId=ea2bdb31-604e-9237-a55c-9e3230a10962, usage=MultiModalConversationUsage(inputTokens=1276, outputTokens=24), output=MultiModalConversationOutput(choices=[MultiModalConversationOutput.Choice(finishReason=null, message=MultiModalMessage(role=assistant, content=[{text=图中是一名女子和她的狗在沙滩上互动。狗狗坐在地上，伸出爪子像是要握手或者击}]))]))
MultiModalConversationResult(requestId=ea2bdb31-604e-9237-a55c-9e3230a10962, usage=MultiModalConversationUsage(inputTokens=1276, outputTokens=32), output=MultiModalConversationOutput(choices=[MultiModalConversationOutput.Choice(finishReason=null, message=MultiModalMessage(role=assistant, content=[{text=图中是一名女子和她的狗在沙滩上互动。狗狗坐在地上，伸出爪子像是要握手或者击掌的样子。这名女士穿着格子}]))]))
MultiModalConversationResult(requestId=ea2bdb31-604e-9237-a55c-9e3230a10962, usage=MultiModalConversationUsage(inputTokens=1276, outputTokens=40), output=MultiModalConversationOutput(choices=[MultiModalConversationOutput.Choice(finishReason=null, message=MultiModalMessage(role=assistant, content=[{text=图中是一名女子和她的狗在沙滩上互动。狗狗坐在地上，伸出爪子像是要握手或者击掌的样子。这名女士穿着格子衬衫，似乎正在与狗狗进行亲密}]))]))
MultiModalConversationResult(requestId=ea2bdb31-604e-9237-a55c-9e3230a10962, usage=MultiModalConversationUsage(inputTokens=1276, outputTokens=48), output=MultiModalConversationOutput(choices=[MultiModalConversationOutput.Choice(finishReason=null, message=MultiModalMessage(role=assistant, content=[{text=图中是一名女子和她的狗在沙滩上互动。狗狗坐在地上，伸出爪子像是要握手或者击掌的样子。这名女士穿着格子衬衫，似乎正在与狗狗进行亲密的接触，并且面带微笑。}]))]))
MultiModalConversationResult(requestId=ea2bdb31-604e-9237-a55c-9e3230a10962, usage=MultiModalConversationUsage(inputTokens=1276, outputTokens=56), output=MultiModalConversationOutput(choices=[MultiModalConversationOutput.Choice(finishReason=null, message=MultiModalMessage(role=assistant, content=[{text=图中是一名女子和她的狗在沙滩上互动。狗狗坐在地上，伸出爪子像是要握手或者击掌的样子。这名女士穿着格子衬衫，似乎正在与狗狗进行亲密的接触，并且面带微笑。背景是海洋和日出或日}]))]))
MultiModalConversationResult(requestId=ea2bdb31-604e-9237-a55c-9e3230a10962, usage=MultiModalConversationUsage(inputTokens=1276, outputTokens=64), output=MultiModalConversationOutput(choices=[MultiModalConversationOutput.Choice(finishReason=null, message=MultiModalMessage(role=assistant, content=[{text=图中是一名女子和她的狗在沙滩上互动。狗狗坐在地上，伸出爪子像是要握手或者击掌的样子。这名女士穿着格子衬衫，似乎正在与狗狗进行亲密的接触，并且面带微笑。背景是海洋和日出或日落时分的天空。这是一}]))]))
MultiModalConversationResult(requestId=ea2bdb31-604e-9237-a55c-9e3230a10962, usage=MultiModalConversationUsage(inputTokens=1276, outputTokens=72), output=MultiModalConversationOutput(choices=[MultiModalConversationOutput.Choice(finishReason=null, message=MultiModalMessage(role=assistant, content=[{text=图中是一名女子和她的狗在沙滩上互动。狗狗坐在地上，伸出爪子像是要握手或者击掌的样子。这名女士穿着格子衬衫，似乎正在与狗狗进行亲密的接触，并且面带微笑。背景是海洋和日出或日落时分的天空。这是一张充满温馨感的照片，展现了人}]))]))
MultiModalConversationResult(requestId=ea2bdb31-604e-9237-a55c-9e3230a10962, usage=MultiModalConversationUsage(inputTokens=1276, outputTokens=79), output=MultiModalConversationOutput(choices=[MultiModalConversationOutput.Choice(finishReason=stop, message=MultiModalMessage(role=assistant, content=[{text=图中是一名女子和她的狗在沙滩上互动。狗狗坐在地上，伸出爪子像是要握手或者击掌的样子。这名女士穿着格子衬衫，似乎正在与狗狗进行亲密的接触，并且面带微笑。背景是海洋和日出或日落时分的天空。这是一张充满温馨感的照片，展现了人与宠物之间的友谊时刻。}]))]))

curl

示例代码

curl --location 'https://dashscope.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--header 'X-DashScope-SSE: enable' \
--data '{
    "model": "qwen-vl-plus",
    "input":{
        "messages":[
            {
                "role": "system",
                "content": [
                    {"text": "You are a helpful assistant."}
                ]
            },
            {
                "role": "user",
                "content": [
                    {"image": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"},
                    {"text": "这个图片是哪里？"}
                ]
            }
        ]
    },
    "parameters": {
    }
}'

返回结果

id:1
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":[{"text":"这张"}],"role":"assistant"},"finish_reason":"null"}]},"usage":{"input_tokens":1279,"output_tokens":1,"image_tokens":1247},"request_id":"ba3c3410-0234-9d56-bd6c-e923255a9695"}

id:2
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":[{"text":"这张照片"}],"role":"assistant"},"finish_reason":"null"}]},"usage":{"input_tokens":1279,"output_tokens":2,"image_tokens":1247},"request_id":"ba3c3410-0234-9d56-bd6c-e923255a9695"}

id:3
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":[{"text":"这张照片显示"}],"role":"assistant"},"finish_reason":"null"}]},"usage":{"input_tokens":1279,"output_tokens":3,"image_tokens":1247},"request_id":"ba3c3410-0234-9d56-bd6c-e923255a9695"}

id:4
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":[{"text":"这张照片显示的是一位女士和一只"}],"role":"assistant"},"finish_reason":"null"}]},"usage":{"input_tokens":1279,"output_tokens":8,"image_tokens":1247},"request_id":"ba3c3410-0234-9d56-bd6c-e923255a9695"}

id:5
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":[{"text":"这张照片显示的是一位女士和一只狗在海滩上。由于我无法"}],"role":"assistant"},"finish_reason":"null"}]},"usage":{"input_tokens":1279,"output_tokens":16,"image_tokens":1247},"request_id":"ba3c3410-0234-9d56-bd6c-e923255a9695"}

id:6
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":[{"text":"这张照片显示的是一位女士和一只狗在海滩上。由于我无法获取具体的地理位置信息，所以不能确定"}],"role":"assistant"},"finish_reason":"null"}]},"usage":{"input_tokens":1279,"output_tokens":24,"image_tokens":1247},"request_id":"ba3c3410-0234-9d56-bd6c-e923255a9695"}

id:7
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":[{"text":"这张照片显示的是一位女士和一只狗在海滩上。由于我无法获取具体的地理位置信息，所以不能确定这是哪个地方的海滩。但是从"}],"role":"assistant"},"finish_reason":"null"}]},"usage":{"input_tokens":1279,"output_tokens":32,"image_tokens":1247},"request_id":"ba3c3410-0234-9d56-bd6c-e923255a9695"}

id:8
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":[{"text":"这张照片显示的是一位女士和一只狗在海滩上。由于我无法获取具体的地理位置信息，所以不能确定这是哪个地方的海滩。但是从视觉内容来看，它可能是一个位于"}],"role":"assistant"},"finish_reason":"null"}]},"usage":{"input_tokens":1279,"output_tokens":40,"image_tokens":1247},"request_id":"ba3c3410-0234-9d56-bd6c-e923255a9695"}

id:9
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":[{"text":"这张照片显示的是一位女士和一只狗在海滩上。由于我无法获取具体的地理位置信息，所以不能确定这是哪个地方的海滩。但是从视觉内容来看，它可能是一个位于沿海地区的沙滩海岸线，并且有"}],"role":"assistant"},"finish_reason":"null"}]},"usage":{"input_tokens":1279,"output_tokens":48,"image_tokens":1247},"request_id":"ba3c3410-0234-9d56-bd6c-e923255a9695"}

id:10
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":[{"text":"这张照片显示的是一位女士和一只狗在海滩上。由于我无法获取具体的地理位置信息，所以不能确定这是哪个地方的海滩。但是从视觉内容来看，它可能是一个位于沿海地区的沙滩海岸线，并且有海浪拍打着岸边。这样的场景"}],"role":"assistant"},"finish_reason":"null"}]},"usage":{"input_tokens":1279,"output_tokens":56,"image_tokens":1247},"request_id":"ba3c3410-0234-9d56-bd6c-e923255a9695"}

id:11
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":[{"text":"这张照片显示的是一位女士和一只狗在海滩上。由于我无法获取具体的地理位置信息，所以不能确定这是哪个地方的海滩。但是从视觉内容来看，它可能是一个位于沿海地区的沙滩海岸线，并且有海浪拍打着岸边。这样的场景在全球许多美丽的海滨地区都可以找到。"}],"role":"assistant"},"finish_reason":"null"}]},"usage":{"input_tokens":1279,"output_tokens":64,"image_tokens":1247},"request_id":"ba3c3410-0234-9d56-bd6c-e923255a9695"}

id:12
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":[{"text":"这张照片显示的是一位女士和一只狗在海滩上。由于我无法获取具体的地理位置信息，所以不能确定这是哪个地方的海滩。但是从视觉内容来看，它可能是一个位于沿海地区的沙滩海岸线，并且有海浪拍打着岸边。这样的场景在全球许多美丽的海滨地区都可以找到。如果您需要更精确的信息，请提供更多的"}],"role":"assistant"},"finish_reason":"null"}]},"usage":{"input_tokens":1279,"output_tokens":72,"image_tokens":1247},"request_id":"ba3c3410-0234-9d56-bd6c-e923255a9695"}

id:13
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":[{"text":"这张照片显示的是一位女士和一只狗在海滩上。由于我无法获取具体的地理位置信息，所以不能确定这是哪个地方的海滩。但是从视觉内容来看，它可能是一个位于沿海地区的沙滩海岸线，并且有海浪拍打着岸边。这样的场景在全球许多美丽的海滨地区都可以找到。如果您需要更精确的信息，请提供更多的背景或细节描述。"}],"role":"assistant"},"finish_reason":"stop"}]},"usage":{"input_tokens":1279,"output_tokens":78,"image_tokens":1247},"request_id":"ba3c3410-0234-9d56-bd6c-e923255a9695"}