通义千问VL

import os
from openai import OpenAI

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-latest",
    messages=[
        {
            "role": "system",
            "content": [{"type": "text", "text": "You are a helpful assistant."}],
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"
                    },
                },
                {"type": "text", "text": "图中描绘的是什么景象?"},
            ],
        },
    ],
)

print(completion.choices[0].message.content)

import OpenAI from "openai";

const openai = new OpenAI({
  // 若没有配置环境变量，请用百炼API Key将下行替换为：apiKey: "sk-xxx"
  apiKey: process.env.DASHSCOPE_API_KEY,
  baseURL: "https://dashscope.aliyuncs.com/compatible-mode/v1"
});

async function main() {
  const response = await openai.chat.completions.create({
    model: "qwen-vl-max-latest",
    messages: [{
        role: "system",
        content: [{
          type: "text",
          text: "You are a helpful assistant."
        }]
      },
      {
        role: "user",
        content: [{
            type: "image_url",
            image_url: {
              "url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"
            }
          },
          {
            type: "text",
            text: "图中描绘的是什么景象?"
          }
        ]
      }
    ]
  });
  console.log(response.choices[0].message.content);
}

main()

返回结果

这是一张在海滩上拍摄的照片。照片中，一位穿着格子衬衫的女性坐在沙滩上，与一只戴着项圈的黄色拉布拉多犬互动。背景是大海和天空，阳光洒在她们身上，营造出温暖的氛围。

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":"system",
  "content":[
    {"type": "text", "text": "You are a helpful assistant."}]},
  {
    "role": "user",
    "content": [
      {"type": "image_url", "image_url": {"url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"}},
      {"type": "text", "text": "图中描绘的是什么景象?"}
    ]
  }]
}'

import os
import dashscope
messages = [
{
    "role": "system",
    "content": [
    {"text": "You are a helpful assistant."}]
},
{
    "role": "user",
    "content": [
    {"image": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"},
    {"text": "图中描绘的是什么景象?"}]
}]
response = dashscope.MultiModalConversation.call(
    #若没有配置环境变量， 请用百炼API Key将下行替换为： api_key ="sk-xxx"
    api_key = os.getenv('DASHSCOPE_API_KEY'),
    model = 'qwen-vl-max-latest',
    messages = messages
)
print(response.output.choices[0].message.content[0]["text"])

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 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://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"),
                        Collections.singletonMap("text", "图中描绘的是什么景象?"))).build();
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                 // 若没有配置环境变量，请用百炼API Key将下行替换为：.apiKey("sk-xxx")
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                .model("qwen-vl-max-latest")
                .messages(Arrays.asList(systemMessage, userMessage))
                .build();
        MultiModalConversationResult result = conv.call(param);
        System.out.println(result.getOutput().getChoices().get(0).getMessage().getContent().get(0).get("text"));
    }
    public static void main(String[] args) {
        try {
            simpleMultiModalConversationCall();
        } catch (ApiException | NoApiKeyException | UploadFileException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }
}

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-latest",
    "input":{
        "messages":[
            {"role": "system",
	     "content": [
	       {"text": "You are a helpful assistant."}]},
            {
             "role": "user",
             "content": [
               {"image": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"},
               {"text": "图中描绘的是什么景象?"}
                ]
            }
        ]
    }
}'

from openai import OpenAI
import os

client = OpenAI(
    # 若没有配置环境变量，请用百炼API Key将下行替换为：api_key="sk-xxx"
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    base_url="https://dashscope.aliyuncs.com/compatible-mode/v1"
)
messages = [
    {
        "role": "system",
        "content": [{"type": "text", "text": "You are a helpful assistant."}]},
    {
        "role": "user",
        "content": [
            {
                "type": "image_url",
                "image_url": {
                    "url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"
                },
            },
            {"type": "text", "text": "图中描绘的是什么景象？"},
        ],
    }
]
completion = client.chat.completions.create(
    model="qwen-vl-max-latest",
    messages=messages,
    )
print(f"第一轮输出：{completion.choices[0].message.content}")
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-max-latest",
    messages=messages,
    )
print(f"第二轮输出：{completion.choices[0].message.content}")

import OpenAI from "openai";

const openai = new OpenAI(
    {
        // 若没有配置环境变量，请用百炼API Key将下行替换为：apiKey: "sk-xxx",
        apiKey: process.env.DASHSCOPE_API_KEY,
        baseURL: "https://dashscope.aliyuncs.com/compatible-mode/v1"
    }
);

let messages = [
    {
	role: "system",
	content: [{"type": "text", "text": "You are a helpful assistant."}]},
    {
        role: "user",
	content: [
        { type: "image_url", image_url: { "url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg" } },
        { type: "text", text: "图中描绘的是什么景象？" },
    ]
}]
async function main() {
    let response = await openai.chat.completions.create({
        model: "qwen-vl-max-latest",
        messages: messages
    });
    console.log(`第一轮输出：${response.choices[0].message.content}`);
    messages.push(response.choices[0].message);
    messages.push({"role": "user", "content": "做一首诗描述这个场景"});
    response = await openai.chat.completions.create({
        model: "qwen-vl-max-latest",
        messages: messages
    });
    console.log(`第二轮输出：${response.choices[0].message.content}`);
}

main()

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": "system",
      "content": [{"type": "text", "text": "You are a helpful assistant."}]},
    {
      "role": "user",
      "content": [
        {
          "type": "image_url",
          "image_url": {
            "url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"
          }
        },
        {
          "type": "text",
          "text": "图中描绘的是什么景象？"
        }
      ]
    },
    {
      "role": "assistant",
      "content": [
        {
          "type": "text",
          "text": "这是一个女孩和一只狗。"
        }
      ]
    },
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "写一首诗描述这个场景"
        }
      ]
    }
  ]
}'

import os
from dashscope import MultiModalConversation

messages = [
    {
	"role": "system",
	"content": [{"text": "You are a helpful assistant."}]},
    {
        "role": "user",
        "content": [
            {
                "image": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"
            },
            {"text": "图中描绘的是什么景象？"},
        ],
    }
]
response = MultiModalConversation.call(
    # 若没有配置环境变量，请用百炼API Key将下行替换为：api_key="sk-xxx",
    api_key=os.getenv('DASHSCOPE_API_KEY'),
    model='qwen-vl-max-latest',
    messages=messages)
print(f"模型第一轮输出：{response.output.choices[0].message.content[0]['text']}")
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(
    # 若没有配置环境变量，请用百炼API Key将下行替换为：api_key="sk-xxx",
    api_key=os.getenv('DASHSCOPE_API_KEY'),
    model='qwen-vl-max-latest',
    messages=messages)
print(f"模型第二轮输出：{response.output.choices[0].message.content[0]['text']}")

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;
public class Main {
    private static final String modelName = "qwen-vl-max-latest";
    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://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"),
                        Collections.singletonMap("text", "图中描绘的是什么景象？"))).build();
        List<MultiModalMessage> messages = new ArrayList<>();
        messages.add(systemMessage);
        messages.add(userMessage);
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                // 若没有配置环境变量，请用百炼API Key将下行替换为：.apiKey("sk-xxx")
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))                
                .model(modelName)
                .messages(messages)
                .build();
        MultiModalConversationResult result = conv.call(param);
        System.out.println("第一轮输出："+result.getOutput().getChoices().get(0).getMessage().getContent().get(0).get("text"));        // 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);
        param.setMessages((List)messages);
        result = conv.call(param);
        System.out.println("第二轮输出："+result.getOutput().getChoices().get(0).getMessage().getContent().get(0).get("text"));    }

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

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-latest",
    "input":{
        "messages":[
            {
                "role": "system",
                "content": [{"text": "You are a helpful assistant."}]},
            {
                "role": "user",
                "content": [
                    {"image": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"},
                    {"text": "图中描绘的是什么景象？"}
                ]
            },
            {
                "role": "assistant",
                "content": [
                    {"text": "图中是一名女子和一只拉布拉多犬在沙滩上玩耍。"}
                ]
            },
            {
                "role": "user",
                "content": [
                    {"text": "写一首七言绝句描述这个场景"}
                ]
            }
        ]
    }
}'

返回结果

{
    "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"
}

from openai import OpenAI
import os

client = OpenAI(
    # 若没有配置环境变量，请用百炼API Key将下行替换为：api_key="sk-xxx"
    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-latest",
    messages=[
	{"role": "system",
         "content": [{"type":"text","text": "You are a helpful assistant."}]},
        {"role": "user",
         "content": [{"type": "image_url",
                    "image_url": {"url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"},},
                    {"type": "text", "text": "图中描绘的是什么景象？"}]}],
    stream=True
)
full_content = ""
print("流式输出内容为：")
for chunk in completion:
    if chunk.choices[0].delta.content is None:
        continue
    full_content += chunk.choices[0].delta.content
    print(chunk.choices[0].delta.content)
print(f"完整内容为：{full_content}")

import OpenAI from "openai";

const openai = new OpenAI(
    {
        // 若没有配置环境变量，请用百炼API Key将下行替换为：apiKey: "sk-xxx"
        apiKey: process.env.DASHSCOPE_API_KEY,
        baseURL: "https://dashscope.aliyuncs.com/compatible-mode/v1"
    }
);

const completion = await openai.chat.completions.create({
    model: "qwen-vl-max-latest",
    messages: [
        {"role": "system",
         "content": [{"type":"text","text": "You are a helpful assistant."}]},
        {"role": "user",
        "content": [{"type": "image_url",
                    "image_url": {"url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"},},
                    {"type": "text", "text": "图中描绘的是什么景象？"}]}],
    stream: true,
});

let fullContent = ""
console.log("流式输出内容为：")
for await (const chunk of completion) {
    if (chunk.choices[0].delta.content != null) {
      fullContent += chunk.choices[0].delta.content;
      console.log(chunk.choices[0].delta.content);
    }
}
console.log(`完整输出内容为：${fullContent}`)

返回结果

流式输出内容为：

图中描绘的是
一个女人和一只
狗在海滩上
互动的景象。
......
在她们身上，
营造出温暖和谐
的氛围。
完整内容为：图中描绘的是一个女人和一只狗在海滩上互动的景象。女人穿着格子衬衫，坐在沙滩上，微笑着与狗握手。狗戴着项圈，看起来很开心。背景是大海和天空，阳光洒在她们身上，营造出温暖和谐的氛围。

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-latest",
    "messages": [
   {
      "role": "system",
      "content": [{"type":"text","text": "You are a helpful assistant."}]},
    {
      "role": "user",
      "content": [
        {
          "type": "image_url",
          "image_url": {
            "url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"
          }
        },
        {
          "type": "text",
          "text": "图中描绘的是什么景象？"
        }
      ]
    }
  ],
    "stream":true,
    "stream_options":{"include_usage":true}
}'

import os
from dashscope import MultiModalConversation

messages = [
    {
    "role": "system",
    "content": [{"text": "You are a helpful assistant."}]},
    {
        "role": "user",
        "content": [
            {"image": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"},
            {"text": "图中描绘的是什么景象?"}
        ]
    }
]
responses = MultiModalConversation.call(
    # 若没有配置环境变量，请用百炼API Key将下行替换为：api_key="sk-xxx"
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    model='qwen-vl-max-latest',
    messages=messages,
    stream=True,
    incremental_output=True
    )
full_content = ""
print("流式输出内容为：")
for response in responses:
    try:
        print(response["output"]["choices"][0]["message"].content[0]["text"])
        full_content += response["output"]["choices"][0]["message"].content[0]["text"]
    except:
        pass
print(f"完整内容为：{full_content}")

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 io.reactivex.Flowable;

public class Main {
    public static void streamCall()
            throws ApiException, NoApiKeyException, UploadFileException {
        MultiModalConversation conv = new MultiModalConversation();
        // must create mutable map.
        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://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"),
                        Collections.singletonMap("text", "图中描绘的是什么景象？"))).build();
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                // 若没有配置环境变量，请用百炼API Key将下行替换为：.apiKey("sk-xxx")
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                .model("qwen-vl-max-latest")
                .messages(Arrays.asList(systemMessage, userMessage))
                .incrementalOutput(true)
                .build();
        Flowable<MultiModalConversationResult> result = conv.streamCall(param);
        result.blockingForEach(item -> {
            try {
                System.out.println(item.getOutput().getChoices().get(0).getMessage().getContent().get(0).get("text"));
            } catch (Exception e){
                System.exit(0);
            }
        });
    }

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

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' \
-H 'X-DashScope-SSE: enable' \
-d '{
    "model": "qwen-vl-max-latest",
    "input":{
        "messages":[
            {
                "role": "system",
                "content": [
                    {"text": "You are a helpful assistant."}
                ]
            },
            {
                "role": "user",
                "content": [
                    {"image": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"},
                    {"text": "图中描绘的是什么景象？"}
                ]
            }
        ]
    },
    "parameters": {
        "incremental_output": true
    }
}'

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")


base64_image = encode_image("test.png")
client = OpenAI(
    # 若没有配置环境变量，请用百炼API Key将下行替换为：api_key="sk-xxx"
    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-latest",
    messages=[
    	{
    	    "role": "system",
            "content": [{"type":"text","text": "You are a helpful assistant."}]},
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    # 需要注意，传入BASE64，图像格式（即image/{format}）需要与支持的图片列表中的Content Type保持一致。"f"是字符串格式化的方法。
                    # PNG图像：  f"data:image/png;base64,{base64_image}"
                    # JPEG图像： f"data:image/jpeg;base64,{base64_image}"
                    # WEBP图像： f"data:image/webp;base64,{base64_image}"
                    "image_url": {"url": f"data:image/png;base64,{base64_image}"}, 
                },
                {"type": "text", "text": "图中描绘的是什么景象?"},
            ],
        }
    ],
)
print(completion.choices[0].message.content)

import OpenAI from "openai";
import { readFileSync } from 'fs';

const openai = new OpenAI(
    {
        // 若没有配置环境变量，请用百炼API Key将下行替换为：apiKey: "sk-xxx"
        apiKey: process.env.DASHSCOPE_API_KEY,
        baseURL: "https://dashscope.aliyuncs.com/compatible-mode/v1"
    }
);

const encodeImage = (imagePath) => {
    const imageFile = readFileSync(imagePath);
    return imageFile.toString('base64');
  };
const base64Image = encodeImage("test.png")
async function main() {
    const completion = await openai.chat.completions.create({
        model: "qwen-vl-max-latest",
        messages: [
            {"role": "system", 
             "content": [{"type":"text","text": "You are a helpful assistant."}]},
            {"role": "user",
             "content": [{"type": "image_url",
                            // 需要注意，传入BASE64，图像格式（即image/{format}）需要与支持的图片列表中的Content Type保持一致。
                           // PNG图像：  data:image/png;base64,${base64Image}
                          // JPEG图像： data:image/jpeg;base64,${base64Image}
                         // WEBP图像： data:image/webp;base64,${base64Image}
                        "image_url": {"url": `data:image/png;base64,${base64Image}`},},
                        {"type": "text", "text": "图中描绘的是什么景象?"}]}]
    });
    console.log(completion.choices[0].message.content);
}

main();

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")


base64_image = encode_image("test.png")
# 若没有配置环境变量，请用百炼API Key将下行替换为：api_key="sk-xxx"
api_key = os.getenv("DASHSCOPE_API_KEY")
headers = {"Content-Type": "application/json", "Authorization": f"Bearer {api_key}"}
payload = {
    "model": "qwen-vl-max-latest",
    "messages": [
        {"role": "system",
         "content": [{"type":"text","text": "You are a helpful assistant."}]},
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    # 需要注意，传入BASE64，图像格式（即image/{format}）需要与支持的图片列表中的Content Type保持一致。"f"是字符串格式化的方法。
                    # PNG图像：  f"data:image/png;base64,{base64_image}"
                    # JPEG图像： f"data:image/jpeg;base64,{base64_image}"
                    # WEBP图像： f"data:image/webp;base64,{base64_image}"
                    "image_url": {"url": f"data:image/png;base64,{base64_image}"},
                },
                {"type": "text", "text": "图中描绘的是什么景象?"},
            ],
        }
    ],
}
response = requests.post(
    "https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions",
    headers=headers,
    json=payload,
)
print(response.json()["choices"][0]["message"]["content"])

import os
from openai import OpenAI

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-latest",
    messages=[
       {"role":"system","content":[{"type": "text", "text": "You are a helpful assistant."}]},
       {"role": "user","content": [
           # 第一张图像链接，如果传入本地文件，请将url的值替换为图像的BASE64编码格式
           {"type": "image_url","image_url": {"url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"},},
           # 第二张图像链接，如果传入本地文件，请将url的值替换为图像的BASE64编码格式
           {"type": "image_url","image_url": {"url": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/tiger.png"},},
           {"type": "text", "text": "这些图描绘了什么内容？"},
            ],
        }
    ],
)

print(completion.choices[0].message.content)

import OpenAI from "openai";

const openai = new OpenAI(
    {
        // 若没有配置环境变量，请用百炼API Key将下行替换为：apiKey: "sk-xxx"
        apiKey: process.env.DASHSCOPE_API_KEY,
        baseURL: "https://dashscope.aliyuncs.com/compatible-mode/v1"
    }
);

async function main() {
    const response = await openai.chat.completions.create({
        model: "qwen-vl-max-latest",
        messages: [
	    {role: "system",content:[{ type: "text", text: "You are a helpful assistant." }]},
	    {role: "user",content: [
	    // 第一张图像链接，如果传入本地文件，请将url的值替换为图像的BASE64编码格式
            {type: "image_url",image_url: {"url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"}},
            // 第二张图像链接，，如果传入本地文件，请将url的值替换为图像的BASE64编码格式
            {type: "image_url",image_url: {"url": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/tiger.png"}},
            {type: "text", text: "这些图描绘了什么内容？" },
        ]}]
    });
    console.log(response.choices[0].message.content);
}

main()

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-latest",
  "messages": [
    {
      "role": "system",
      "content": [{"type": "text", "text": "You are a helpful assistant."}]},
    {
      "role": "user",
      "content": [
        {
          "type": "image_url",
          "image_url": {
            "url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"
          }
        },
        {
          "type": "image_url",
          "image_url": {
            "url": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/tiger.png"
          }
        },
        {
          "type": "text",
          "text": "这些图描绘了什么内容？"
        }
      ]
    }
  ]
}'

import os
import dashscope

messages = [
    {
	"role": "system",
	"content": [{"text": "You are a helpful assistant."}]},
    {
        "role": "user",
        "content": [
            # 第一张图像链接，如果传入本地文件，请将url的值替换为图像的BASE64编码格式
            {"image": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"},
            # 第二张图像链接，如果传入本地文件，请将url的值替换为图像的BASE64编码格式
            {"image": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/tiger.png"},
            # 第三张图像链接，如果传入本地文件，请将url的值替换为图像的BASE64编码格式
            {"image": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/hbygyo/rabbit.jpg"},
            {"text": "这些图描绘了什么内容?"}
        ]
    }
]

response = dashscope.MultiModalConversation.call(
    # 若没有配置环境变量，请用百炼API Key将下行替换为：api_key="sk-xxx"
    api_key=os.getenv('DASHSCOPE_API_KEY'),
    model='qwen-vl-max-latest',
    messages=messages
)

print(response.output.choices[0].message.content[0]["text"])

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 java.util.HashMap;
public class Main {
    public static void simpleMultiModalConversationCall()
            throws ApiException, NoApiKeyException, UploadFileException {
        MultiModalConversation conv = new MultiModalConversation();
         // 如果使用本地图像，请导入 import java.util.HashMap;，再为函数添加【String localPath】参数，并释放下面注释
        // String filePath = "file://"+localPath;
        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(
                        // 第一张图像链接
                        Collections.singletonMap("image", "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"),
                        // 如果使用本地图像，请并释放下面注释
                        // new HashMap<String, Object>(){{put("image", filePath);}},
                        // 第二张图像链接
                        Collections.singletonMap("image", "https://dashscope.oss-cn-beijing.aliyuncs.com/images/tiger.png"),
                        // 第三张图像链接
                        Collections.singletonMap("image", "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/hbygyo/rabbit.jpg"),
                        Collections.singletonMap("text", "这些图描绘了什么内容?"))).build();
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                // 若没有配置环境变量，请用百炼API Key将下行替换为：.apiKey("sk-xxx")
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                .model("qwen-vl-max-latest")
                .messages(Arrays.asList(systemMessage, userMessage))
                .build();
        MultiModalConversationResult result = conv.call(param);
        System.out.println(result.getOutput().getChoices().get(0).getMessage().getContent().get(0).get("text"));    }
    public static void main(String[] args) {
        try {
            simpleMultiModalConversationCall();
        } catch (ApiException | NoApiKeyException | UploadFileException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }
}

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-max-latest",
    "input":{
        "messages":[
            {
                "role": "system",
                "content": [{"text": "You are a helpful assistant."}]},
            {
                "role": "user",
                "content": [
                    {"image": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"},
                    {"image": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/tiger.png"},
                    {"image": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/hbygyo/rabbit.jpg"},
                    {"text": "这些图展现了什么内容？"}
                ]
            }
        ]
    }
}'