视觉推理

from openai import OpenAI
import os

# 初始化OpenAI客户端
client = OpenAI(
    # 若没有配置环境变量，请用阿里云百炼API Key将下行替换为：api_key="sk-xxx",
    # 新加坡和北京地域的API Key不同。获取API Key：https://help.aliyun.com/zh/model-studio/get-api-key
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # 以下是北京地域base_url，如果使用新加坡地域的模型，需要将base_url替换为：https://dashscope-intl.aliyuncs.com/compatible-mode/v1
    base_url="https://dashscope.aliyuncs.com/compatible-mode/v1",
)

reasoning_content = ""  # 定义完整思考过程
answer_content = ""     # 定义完整回复
is_answering = False   # 判断是否结束思考过程并开始回复
enable_thinking = True
# 创建聊天完成请求
completion = client.chat.completions.create(
    model="qwen3-vl-plus",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://img.alicdn.com/imgextra/i1/O1CN01gDEY8M1W114Hi3XcN_!!6000000002727-0-tps-1024-406.jpg"
                    },
                },
                {"type": "text", "text": "这道题怎么解答？"},
            ],
        },
    ],
    stream=True,
    # enable_thinking 参数开启思考过程，thinking_budget 参数设置最大推理过程 Token 数
    # qwen3-vl-plus、 qwen3-vl-flash可通过enable_thinking开启或关闭思考、对于qwen3-vl-235b-a22b-thinking等带thinking后缀的模型，enable_thinking仅支持设置为开启，对其他Qwen-VL模型均不适用
    extra_body={
        'enable_thinking': enable_thinking,
        "thinking_budget": 81920},

    # 解除以下注释会在最后一个chunk返回Token使用量
    # stream_options={
    #     "include_usage": True
    # }
)

if enable_thinking:
    print("\n" + "=" * 20 + "思考过程" + "=" * 20 + "\n")

for chunk in completion:
    # 如果chunk.choices为空，则打印usage
    if not chunk.choices:
        print("\nUsage:")
        print(chunk.usage)
    else:
        delta = chunk.choices[0].delta
        # 打印思考过程
        if hasattr(delta, 'reasoning_content') and delta.reasoning_content != None:
            print(delta.reasoning_content, end='', flush=True)
            reasoning_content += delta.reasoning_content
        else:
            # 开始回复
            if delta.content != "" and is_answering is False:
                print("\n" + "=" * 20 + "完整回复" + "=" * 20 + "\n")
                is_answering = True
            # 打印回复过程
            print(delta.content, end='', flush=True)
            answer_content += delta.content

# print("=" * 20 + "完整思考过程" + "=" * 20 + "\n")
# print(reasoning_content)
# print("=" * 20 + "完整回复" + "=" * 20 + "\n")
# print(answer_content)

import OpenAI from "openai";

// 初始化 openai 客户端
const openai = new OpenAI({
     // 若没有配置环境变量，请用阿里云百炼API Key将下行替换为：api_key="sk-xxx",
    // 新加坡和北京地域的API Key不同。获取API Key：https://help.aliyun.com/zh/model-studio/get-api-key
    apiKey: process.env.DASHSCOPE_API_KEY, 
    // 以下是北京地域base_url，如果使用新加坡地域的模型，需要将base_url替换为：https://dashscope-intl.aliyuncs.com/compatible-mode/v1
    baseURL: 'https://dashscope.aliyuncs.com/compatible-mode/v1'
});

let reasoningContent = '';
let answerContent = '';
let isAnswering = false;
let enableThinking = true;

let messages = [
    {
        role: "user",
        content: [
        { type: "image_url", image_url: { "url": "https://img.alicdn.com/imgextra/i1/O1CN01gDEY8M1W114Hi3XcN_!!6000000002727-0-tps-1024-406.jpg" } },
        { type: "text", text: "解答这道题" },
    ]
}]

async function main() {
    try {
        const stream = await openai.chat.completions.create({
            model: 'qwen3-vl-plus',
            messages: messages,
            stream: true,
          // 注意：在 Node.js SDK，enableThinking 这样的非标准参数作为顶层属性传递的，无需放在 extra_body 中
          enable_thinking: enableThinking,
          thinking_budget: 81920

        });

        if (enableThinking){console.log('\n' + '='.repeat(20) + '思考过程' + '='.repeat(20) + '\n');}

        for await (const chunk of stream) {
            if (!chunk.choices?.length) {
                console.log('\nUsage:');
                console.log(chunk.usage);
                continue;
            }

            const delta = chunk.choices[0].delta;

            // 处理思考过程
            if (delta.reasoning_content) {
                process.stdout.write(delta.reasoning_content);
                reasoningContent += delta.reasoning_content;
            }
            // 处理正式回复
            else if (delta.content) {
                if (!isAnswering) {
                    console.log('\n' + '='.repeat(20) + '完整回复' + '='.repeat(20) + '\n');
                    isAnswering = true;
                }
                process.stdout.write(delta.content);
                answerContent += delta.content;
            }
        }
    } catch (error) {
        console.error('Error:', error);
    }
}

main();

# ======= 重要提示 =======
# 新加坡和北京地域的API Key不同。获取API Key：https://help.aliyun.com/zh/model-studio/get-api-key
# 以下是北京地域base_url，如果使用新加坡地域的模型，需要将base_url替换为：https://dashscope-intl.aliyuncs.com/compatible-mode/v1/chat/completions
# === 执行时请删除该注释 ===

curl --location 'https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
    "model": "qwen3-vl-plus",
    "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "image_url",
          "image_url": {
            "url": "https://img.alicdn.com/imgextra/i1/O1CN01gDEY8M1W114Hi3XcN_!!6000000002727-0-tps-1024-406.jpg"
          }
        },
        {
          "type": "text",
          "text": "请解答这道题"
        }
      ]
    }
  ],
    "stream":true,
    "stream_options":{"include_usage":true},
    "enable_thinking": true,
    "thinking_budget": 81920
}'

import os
import dashscope
from dashscope import MultiModalConversation

# 若使用新加坡地域的模型，请取消下列注释
# dashscope.base_http_api_url = "https://dashscope-intl.aliyuncs.com/api/v1"
enable_thinking=True
messages = [
    {
        "role": "user",
        "content": [
            {"image": "https://img.alicdn.com/imgextra/i1/O1CN01gDEY8M1W114Hi3XcN_!!6000000002727-0-tps-1024-406.jpg"},
            {"text": "解答这道题？"}
        ]
    }
]

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="qwen3-vl-plus",
    messages=messages,
    stream=True,
    # enable_thinking 参数开启思考过程
    # qwen3-vl-plus、 qwen3-vl-flash可通过enable_thinking开启或关闭思考、对于qwen3-vl-235b-a22b-thinking等带thinking后缀的模型，enable_thinking仅支持设置为开启，对其他Qwen-VL模型均不适用
    enable_thinking=enable_thinking,
    # thinking_budget 参数设置最大推理过程 Token 数
    thinking_budget=81920,

)

# 定义完整思考过程
reasoning_content = ""
# 定义完整回复
answer_content = ""
# 判断是否结束思考过程并开始回复
is_answering = False
if enable_thinking:
    print("=" * 20 + "思考过程" + "=" * 20)

for chunk in response:
    # 如果思考过程与回复皆为空，则忽略
    message = chunk.output.choices[0].message
    reasoning_content_chunk = message.get("reasoning_content", None)
    if (chunk.output.choices[0].message.content == [] and
        reasoning_content_chunk == ""):
        pass
    else:
        # 如果当前为思考过程
        if reasoning_content_chunk != None and chunk.output.choices[0].message.content == []:
            print(chunk.output.choices[0].message.reasoning_content, end="")
            reasoning_content += chunk.output.choices[0].message.reasoning_content
        # 如果当前为回复
        elif chunk.output.choices[0].message.content != []:
            if not is_answering:
                print("\n" + "=" * 20 + "完整回复" + "=" * 20)
                is_answering = True
            print(chunk.output.choices[0].message.content[0]["text"], end="")
            answer_content += chunk.output.choices[0].message.content[0]["text"]

# 如果您需要打印完整思考过程与完整回复，请将以下代码解除注释后运行
# print("=" * 20 + "完整思考过程" + "=" * 20 + "\n")
# print(f"{reasoning_content}")
# print("=" * 20 + "完整回复" + "=" * 20 + "\n")
# print(f"{answer_content}")

// dashscope SDK的版本 >= 2.21.10
import java.util.*;

import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

import com.alibaba.dashscope.common.Role;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import io.reactivex.Flowable;

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.exception.UploadFileException;
import com.alibaba.dashscope.exception.InputRequiredException;
import java.lang.System;
import com.alibaba.dashscope.utils.Constants;

public class Main {

    // 若使用新加坡地域的模型，请取消下列注释
    //  static {Constants.baseHttpApiUrl="https://dashscope-intl.aliyuncs.com/api/v1";}

    private static final Logger logger = LoggerFactory.getLogger(Main.class);
    private static StringBuilder reasoningContent = new StringBuilder();
    private static StringBuilder finalContent = new StringBuilder();
    private static boolean isFirstPrint = true;

    private static void handleGenerationResult(MultiModalConversationResult message) {
        String re = message.getOutput().getChoices().get(0).getMessage().getReasoningContent();
        String reasoning = Objects.isNull(re)?"":re; // 默认值

        List<Map<String, Object>> content = message.getOutput().getChoices().get(0).getMessage().getContent();
        if (!reasoning.isEmpty()) {
            reasoningContent.append(reasoning);
            if (isFirstPrint) {
                System.out.println("====================思考过程====================");
                isFirstPrint = false;
            }
            System.out.print(reasoning);
        }

        if (Objects.nonNull(content) && !content.isEmpty()) {
            Object text = content.get(0).get("text");
            finalContent.append(content.get(0).get("text"));
            if (!isFirstPrint) {
                System.out.println("\n====================完整回复====================");
                isFirstPrint = true;
            }
            System.out.print(text);
        }
    }
    public static MultiModalConversationParam buildMultiModalConversationParam(MultiModalMessage Msg)  {
        return 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")
                // 新加坡和北京地域的API Key不同。获取API Key：https://help.aliyun.com/zh/model-studio/get-api-key
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                .model("qwen3-vl-plus")
                .messages(Arrays.asList(Msg))
                .enableThinking(true)
                .thinkingBudget(81920)
                .incrementalOutput(true)
                .build();
    }

    public static void streamCallWithMessage(MultiModalConversation conv, MultiModalMessage Msg)
            throws NoApiKeyException, ApiException, InputRequiredException, UploadFileException {
        MultiModalConversationParam param = buildMultiModalConversationParam(Msg);
        Flowable<MultiModalConversationResult> result = conv.streamCall(param);
        result.blockingForEach(message -> {
            handleGenerationResult(message);
        });
    }
    public static void main(String[] args) {
        try {
            MultiModalConversation conv = new MultiModalConversation();
            MultiModalMessage userMsg = MultiModalMessage.builder()
                    .role(Role.USER.getValue())
                    .content(Arrays.asList(Collections.singletonMap("image", "https://img.alicdn.com/imgextra/i1/O1CN01gDEY8M1W114Hi3XcN_!!6000000002727-0-tps-1024-406.jpg"),
                            Collections.singletonMap("text", "请解答这道题")))
                    .build();
            streamCallWithMessage(conv, userMsg);
//             打印最终结果
//            if (reasoningContent.length() > 0) {
//                System.out.println("\n====================完整回复====================");
//                System.out.println(finalContent.toString());
//            }
        } catch (ApiException | NoApiKeyException | UploadFileException | InputRequiredException e) {
            logger.error("An exception occurred: {}", e.getMessage());
        }
        System.exit(0);
    }
}

# ======= 重要提示 =======
# 新加坡和北京地域的API Key不同。获取API Key：https://help.aliyun.com/zh/model-studio/get-api-key
# 以下是北京地域base_url，如果使用新加坡地域的模型，需要将base_url替换为：https://dashscope-intl.aliyuncs.com/compatible-mode/v1
# === 执行时请删除该注释 ===

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": "qwen3-vl-plus",
    "input":{
        "messages":[
            {
                "role": "user",
                "content": [
                    {"image": "https://img.alicdn.com/imgextra/i1/O1CN01gDEY8M1W114Hi3XcN_!!6000000002727-0-tps-1024-406.jpg"},
                    {"text": "请解答这道题"}
                ]
            }
        ]
    },
    "parameters":{
        "enable_thinking": true,
        "incremental_output": true,
        "thinking_budget": 81920
    }
}'