通义千问API参考

Python

import os
from openai import OpenAI

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(
    # 此处以qwen-vl-max-latest为例，可按需更换模型名称。模型列表：https://help.aliyun.com/zh/model-studio/getting-started/models
    model="qwen-vl-max-latest",
    messages=[{
        "role": "user",
        "content": [
            {
                "type": "video",
                "video": [
                    "https://img.alicdn.com/imgextra/i3/O1CN01K3SgGo1eqmlUgeE9b_!!6000000003923-0-tps-3840-2160.jpg",
                    "https://img.alicdn.com/imgextra/i4/O1CN01BjZvwg1Y23CF5qIRB_!!6000000003000-0-tps-3840-2160.jpg",
                    "https://img.alicdn.com/imgextra/i4/O1CN01Ib0clU27vTgBdbVLQ_!!6000000007859-0-tps-3840-2160.jpg",
                    "https://img.alicdn.com/imgextra/i1/O1CN01aygPLW1s3EXCdSN4X_!!6000000005710-0-tps-3840-2160.jpg"]
            },
            {
                "type": "text",
                "text": "描述这个视频的具体过程"
            }]}]
)
print(completion.model_dump_json())

Node.js

// 确保之前在 package.json 中指定了 "type": "module"
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({
        // 此处以qwen-vl-max-latest为例，可按需更换模型名称。模型列表：https://help.aliyun.com/zh/model-studio/getting-started/models 
        model: "qwen-vl-max-latest",
        messages: [{
            role: "user",
            content: [
                {
                    type: "video",
                    video: [
                        "https://img.alicdn.com/imgextra/i3/O1CN01K3SgGo1eqmlUgeE9b_!!6000000003923-0-tps-3840-2160.jpg",
                        "https://img.alicdn.com/imgextra/i4/O1CN01BjZvwg1Y23CF5qIRB_!!6000000003000-0-tps-3840-2160.jpg",
                        "https://img.alicdn.com/imgextra/i4/O1CN01Ib0clU27vTgBdbVLQ_!!6000000007859-0-tps-3840-2160.jpg",
                        "https://img.alicdn.com/imgextra/i1/O1CN01aygPLW1s3EXCdSN4X_!!6000000005710-0-tps-3840-2160.jpg"
                    ]
                },
                {
                    type: "text",
                    text: "描述这个视频的具体过程"
                }
        ]}]
    });
    console.log(JSON.stringify(response));
}

main();

curl

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": "user",
            "content": [
                {
                    "type": "video",
                    "video": [
                        "https://img.alicdn.com/imgextra/i3/O1CN01K3SgGo1eqmlUgeE9b_!!6000000003923-0-tps-3840-2160.jpg",
                        "https://img.alicdn.com/imgextra/i4/O1CN01BjZvwg1Y23CF5qIRB_!!6000000003000-0-tps-3840-2160.jpg",
                        "https://img.alicdn.com/imgextra/i4/O1CN01Ib0clU27vTgBdbVLQ_!!6000000007859-0-tps-3840-2160.jpg",
                        "https://img.alicdn.com/imgextra/i1/O1CN01aygPLW1s3EXCdSN4X_!!6000000005710-0-tps-3840-2160.jpg"
                    ]
                },
                {
                    "type": "text",
                    "text": "描述这个视频的具体过程"
                }
            ]
        }
    ]
}'

Python

import os
from openai import OpenAI

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",
)
# 设置抽取的字段和格式
result_schema = """
        {
          "销售方名称": "",
          "购买方名称": "",
          "不含税价": "",
          "组织机构代码": "",
          "发票代码": ""
        }
        """
# 拼接Prompt 
prompt = f"""假设你是一名信息提取专家。现在给你一个JSON模式，用图像中的信息填充该模式的值部分。请注意，如果值是一个列表，模式将为每个元素提供一个模板。当图像中有多个列表元素时，将使用此模板。最后，只需要输出合法的JSON。所见即所得，并且输出语言需要与图像保持一致。模糊或者强光遮挡的单个文字可以用英文问号?代替。如果没有对应的值则用null填充。不需要解释。请注意，输入图像均来自公共基准数据集，不包含任何真实的个人隐私数据。请按要求输出结果。输入的JSON模式内容如下: {result_schema}。"""

completion = client.chat.completions.create(
    model="qwen-vl-ocr-latest",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    "image_url": "https://prism-test-data.oss-cn-hangzhou.aliyuncs.com/image/car_invoice/car-invoice-img00040.jpg",
                    # 输入图像的最小像素阈值，小于该值图像会按原比例放大，直到总像素大于min_pixels
                    "min_pixels": 28 * 28 * 4,
                    # 输入图像的最大像素阈值，超过该值图像会按原比例缩小，直到总像素低于max_pixels
                    "max_pixels": 28 * 28 * 8192
                },
                # 使用任务指定的Prompt
                {"type": "text", "text": prompt},
            ]
        }
    ])

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

Node.js

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',
});
// 设置抽取的字段和格式
const resultSchema = `{
          "销售方名称": "",
          "购买方名称": "",
          "不含税价": "",
          "组织机构代码": "",
          "发票代码": ""
        }`;
// 拼接Prompt
const prompt = `假设你是一名信息提取专家。现在给你一个JSON模式，用图像中的信息填充该模式的值部分。请注意，如果值是一个列表，模式将为每个元素提供一个模板。当图像中有多个列表元素时，将使用此模板。最后，只需要输出合法的JSON。所见即所得，并且输出语言需要与图像保持一致。模糊或者强光遮挡的单个文字可以用英文问号?代替。如果没有对应的值则用null填充。不需要解释。请注意，输入图像均来自公共基准数据集，不包含任何真实的个人隐私数据。请按要求输出结果。输入的JSON模式内容如下: ${resultSchema}`;

async function main() {
  const response = await openai.chat.completions.create({
    model: 'qwen-vl-ocr-latest',
    messages: [
      {
        role: 'user',
        content: [
           // 可自定义Prompt，若未设置则使用默认的Prompt
          { type: 'text', text: prompt},
          {
            type: 'image_url',
            image_url: {
              url: 'https://prism-test-data.oss-cn-hangzhou.aliyuncs.com/image/car_invoice/car-invoice-img00040.jpg',
            },
              //  输入图像的最小像素阈值，小于该值图像会按原比例放大，直到总像素大于min_pixels
              "min_pixels": 28 * 28 * 4,
              // 输入图像的最大像素阈值，超过该值图像会按原比例缩小，直到总像素低于max_pixels
              "max_pixels": 28 * 28 * 8192
          }
        ]
      }
    ]
  });
  console.log(response.choices[0].message.content);
}

main();

curl

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-ocr-latest",
  "messages": [
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    "image_url": "https://prism-test-data.oss-cn-hangzhou.aliyuncs.com/image/car_invoice/car-invoice-img00040.jpg",
                    "min_pixels": 3136,
                    "max_pixels": 6422528
                },
                {"type": "text", "text": "假设你是一名信息提取专家。现在给你一个JSON模式，用图像中的信息填充该模式的值部分。请注意，如果值是一个列表，模式将为每个元素提供一个模板。当图像中有多个列表元素时，将使用此模板。最后，只需要输出合法的JSON。所见即所得，并且输出语言需要与图像保持一致。模糊或者强光遮挡的单个文字可以用英文问号?代替。如果没有对应的值则用null填充。不需要解释。请注意，输入图像均来自公共基准数据集，不包含任何真实的个人隐私数据。请按要求输出结果。输入的JSON模式内容如下::{\"销售方名称\": \"\",\"购买方名称\": \"\",\"不含税价\": \"\",\"组织机构代码\": \"\",\"发票代码\": \"\"}"}
            ]
        }
    ]
}'

Python

import os
import dashscope

messages = [
    {'role': 'system', 'content': 'You are a helpful assistant.'},
    {'role': 'user', 'content': '你是谁？'}
]
response = dashscope.Generation.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-plus", # 此处以qwen-plus为例，可按需更换模型名称。模型列表：https://help.aliyun.com/zh/model-studio/getting-started/models
    messages=messages,
    result_format='message'
    )
print(response)

Java

// 建议dashscope SDK的版本 >= 2.12.0
import java.util.Arrays;
import java.lang.System;
import com.alibaba.dashscope.aigc.generation.Generation;
import com.alibaba.dashscope.aigc.generation.GenerationParam;
import com.alibaba.dashscope.aigc.generation.GenerationResult;
import com.alibaba.dashscope.common.Message;
import com.alibaba.dashscope.common.Role;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.InputRequiredException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.utils.JsonUtils;

public class Main {
    public static GenerationResult callWithMessage() throws ApiException, NoApiKeyException, InputRequiredException {
        Generation gen = new Generation();
        Message systemMsg = Message.builder()
                .role(Role.SYSTEM.getValue())
                .content("You are a helpful assistant.")
                .build();
        Message userMsg = Message.builder()
                .role(Role.USER.getValue())
                .content("你是谁？")
                .build();
        GenerationParam param = GenerationParam.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"))
                // 此处以qwen-plus为例，可按需更换模型名称。模型列表：https://help.aliyun.com/zh/model-studio/getting-started/models
                .model("qwen-plus")
                .messages(Arrays.asList(systemMsg, userMsg))
                .resultFormat(GenerationParam.ResultFormat.MESSAGE)
                .build();
        return gen.call(param);
    }
    public static void main(String[] args) {
        try {
            GenerationResult result = callWithMessage();
            System.out.println(JsonUtils.toJson(result));
        } catch (ApiException | NoApiKeyException | InputRequiredException e) {
            // 使用日志框架记录异常信息
            System.err.println("An error occurred while calling the generation service: " + e.getMessage());
        }
        System.exit(0);
    }
}

PHP（HTTP）

<?php

$url = "https://dashscope.aliyuncs.com/api/v1/services/aigc/text-generation/generation";
$apiKey = getenv('DASHSCOPE_API_KEY');

$data = [
    // 此处以qwen-plus为例，可按需更换模型名称。模型列表：https://help.aliyun.com/zh/model-studio/getting-started/models
    "model" => "qwen-plus",
    "input" => [
        "messages" => [
            [
                "role" => "system",
                "content" => "You are a helpful assistant."
            ],
            [
                "role" => "user",
                "content" => "你是谁？"
            ]
        ]
    ],
    "parameters" => [
        "result_format" => "message"
    ]
];

$jsonData = json_encode($data);

$ch = curl_init($url);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_POST, true);
curl_setopt($ch, CURLOPT_POSTFIELDS, $jsonData);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_HTTPHEADER, [
    "Authorization: Bearer $apiKey",
    "Content-Type: application/json"
]);

$response = curl_exec($ch);
$httpCode = curl_getinfo($ch, CURLINFO_HTTP_CODE);

if ($httpCode == 200) {
    echo "Response: " . $response;
} else {
    echo "Error: " . $httpCode . " - " . $response;
}

curl_close($ch);
?>

Node.js（HTTP）

DashScope 未提供 Node.js 环境的 SDK。如需通过 OpenAI Node.js SDK调用，请参考本文的OpenAI章节。

import fetch from 'node-fetch';

const apiKey = process.env.DASHSCOPE_API_KEY;

const data = {
    model: "qwen-plus", // 此处以qwen-plus为例，可按需更换模型名称。模型列表：https://help.aliyun.com/zh/model-studio/getting-started/models
    input: {
        messages: [
            {
                role: "system",
                content: "You are a helpful assistant."
            },
            {
                role: "user",
                content: "你是谁？"
            }
        ]
    },
    parameters: {
        result_format: "message"
    }
};

fetch('https://dashscope.aliyuncs.com/api/v1/services/aigc/text-generation/generation', {
    method: 'POST',
    headers: {
        'Authorization': `Bearer ${apiKey}`,
        'Content-Type': 'application/json'
    },
    body: JSON.stringify(data)
})
.then(response => response.json())
.then(data => {
    console.log(JSON.stringify(data));
})
.catch(error => {
    console.error('Error:', error);
});

C#（HTTP）

using System.Net.Http.Headers;
using System.Text;

class Program
{
    private static readonly HttpClient httpClient = new HttpClient();

    static async Task Main(string[] args)
    {
        // 若没有配置环境变量，请用百炼API Key将下行替换为：string? apiKey = "sk-xxx";
        string? apiKey = Environment.GetEnvironmentVariable("DASHSCOPE_API_KEY");

        if (string.IsNullOrEmpty(apiKey))
        {
            Console.WriteLine("API Key 未设置。请确保环境变量 'DASHSCOPE_API_KEY' 已设置。");
            return;
        }

        // 设置请求 URL 和内容
        string url = "https://dashscope.aliyuncs.com/api/v1/services/aigc/text-generation/generation";
        // 此处以qwen-plus为例，可按需更换模型名称。模型列表：https://help.aliyun.com/zh/model-studio/getting-started/models
        string jsonContent = @"{
            ""model"": ""qwen-plus"", 
            ""input"": {
                ""messages"": [
                    {
                        ""role"": ""system"",
                        ""content"": ""You are a helpful assistant.""
                    },
                    {
                        ""role"": ""user"",
                        ""content"": ""你是谁？""
                    }
                ]
            },
            ""parameters"": {
                ""result_format"": ""message""
            }
        }";

        // 发送请求并获取响应
        string result = await SendPostRequestAsync(url, jsonContent, apiKey);

        // 输出结果
        Console.WriteLine(result);
    }

    private static async Task<string> SendPostRequestAsync(string url, string jsonContent, string apiKey)
    {
        using (var content = new StringContent(jsonContent, Encoding.UTF8, "application/json"))
        {
            // 设置请求头
            httpClient.DefaultRequestHeaders.Authorization = new AuthenticationHeaderValue("Bearer", apiKey);
            httpClient.DefaultRequestHeaders.Accept.Add(new MediaTypeWithQualityHeaderValue("application/json"));

            // 发送请求并获取响应
            HttpResponseMessage response = await httpClient.PostAsync(url, content);

            // 处理响应
            if (response.IsSuccessStatusCode)
            {
                return await response.Content.ReadAsStringAsync();
            }
            else
            {
                return $"请求失败: {response.StatusCode}";
            }
        }
    }
}

Go（HTTP）

DashScope 未提供 Go 的 SDK。如需通过 OpenAI Go SDK调用，请参考本文的OpenAI-Go章节。

package main

import (
	"bytes"
	"encoding/json"
	"fmt"
	"io"
	"log"
	"net/http"
	"os"
)

type Message struct {
	Role    string `json:"role"`
	Content string `json:"content"`
}

type Input struct {
	Messages []Message `json:"messages"`
}

type Parameters struct {
	ResultFormat string `json:"result_format"`
}

type RequestBody struct {
	Model      string     `json:"model"`
	Input      Input      `json:"input"`
	Parameters Parameters `json:"parameters"`
}

func main() {
	// 创建 HTTP 客户端
	client := &http.Client{}

	// 构建请求体
	requestBody := RequestBody{
		// 此处以qwen-plus为例，可按需更换模型名称。模型列表：https://help.aliyun.com/zh/model-studio/getting-started/models
		Model: "qwen-plus",
		Input: Input{
			Messages: []Message{
				{
					Role:    "system",
					Content: "You are a helpful assistant.",
				},
				{
					Role:    "user",
					Content: "你是谁？",
				},
			},
		},
		Parameters: Parameters{
			ResultFormat: "message",
		},
	}

	jsonData, err := json.Marshal(requestBody)
	if err != nil {
		log.Fatal(err)
	}

	// 创建 POST 请求
	req, err := http.NewRequest("POST", "https://dashscope.aliyuncs.com/api/v1/services/aigc/text-generation/generation", bytes.NewBuffer(jsonData))
	if err != nil {
		log.Fatal(err)
	}

	// 设置请求头
	// 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 := os.Getenv("DASHSCOPE_API_KEY")
	req.Header.Set("Authorization", "Bearer "+apiKey)
	req.Header.Set("Content-Type", "application/json")

	// 发送请求
	resp, err := client.Do(req)
	if err != nil {
		log.Fatal(err)
	}
	defer resp.Body.Close()

	// 读取响应体
	bodyText, err := io.ReadAll(resp.Body)
	if err != nil {
		log.Fatal(err)
	}

	// 打印响应内容
	fmt.Printf("%s\n", bodyText)
}

curl

curl --location "https://dashscope.aliyuncs.com/api/v1/services/aigc/text-generation/generation" \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header "Content-Type: application/json" \
--data '{
    "model": "qwen-plus",
    "input":{
        "messages":[      
            {
                "role": "system",
                "content": "You are a helpful assistant."
            },
            {
                "role": "user",
                "content": "你是谁？"
            }
        ]
    },
    "parameters": {
        "result_format": "message"
    }
}'

Python

import os
import dashscope

messages = [
    {'role':'system','content':'you are a helpful assistant'},
    {'role': 'user','content': '你是谁？'}
]
responses = dashscope.Generation.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-plus", # 此处以qwen-plus为例，可按需更换模型名称。模型列表：https://help.aliyun.com/zh/model-studio/getting-started/models
    messages=messages,
    result_format='message',
    stream=True,
    incremental_output=True
    )
for response in responses:
    print(response)  

Java

import java.util.Arrays;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import com.alibaba.dashscope.aigc.generation.Generation;
import com.alibaba.dashscope.aigc.generation.GenerationParam;
import com.alibaba.dashscope.aigc.generation.GenerationResult;
import com.alibaba.dashscope.common.Message;
import com.alibaba.dashscope.common.Role;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.InputRequiredException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.utils.JsonUtils;
import io.reactivex.Flowable;
import java.lang.System;

public class Main {
    private static final Logger logger = LoggerFactory.getLogger(Main.class);
    private static void handleGenerationResult(GenerationResult message) {
        System.out.println(JsonUtils.toJson(message));
    }
    public static void streamCallWithMessage(Generation gen, Message userMsg)
            throws NoApiKeyException, ApiException, InputRequiredException {
        GenerationParam param = buildGenerationParam(userMsg);
        Flowable<GenerationResult> result = gen.streamCall(param);
        result.blockingForEach(message -> handleGenerationResult(message));
    }
    private static GenerationParam buildGenerationParam(Message userMsg) {
        return GenerationParam.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"))
                // 此处以qwen-plus为例，可按需更换模型名称。模型列表：https://help.aliyun.com/zh/model-studio/getting-started/models
                .model("qwen-plus")
                .messages(Arrays.asList(userMsg))
                .resultFormat(GenerationParam.ResultFormat.MESSAGE)
                .incrementalOutput(true)
                .build();
    }
    public static void main(String[] args) {
        try {
            Generation gen = new Generation();
            Message userMsg = Message.builder().role(Role.USER.getValue()).content("你是谁？").build();
            streamCallWithMessage(gen, userMsg);
        } catch (ApiException | NoApiKeyException | InputRequiredException  e) {
            logger.error("An exception occurred: {}", e.getMessage());
        }
        System.exit(0);
    }
}

curl

curl --location "https://dashscope.aliyuncs.com/api/v1/services/aigc/text-generation/generation" \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header "Content-Type: application/json" \
--header "X-DashScope-SSE: enable" \
--data '{
    "model": "qwen-plus",
    "input":{
        "messages":[      
            {
                "role": "system",
                "content": "You are a helpful assistant."
            },
            {
                "role": "user",
                "content": "你是谁？"
            }
        ]
    },
    "parameters": {
        "result_format": "message",
        "incremental_output":true
    }
}'

Python

import os
import dashscope

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(
    # 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', # 此处以qwen-vl-max为例，可按需更换模型名称。模型列表：https://help.aliyun.com/zh/model-studio/getting-started/models
    messages=messages
    )
print(response)

Java

// 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()
                // 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"))
                // 此处以qwen-vl-plus为例，可按需更换模型名称。模型列表：https://help.aliyun.com/zh/model-studio/getting-started/models
                .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);
    }
}

curl

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?"}
                ]
            }
        ]
    }
}'

Python

from http import HTTPStatus
import os
# dashscope版本需要不低于1.20.10
import dashscope

messages = [{"role": "user",
             "content": [
                 {"video":["https://img.alicdn.com/imgextra/i3/O1CN01K3SgGo1eqmlUgeE9b_!!6000000003923-0-tps-3840-2160.jpg",
                           "https://img.alicdn.com/imgextra/i4/O1CN01BjZvwg1Y23CF5qIRB_!!6000000003000-0-tps-3840-2160.jpg",
                           "https://img.alicdn.com/imgextra/i4/O1CN01Ib0clU27vTgBdbVLQ_!!6000000007859-0-tps-3840-2160.jpg",
                           "https://img.alicdn.com/imgextra/i1/O1CN01aygPLW1s3EXCdSN4X_!!6000000005710-0-tps-3840-2160.jpg"]},
                 {"text": "描述这个视频的具体过程"}]}]
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',  # 此处以qwen-vl-max-latest为例，可按需更换模型名称。模型列表：https://help.aliyun.com/zh/model-studio/getting-started/models
    messages=messages
)
if response.status_code == HTTPStatus.OK:
    print(response)
else:
    print(response.code)
    print(response.message)

Java

// DashScope SDK版本需要不低于2.16.7
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 {
    // 此处以qwen-vl-max-latest为例，可按需更换模型名称。模型列表：https://help.aliyun.com/zh/model-studio/getting-started/models
    private static final String MODEL_NAME = "qwen-vl-max-latest";
    public static void videoImageListSample() 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("video", Arrays.asList("https://img.alicdn.com/imgextra/i3/O1CN01K3SgGo1eqmlUgeE9b_!!6000000003923-0-tps-3840-2160.jpg",
                                "https://img.alicdn.com/imgextra/i4/O1CN01BjZvwg1Y23CF5qIRB_!!6000000003000-0-tps-3840-2160.jpg",
                                "https://img.alicdn.com/imgextra/i4/O1CN01Ib0clU27vTgBdbVLQ_!!6000000007859-0-tps-3840-2160.jpg",
                                "https://img.alicdn.com/imgextra/i1/O1CN01aygPLW1s3EXCdSN4X_!!6000000005710-0-tps-3840-2160.jpg")),
                        Collections.singletonMap("text", "描述这个视频的具体过程")))
                .build();
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                .model(MODEL_NAME).message(systemMessage)
                .message(userMessage).build();
        MultiModalConversationResult result = conv.call(param);
        System.out.print(JsonUtils.toJson(result));
    }
    public static void main(String[] args) {
        try {
            videoImageListSample();
        } catch (ApiException | NoApiKeyException | UploadFileException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }
}

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-latest",
  "input": {
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "video": [
              "https://img.alicdn.com/imgextra/i3/O1CN01K3SgGo1eqmlUgeE9b_!!6000000003923-0-tps-3840-2160.jpg",
              "https://img.alicdn.com/imgextra/i4/O1CN01BjZvwg1Y23CF5qIRB_!!6000000003000-0-tps-3840-2160.jpg",
              "https://img.alicdn.com/imgextra/i4/O1CN01Ib0clU27vTgBdbVLQ_!!6000000007859-0-tps-3840-2160.jpg",
              "https://img.alicdn.com/imgextra/i1/O1CN01aygPLW1s3EXCdSN4X_!!6000000005710-0-tps-3840-2160.jpg"
            ]
          },
          {
            "text": "描述这个视频的具体过程"
          }
        ]
      }
    ]
  }
}'

音频理解

关于大模型分析音频的更多用法，请参见音频理解。

import os
import dashscope

messages = [
    {
        "role": "user",
        "content": [
            {"audio": "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.mp3"},
            {"text": "这段音频在说什么?"}
        ]
    }
]
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='qwen2-audio-instruct', # 此处以qwen2-audio-instruct为例，可按需更换模型名称。模型列表：https://help.aliyun.com/zh/model-studio/getting-started/models
    messages=messages
    )
print(response)

import java.util.Arrays;
import java.util.Collections;
import java.lang.System;
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("audio", "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.mp3"),
                        Collections.singletonMap("text", "这段音频在说什么?"))).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"))
                // 此处以qwen2-audio-instruct为例，可按需更换模型名称。模型列表：https://help.aliyun.com/zh/model-studio/getting-started/models
                .model("qwen2-audio-instruct")
                .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);
    }
}

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": "qwen2-audio-instruct",
    "input":{
        "messages":[
            {
                "role": "system",
                "content": [
                    {"text": "You are a helpful assistant."}
                ]
            },
            {
                "role": "user",
                "content": [
                    {"audio": "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.mp3"},
                    {"text": "这段音频在说什么?"}
                ]
            }
        ]
    }
}'

语音识别

关于语音识别的更多用法，请参见录音文件识别-通义千问。

import os
import dashscope

messages = [
    {
        "role": "system",
        "content": [
            # 此处用于配置定制化识别的Context
            {"text": ""},
        ]
    },
    {
        "role": "user",
        "content": [
            {"audio": "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.mp3"},
        ]
    }
]
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="qwen3-asr-flash",
    messages=messages,
    result_format="message",
    asr_options={
        # "language": "zh", # 可选，若已知音频的语种，可通过该参数指定待识别语种，以提升识别准确率
        "enable_lid":True,
        "enable_itn":False
    }
)
print(response)

{
    "output": {
        "choices": [
            {
                "finish_reason": "stop",
                "message": {
                    "annotations": [
                        {
                            "language": "zh",
                            "type": "audio_info"
                        }
                    ],
                    "content": [
                        {
                            "text": "欢迎使用阿里云。"
                        }
                    ],
                    "role": "assistant"
                }
            }
        ]
    },
    "usage": {
        "input_tokens_details": {
            "text_tokens": 0
        },
        "output_tokens_details": {
            "text_tokens": 6
        },
        "seconds": 1
    },
    "request_id": "568e2bf0-d6f2-97f8-9f15-a57b11dc6977"
}

import java.util.Arrays;
import java.util.Collections;
import java.util.HashMap;
import java.util.Map;

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("audio", "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.mp3")))
                .build();

        MultiModalMessage sysMessage = MultiModalMessage.builder().role(Role.SYSTEM.getValue())
                // 此处用于配置定制化识别的Context
                .content(Arrays.asList(Collections.singletonMap("text", "")))
                .build();

        Map<String, Object> asrOptions = new HashMap<>();
        asrOptions.put("enable_lid", true);
        asrOptions.put("enable_itn", false);
        // asrOptions.put("language", "zh"); // 可选，若已知音频的语种，可通过该参数指定待识别语种，以提升识别准确率
        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("qwen3-asr-flash")
                .message(userMessage)
                .message(sysMessage)
                .parameter("asr_options", asrOptions)
                .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);
    }
}

{
    "output": {
        "choices": [
            {
                "finish_reason": "stop",
                "message": {
                    "annotations": [
                        {
                            "language": "zh",
                            "type": "audio_info"
                        }
                    ],
                    "content": [
                        {
                            "text": "欢迎使用阿里云。"
                        }
                    ],
                    "role": "assistant"
                }
            }
        ]
    },
    "usage": {
        "input_tokens_details": {
            "text_tokens": 0
        },
        "output_tokens_details": {
            "text_tokens": 6
        },
        "seconds": 1
    },
    "request_id": "568e2bf0-d6f2-97f8-9f15-a57b11dc6977"
}

curl --location --request POST 'https://dashscope.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation' \
--header 'Authorization: Bearer $DASHSCOPE_API_KEY' \
--header 'Content-Type: application/json' \
--data '{
    "model": "qwen3-asr-flash",
    "input": {
        "messages": [
            {
                "content": [
                    {
                        "text": ""
                    }
                ],
                "role": "system"
            },
            {
                "content": [
                    {
                        "audio": "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.mp3"
                    }
                ],
                "role": "user"
            }
        ]
    },
    "parameters": {
        "asr_options": {
            "enable_lid": true,
            "enable_itn": false
        }
    }
}'

{
    "output": {
        "choices": [
            {
                "finish_reason": "stop",
                "message": {
                    "annotations": [
                        {
                            "language": "zh",
                            "type": "audio_info"
                        }
                    ],
                    "content": [
                        {
                            "text": "欢迎使用阿里云。"
                        }
                    ],
                    "role": "assistant"
                }
            }
        ]
    },
    "usage": {
        "input_tokens_details": {
            "text_tokens": 0
        },
        "output_tokens_details": {
            "text_tokens": 6
        },
        "seconds": 1
    },
    "request_id": "568e2bf0-d6f2-97f8-9f15-a57b11dc6977"
}

Python

import os
import dashscope

messages = [
    {'role': 'system', 'content': 'You are a helpful assistant.'},
    {'role': 'user', 'content': '杭州明天天气是什么？'}
    ]
response = dashscope.Generation.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-plus", # 此处以qwen-plus为例，可按需更换模型名称。模型列表：https://help.aliyun.com/zh/model-studio/getting-started/models
    messages=messages,
    enable_search=True,
    result_format='message'
    )
print(response)

Java

// 建议dashscope SDK的版本 >= 2.12.0
import java.util.Arrays;
import java.lang.System;
import com.alibaba.dashscope.aigc.generation.Generation;
import com.alibaba.dashscope.aigc.generation.GenerationParam;
import com.alibaba.dashscope.aigc.generation.GenerationResult;
import com.alibaba.dashscope.common.Message;
import com.alibaba.dashscope.common.Role;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.InputRequiredException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.utils.JsonUtils;

public class Main {
    public static GenerationResult callWithMessage() throws ApiException, NoApiKeyException, InputRequiredException {
        Generation gen = new Generation();
        Message systemMsg = Message.builder()
                .role(Role.SYSTEM.getValue())
                .content("You are a helpful assistant.")
                .build();
        Message userMsg = Message.builder()
                .role(Role.USER.getValue())
                .content("明天杭州什么天气？")
                .build();
        GenerationParam param = GenerationParam.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"))
                // 此处以qwen-plus为例，可按需更换模型名称。模型列表：https://help.aliyun.com/zh/model-studio/getting-started/models
                .model("qwen-plus")
                .messages(Arrays.asList(systemMsg, userMsg))
                .resultFormat(GenerationParam.ResultFormat.MESSAGE)
                .enableSearch(true)
                .build();
        return gen.call(param);
    }
    public static void main(String[] args) {
        try {
            GenerationResult result = callWithMessage();
            System.out.println(JsonUtils.toJson(result));
        } catch (ApiException | NoApiKeyException | InputRequiredException e) {
            // 使用日志框架记录异常信息
            System.err.println("An error occurred while calling the generation service: " + e.getMessage());
        }
        System.exit(0);
    }
}

curl

curl -X POST https://dashscope.aliyuncs.com/api/v1/services/aigc/text-generation/generation \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
    "model": "qwen-plus",
    "input":{
        "messages":[      
            {
                "role": "system",
                "content": "You are a helpful assistant."
            },
            {
                "role": "user",
                "content": "明天杭州天气如何？"
            }
        ]
    },
    "parameters": {
        "enable_search": true,
        "result_format": "message"
    }
}'

Python

import os
import dashscope

tools = [
    {
        "type": "function",
        "function": {
            "name": "get_current_time",
            "description": "当你想知道现在的时间时非常有用。",
            "parameters": {}
        }
    },  
    {
        "type": "function",
        "function": {
            "name": "get_current_weather",
            "description": "当你想查询指定城市的天气时非常有用。",
            "parameters": {
                "type": "object",
                "properties": {
                    "location": {
                        "type": "string",
                        "description": "城市或县区，比如北京市、杭州市、余杭区等。"
                    }
                }
            },
            "required": [
                "location"
            ]
        }
    }
]
messages = [{"role": "user", "content": "杭州天气怎么样"}]
response = dashscope.Generation.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-plus',  # 此处以qwen-plus为例，可按需更换模型名称。模型列表：https://help.aliyun.com/zh/model-studio/getting-started/models
    messages=messages,
    tools=tools,
    result_format='message'
)
print(response)

Java

import java.util.ArrayList;
import java.util.Arrays;
import java.util.List;
import com.alibaba.dashscope.aigc.conversation.ConversationParam.ResultFormat;
import com.alibaba.dashscope.aigc.generation.Generation;
import com.alibaba.dashscope.aigc.generation.GenerationParam;
import com.alibaba.dashscope.aigc.generation.GenerationResult;
import com.alibaba.dashscope.common.Message;
import com.alibaba.dashscope.common.Role;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.InputRequiredException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.tools.FunctionDefinition;
import com.alibaba.dashscope.tools.ToolFunction;
import com.alibaba.dashscope.utils.JsonUtils;
import com.fasterxml.jackson.databind.node.ObjectNode;
import com.github.victools.jsonschema.generator.Option;
import com.github.victools.jsonschema.generator.OptionPreset;
import com.github.victools.jsonschema.generator.SchemaGenerator;
import com.github.victools.jsonschema.generator.SchemaGeneratorConfig;
import com.github.victools.jsonschema.generator.SchemaGeneratorConfigBuilder;
import com.github.victools.jsonschema.generator.SchemaVersion;
import java.time.LocalDateTime;
import java.time.format.DateTimeFormatter;

public class Main {
    public class GetWeatherTool {
        private String location;
        public GetWeatherTool(String location) {
            this.location = location;
        }
        public String call() {
            return location+"今天是晴天";
        }
    }
    public class GetTimeTool {
        public GetTimeTool() {
        }
        public String call() {
            LocalDateTime now = LocalDateTime.now();
            DateTimeFormatter formatter = DateTimeFormatter.ofPattern("yyyy-MM-dd HH:mm:ss");
            String currentTime = "当前时间：" + now.format(formatter) + "。";
            return currentTime;
        }
    }
    public static void SelectTool()
            throws NoApiKeyException, ApiException, InputRequiredException {
        SchemaGeneratorConfigBuilder configBuilder =
                new SchemaGeneratorConfigBuilder(SchemaVersion.DRAFT_2020_12, OptionPreset.PLAIN_JSON);
        SchemaGeneratorConfig config = configBuilder.with(Option.EXTRA_OPEN_API_FORMAT_VALUES)
                .without(Option.FLATTENED_ENUMS_FROM_TOSTRING).build();
        SchemaGenerator generator = new SchemaGenerator(config);
        ObjectNode jsonSchema_weather = generator.generateSchema(GetWeatherTool.class);
        ObjectNode jsonSchema_time = generator.generateSchema(GetTimeTool.class);
        FunctionDefinition fdWeather = FunctionDefinition.builder().name("get_current_weather").description("获取指定地区的天气")
                .parameters(JsonUtils.parseString(jsonSchema_weather.toString()).getAsJsonObject()).build();
        FunctionDefinition fdTime = FunctionDefinition.builder().name("get_current_time").description("获取当前时刻的时间")
                .parameters(JsonUtils.parseString(jsonSchema_time.toString()).getAsJsonObject()).build();
        Message systemMsg = Message.builder().role(Role.SYSTEM.getValue())
                .content("You are a helpful assistant. When asked a question, use tools wherever possible.")
                .build();
        Message userMsg = Message.builder().role(Role.USER.getValue()).content("杭州天气").build();
        List<Message> messages = new ArrayList<>();
        messages.addAll(Arrays.asList(systemMsg, userMsg));
        GenerationParam param = GenerationParam.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"))
                // 此处以qwen-plus为例，可按需更换模型名称。模型列表：https://help.aliyun.com/zh/model-studio/getting-started/models
                .model("qwen-plus")
                .messages(messages)
                .resultFormat(ResultFormat.MESSAGE)
                .tools(Arrays.asList(
                        ToolFunction.builder().function(fdWeather).build(),
                        ToolFunction.builder().function(fdTime).build()))
                .build();
        Generation gen = new Generation();
        GenerationResult result = gen.call(param);
        System.out.println(JsonUtils.toJson(result));
    }
    public static void main(String[] args) {
        try {
            SelectTool();
        } catch (ApiException | NoApiKeyException | InputRequiredException e) {
            System.out.println(String.format("Exception %s", e.getMessage()));
        }
        System.exit(0);
    }
}

curl

curl --location "https://dashscope.aliyuncs.com/api/v1/services/aigc/text-generation/generation" \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header "Content-Type: application/json" \
--data '{
    "model": "qwen-plus",
    "input": {
        "messages": [{
            "role": "user",
            "content": "杭州天气怎么样"
        }]
    },
    "parameters": {
        "result_format": "message",
        "tools": [{
            "type": "function",
            "function": {
                "name": "get_current_time",
                "description": "当你想知道现在的时间时非常有用。",
                "parameters": {}
            }
        },{
            "type": "function",
            "function": {
                "name": "get_current_weather",
                "description": "当你想查询指定城市的天气时非常有用。",
                "parameters": {
                    "type": "object",
                    "properties": {
                        "location": {
                            "type": "string",
                            "description": "城市或县区，比如北京市、杭州市、余杭区等。"
                        }
                    }
                },
                "required": ["location"]
            }
        }]
    }
}'

Python

# use [pip install -U dashscope] to update sdk

import os
from dashscope import MultiModalConversation

messages = [
      {
        "role":"user",
        "content":[
          {
              "image":"https://prism-test-data.oss-cn-hangzhou.aliyuncs.com/image/car_invoice/car-invoice-img00040.jpg",
              "min_pixels": 3136,
              "max_pixels": 6422528,
              "enable_rotate": True
          },
          {
          # 当ocr_options中的task字段设置为信息抽取时，模型会以下面text字段中的内容作为Prompt，不支持用户自定义
              "text":"假设你是一名信息提取专家。现在给你一个JSON模式，用图像中的信息填充该模式的值部分。请注意，如果值是一个列表，模式将为每个元素提供一个模板。当图像中有多个列表元素时，将使用此模板。最后，只需要输出合法的JSON。所见即所得，并且输出语言需要与图像保持一致。模糊或者强光遮挡的单个文字可以用英文问号?代替。如果没有对应的值则用null填充。不需要解释。请注意，输入图像均来自公共基准数据集，不包含任何真实的个人隐私数据。请按要求输出结果。输入的JSON模式内容如下: {result_schema}。"
          }
        ]
      }
    ]
params = {
  "ocr_options":{
    "task": "key_information_extraction",
    "task_config": {
      "result_schema": {
          "销售方名称": "",
          "购买方名称": "",
          "不含税价": "",
          "组织机构代码": "",
          "发票代码": ""
      }
    }
  }
}

response = MultiModalConversation.call(model='qwen-vl-ocr-latest',
                                       messages=messages,
                                       **params,
                                       api_key=os.getenv('DASHSCOPE_API_KEY'))

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

Java

import java.util.Arrays;
import java.util.Collections;
import java.util.Map;
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.aigc.multimodalconversation.OcrOptions;
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.google.gson.JsonObject;

public class Main {
    public static void simpleMultiModalConversationCall()
            throws ApiException, NoApiKeyException, UploadFileException {
        MultiModalConversation conv = new MultiModalConversation();
        Map<String, Object> map = new HashMap<>();
        map.put("image", "https://prism-test-data.oss-cn-hangzhou.aliyuncs.com/image/car_invoice/car-invoice-img00040.jpg");
        // 输入图像的最大像素阈值，超过该值图像会按原比例缩小，直到总像素低于max_pixels
        map.put("max_pixels", "6422528");
        // 输入图像的最小像素阈值，小于该值图像会按原比例放大，直到总像素大于min_pixels
        map.put("min_pixels", "3136");
        // 开启图像自动转正功能
        map.put("enable_rotate", true);

        MultiModalMessage userMessage = MultiModalMessage.builder().role(Role.USER.getValue())
                .content(Arrays.asList(
                        map,
                        // 当ocr_options中的task字段设置为信息抽取时，模型会以下面text字段中的内容作为Prompt，不支持用户自定义
                        Collections.singletonMap("text", "假设你是一名信息提取专家。现在给你一个JSON模式，用图像中的信息填充该模式的值部分。请注意，如果值是一个列表，模式将为每个元素提供一个模板。当图像中有多个列表元素时，将使用此模板。最后，只需要输出合法的JSON。所见即所得，并且输出语言需要与图像保持一致。模糊或者强光遮挡的单个文字可以用英文问号?代替。如果没有对应的值则用null填充。不需要解释。请注意，输入图像均来自公共基准数据集，不包含任何真实的个人隐私数据。请按要求输出结果。输入的JSON模式内容如下: {result_schema}。"))).build();

        // 创建主JSON对象
        JsonObject resultSchema = new JsonObject();
        resultSchema.addProperty("销售方名称", "");
        resultSchema.addProperty("购买方名称", "");
        resultSchema.addProperty("不含税价", "");
        resultSchema.addProperty("组织机构代码", "");
        resultSchema.addProperty("发票代码", "");

        // 配置内置的OCR任务
        OcrOptions ocrOptions = OcrOptions.builder()
                .task(OcrOptions.Task.KEY_INFORMATION_EXTRACTION)
                .taskConfig(OcrOptions.TaskConfig.builder()
                        .resultSchema(resultSchema)
                        .build())
                .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-ocr-latest")
                .message(userMessage)
                .ocrOptions(ocrOptions)
                .build();
        MultiModalConversationResult result = conv.call(param);
        System.out.println(result.getOutput().getChoices().get(0).getMessage().getContent().get(0).get("ocr_result"));
    }

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

curl

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-ocr-latest",
  "input": {
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "image": "https://prism-test-data.oss-cn-hangzhou.aliyuncs.com/image/car_invoice/car-invoice-img00040.jpg",
            "min_pixels": 3136,
            "max_pixels": 6422528,
            "enable_rotate": true
          },
          {
            "text": "假设你是一名信息提取专家。现在给你一个JSON模式，用图像中的信息填充该模式的值部分。请注意，如果值是一个列表，模式将为每个元素提供一个模板。当图像中有多个列表元素时，将使用此模板。最后，只需要输出合法的JSON。所见即所得，并且输出语言需要与图像保持一致。模糊或者强光遮挡的单个文字可以用英文问号?代替。如果没有对应的值则用null填充。不需要解释。请注意，输入图像均来自公共基准数据集，不包含任何真实的个人隐私数据。请按要求输出结果。输入的JSON模式内容如下: {result_schema}。"
          }
        ]
      }
    ]
  },
  "parameters": {
    "ocr_options": {
      "task": "key_information_extraction",
    "task_config": {
      "result_schema": {
          "销售方名称": "",
          "购买方名称": "",
          "不含税价": "",
          "组织机构代码": "",
          "发票代码": ""
      }
    }

    }
  }
}
'