API详情

from http import HTTPStatus
import dashscope


def simple_multimodal_conversation_call():
    """Simple single round multimodal conversation call.
    """
    messages = [
        {
            "role": "user",
            "content": [
                {"image": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"},
                {"text": "这是什么?"}
            ]
        }
    ]
    response = dashscope.MultiModalConversation.call(model='qwen-vl-plus',
                                                     messages=messages)
    # The response status_code is HTTPStatus.OK indicate success,
    # otherwise indicate request is failed, you can get error code
    # and message from code and message.
    if response.status_code == HTTPStatus.OK:
        print(response)
    else:
        print(response.code)  # The error code.
        print(response.message)  # The error message.


if __name__ == '__main__':
    simple_multimodal_conversation_call()

// 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;

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("text", "这是什么?"))).build();
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                .model(MultiModalConversation.Models.QWEN_VL_PLUS)
                .message(userMessage)
                .build();
        MultiModalConversationResult result = conv.call(param);
        System.out.println(result);
    }

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

from dashscope import MultiModalConversation


def call_with_local_file():
    """Sample of use local file.
       linux&mac file schema: file:///home/images/test.png
       windows file schema: file://D:/images/abc.png
    """
    local_file_path1 = 'file://The_local_absolute_file_path1'
    local_file_path2 = 'file://The_local_absolute_file_path1'
    messages = [{
        'role': 'system',
        'content': [{
            'text': 'You are a helpful assistant.'
        }]
    }, {
        'role':
        'user',
        'content': [
            {
                'image': local_file_path1
            },
            {
                'image': local_file_path2
            },
            {
                'text': '图片里有什么东西?'
            },
        ]
    }]
    response = MultiModalConversation.call(model='qwen-vl-plus', messages=messages)
    print(response)


if __name__ == '__main__':
    call_with_local_file()

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

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

public class MultiModalConversationLocalFile2 {
    /**
     * sample of use local file
     * Windows file format: file:///D:/test/images/test.png
     * Linux & Mac format: file://The_absolute_local_path
     * 
     */
    public static void callWithLocalFile()
            throws ApiException, NoApiKeyException, UploadFileException {
        String localFilePath1 = "file://The_file_absolute_path";
        String localFilePath2 = "file://The_file_absolute_path2"; 
        MultiModalConversation conv = new MultiModalConversation();
        // The content list elements must be mutable map, such as HashMap.
        MultiModalMessage userMessage = MultiModalMessage.builder().role(Role.USER.getValue())
        .content(Arrays.asList(new HashMap<String, Object>(){{put("image", localFilePath1);}},
                               new HashMap<String, Object>(){{put("image", localFilePath2);}},
                               new HashMap<String, Object>(){{put("text", "这是什么?");}})).build();
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                .model(MultiModalConversation.Models.QWEN_VL_PLUS)
                .message(userMessage)
                .build();
        Flowable<MultiModalConversationResult> result = conv.streamCall(param);
        result.blockingForEach(item -> {
            System.out.println(item);
        });
    }

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

from http import HTTPStatus
from dashscope import MultiModalConversation


def conversation_call():
    """Sample of multiple rounds of conversation.
    """
    messages = [
        {
            "role": "user",
            "content": [
                {"image": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"},
                {"text": "这是什么?"},
            ]
        }
    ]
    response = MultiModalConversation.call(model='qwen-vl-plus',
                                           messages=messages)
    # The response status_code is HTTPStatus.OK indicate success,
    # otherwise indicate request is failed, you can get error code
    # and message from code and message.
    if response.status_code == HTTPStatus.OK:
        print(response)
    else:
        print(response.code)  # The error code.
        print(response.message)  # The error message.
    messages.append({'role': response.output.choices[0].message.role,
                     'content': response.output.choices[0].message.content})
    messages.append({"role": "user",
                     "content": [
                         {"text": "她们在干什么?", }
                     ]})
    import json
    print(json.dumps(messages, ensure_ascii=False))
    response = MultiModalConversation.call(model='qwen-vl-plus',
                                           messages=messages)
    # The response status_code is HTTPStatus.OK indicate success,
    # otherwise indicate request is failed, you can get error code
    # and message from code and message.
    if response.status_code == HTTPStatus.OK:
        print(response)
    else:
        print(response.code)  # The error code.
        print(response.message)  # The error message.


if __name__ == '__main__':
    conversation_call()

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

import java.util.ArrayList;
import java.util.Arrays;
import java.util.Collections;
import java.util.List;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversation;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationParam;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationResult;
import com.alibaba.dashscope.common.MultiModalMessage;
import com.alibaba.dashscope.common.Role;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.exception.UploadFileException;

public class Main {
    private static final String modelName = "qwen-vl-plus";
    public static void MultiRoundConversationCall() throws ApiException, NoApiKeyException, UploadFileException {
        MultiModalConversation conv = new MultiModalConversation();
        MultiModalMessage systemMessage = MultiModalMessage.builder().role(Role.SYSTEM.getValue())
        .content(Arrays.asList(Collections.singletonMap("text", "You are a helpful assistant."))).build();

        MultiModalMessage userMessage = MultiModalMessage.builder().role(Role.USER.getValue())
        .content(Arrays.asList(Collections.singletonMap("image", "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"), 
        Collections.singletonMap("text", "图片里有什么动物?"))).build();
        List<MultiModalMessage> messages = new ArrayList<>();
        messages.add(systemMessage);
        messages.add(userMessage);
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                .model(modelName)
                .messages(messages)
                .build();
        MultiModalConversationResult result = conv.call(param);
        System.out.println(result);
        // add the result to conversation
        messages.add(result.getOutput().getChoices().get(0).getMessage());
        MultiModalMessage msg = MultiModalMessage.builder().role(Role.USER.getValue())
        .content(Arrays.asList(Collections.singletonMap("text", "图片动物是什么？"))).build();
        messages.add(msg);
        // new messages
        param.setMessages((List)messages);
        result = conv.call(param);
        System.out.print(result);
    }

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

from dashscope import MultiModalConversation


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


if __name__ == '__main__':
    simple_multimodal_conversation_call()

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

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

public class MultiModalConversationStream {
    public static void streamCall()
            throws ApiException, NoApiKeyException, UploadFileException {
        MultiModalConversation conv = new MultiModalConversation();
        // must create mutable map.
        MultiModalMessage userMessage = MultiModalMessage.builder().role(Role.USER.getValue())
        .content(Arrays.asList(new HashMap<String, Object>(){{put("image", "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg");}}, 
        new HashMap<String, Object>(){{put("text", "基于这幅图，讲一个故事");}})).build();
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                .model(MultiModalConversation.Models.QWEN_VL_PLUS)
                .message(userMessage)
                .build();
        Flowable<MultiModalConversationResult> result = conv.streamCall(param);
        result.blockingForEach(item -> {
            System.out.println(item);
        });
    }

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

{
    "status_code": 200,
    "request_id": "afbf4016-8704-965d-b98a-53ea46a06742",
    "code": "",
    "message": "",
    "output": {
        "text": null,
        "finish_reason": null,
        "choices": [
            {
                "finish_reason": null,
                "message": {
                    "role": "assistant",
                    "content": [
                        {
                            "text": "这是一个关于友情的故事。在这个故事中，有一只可爱的小狗，它非常喜欢和人类玩耍。一天，它和一个喜欢它的女孩一起去了海滩。他们在沙滩上玩得很开心，互相追逐，玩耍，甚至互相握手。在他们的快乐时光中，女孩给小狗一个饼干，小狗非常高兴地接受了。夕阳西下，他们坐在沙滩上，享受着这美好的时光，直到天黑。这个故事告诉我们，友情不分物种，只要我们用心去交流和理解，就能找到共同的乐趣。"
                        }
                    ]
                }
            }
        ]
    },
    "usage": {
        "input_tokens": 1282,
        "output_tokens": 107
    }
}