使用 Azure 自定义问题解答在同一个 Slack 线程上回复

Question

如果可能的话，我恳请您就这个话题提供帮助。

基于自定义问答的我的 Azure 机器人实际上已启动并运行： 根据知识固定问题我得到相应的答案。

这是我在 qnaBotWithMSI.js 文件中使用的实际代码：

const { ActivityHandler } = require('botbuilder');
class QnABotWithMSI extends ActivityHandler {
    /**
     *
     * @param {ConversationState} conversationState
     * @param {UserState} userState
     * @param {Dialog} dialog
     */
    constructor(conversationState, userState, dialog) {
        super();
        if (!conversationState) throw new Error('[QnABotWithMSI]: Missing parameter. conversationState is required');
        if (!userState) throw new Error('[QnABotWithMSI]: Missing parameter. userState is required');
        if (!dialog) throw new Error('[QnABotWithMSI]: Missing parameter. dialog is required');

        this.conversationState = conversationState;
        this.userState = userState;
        this.dialog = dialog;
        this.dialogState = this.conversationState.createProperty('DialogState');

        this.onMessage(async (context, next) => {
            console.log('Running dialog with Message Activity.');

            // Run the Dialog with the new message Activity.
            await this.dialog.run(context, this.dialogState);

            // By calling next() you ensure that the next BotHandler is run.
            await next();
        });
        // If a new user is added to the conversation:
        this.onMembersAdded(async (context, next) => {
            const membersAdded = context.activity.membersAdded;
            for (let cnt = 0; cnt < membersAdded.length; cnt++) {
                if (membersAdded[cnt].id !== context.activity.recipient.id) {
                    const defaultWelcome = process.env.DefaultWelcomeMessage;
                    if (defaultWelcome !== '') await context.sendActivity(defaultWelcome);
                    else await context.sendActivity('Welcome to the QnA Maker');
                }
            }
            await next();
        });
    }
    async run(context) {
        await super.run(context);
        // Save any state changes. The load happened during the execution of the Dialog.
        await this.conversationState.saveChanges(context, false);
        await this.userState.saveChanges(context, false);
    }
}

主要目标是在 Slack 上提出问题并让机器人回复。为此，可以通过 Azure Bot 进行通道集成。 然而，答案不是在同一个相应的消息线程上提供的，而是作为在用于集成的同一频道上发布的新消息提供的，其中已经提出了问题。

如果可以的话，请您建议如何编辑代码，以便在同一个“问题线程”上获得答案，而不是在频道中弹出新消息？

提前感谢您的帮助:)

上面提供的所有详细信息，我实际上没有找到合适的解决方案

Answer 1

为了确保您的 Azure 机器人在提出问题的同一个 Slack 线程中进行回复，您需要修改机器人代码以在传出活动中包含

replyToId

属性：

this.onMessage(async (context, next) => {
    console.log('Running dialog with Message Activity.');
    await this.dialog.run(context, this.dialogState);
    if (context.activity.conversation && context.activity.conversation.id) {
        const threadId = context.activity.conversation.id; 
        context.activity.replyToId = threadId; 
    }
    await next();
});

设置

replyToId

以确保响应作为 Slack 线程的一部分发送：

const response = await this.qnaMaker.getAnswers(context);

if (response.length > 0) {
    const replyText = response[0].answer;
    const replyActivity = {
        type: ActivityTypes.Message,
        text: replyText,
        replyToId: context.activity.id 
    };
    await context.sendActivity(replyActivity);
} else {
    await context.sendActivity({
        type: ActivityTypes.Message,
        text: 'No answers were found.',
        replyToId: context.activity.id 
    });
}

我参考了此链接，获取有关使用 Azure 自定义问答在机器人服务中回答问题的指南。

下面的代码创建一个机器人，可以使用常见问题解答中的内容回答问题。

机器人使用以下 Azure 认知服务自定义问答服务：

const path = require('path');

const ENV_FILE = path.join(__dirname, '.env');
require('dotenv').config({ path: ENV_FILE });

const restify = require('restify');

const {
    ActivityTypes,
    CloudAdapter,
    ConfigurationBotFrameworkAuthentication
} = require('botbuilder');

const { CustomQABot } = require('./bots/CustomQABot');

const botFrameworkAuthentication = new ConfigurationBotFrameworkAuthentication(process.env);

const adapter = new CloudAdapter(botFrameworkAuthentication);

adapter.onTurnError = async (context, error) => {
    const traceActivity = {
        type: ActivityTypes.Trace,
        timestamp: new Date(),
        name: 'onTurnError Trace',
        label: 'TurnError',
        value: `${ error }`,
        valueType: 'https://www.botframework.com/schemas/error'
    };
  
    console.error(`\n [onTurnError] unhandled error: ${ error }`);
    await context.sendActivity(traceActivity);

   
    await context.sendActivity('The bot encountered an error or bug.');
    await context.sendActivity('To continue ');
};

const bot = new CustomQABot();

const server = restify.createServer();
server.use(restify.plugins.bodyParser());

server.listen(process.env.port || process.env.PORT || 3978, function() {
    console.log(`\n${ server.name } listening to ${ server.url }`);
    console.log('\nGet Bot Framework Emulator: https://aka.ms/botframework-emulator');
});

server.post('/api/messages', async (req, res) => {
    
    await adapter.process(req, res, (context) => bot.run(context));
});

输出：