ChatGpt intergration

[SILLEN 0]

@sdetweil yea i guess but how in the world would you make it send just the phrase after chatgpt is said. in other words i have no idea how the recipie file should be coded

[sdetweil]

@SILLEN-0 you said you understood recipe

[SILLEN 0]

@sdetweil maybe i formulated it bad. i know how the recipie structure should look like and i can make simple recipies but having the notification only send everything after “chatgpt” that i have no idea how too do. as i said i am a beginner in coding and trying my best

[sdetweil]

@SILLEN-0 look at the memo and selfie shoot recipies

memo gets the rest of the words
selfie shoot ‘command’ is to send a notification

when the ‘command’ function is invoked it gets params… ie, the rest of the words

[SILLEN 0]

@sdetweil ok hello. alot of things have happend in the last week. i have got somthing that should be working but i had too fix abunch of errors in the code. but for the last couple of days i have been stuck on this perticular error in my code:

0|MagicMirror  | [25.01.2023 21:05.25.175] [LOG]   Error in getResponse:  RangeError: Maximum call stack size exceeded
0|MagicMirror  |     at isBinary (/home/pi/MagicMirror/node_modules/socket.io-parser/build/cjs/is-binary.js:22:18)
0|MagicMirror  |     at hasBinary (/home/pi/MagicMirror/node_modules/socket.io-parser/build/cjs/is-binary.js:40:9)
0|MagicMirror  |     at hasBinary (/home/pi/MagicMirror/node_modules/socket.io-parser/build/cjs/is-binary.js:49:63)
0|MagicMirror  |     at hasBinary (/home/pi/MagicMirror/node_modules/socket.io-parser/build/cjs/is-binary.js:49:63)
0|MagicMirror  |     at hasBinary (/home/pi/MagicMirror/node_modules/socket.io-parser/build/cjs/is-binary.js:49:63)
0|MagicMirror  |     at hasBinary (/home/pi/MagicMirror/node_modules/socket.io-parser/build/cjs/is-binary.js:49:63)
0|MagicMirror  |     at hasBinary (/home/pi/MagicMirror/node_modules/socket.io-parser/build/cjs/is-binary.js:49:63)
0|MagicMirror  |     at hasBinary (/home/pi/MagicMirror/node_modules/socket.io-parser/build/cjs/is-binary.js:49:63)
0|MagicMirror  |     at hasBinary (/home/pi/MagicMirror/node_modules/socket.io-parser/build/cjs/is-binary.js:49:63)
0|MagicMirror  |     at hasBinary (/home/pi/MagicMirror/node_modules/socket.io-parser/build/cjs/is-binary.js:49:63)

the internet says that it is probobally a part of the code calling itself but i just cant seem too find anything. it may be super clear what the issue is here but i really cant seem too find the cause of the error. help would be greatly apprecieted. here is my code:

chatgpt.js:

Module.register("chatgpt",{
    defaults: {
        question: "What is the weather like today?",
    },

    start: function() {
        console.log("Starting module: " + this.name);
        this.question = this.config.question;
    },

    notificationReceived: function(notification, payload) {
        if(notification === "ASK_QUESTION") {
            this.question = payload.question;
            console.log("Received question: " + this.question);
            this.sendSocketNotification("ASK_QUESTION", this.question);
        }
    },

    socketNotificationReceived: function(notification, payload) {
        if(notification === "RESPONSE") {
            this.answer = payload.answer;
            console.log("Received answer: " + this.answer);
            console.log("Calling updateDom");
            this.updateDom();
        } else {
            console.log("Unhandled notification: " + notification);
            console.log("Payload: " + payload);
        }
    },

    getDom: function() {
        var wrapper = document.createElement("div");
        var question = document.createElement("div");
        var answer = document.createElement("div");

        if (this.answer) {
            answer.innerHTML = this.answer;
        } else {
            answer.innerHTML = "Ask me something";
        }

        question.innerHTML = this.question;
        wrapper.appendChild(question);
        wrapper.appendChild(answer);

        return wrapper;
    },
});

node_helper.js:

const NodeHelper = require("node_helper");
const { Configuration, OpenAIApi } = require("openai");

module.exports = NodeHelper.create({
    start: function() {
        console.log("Starting node helper for: " + this.name);
        this.configuration = new Configuration({
            apiKey: "XXXXXXXXXXXXXXXXXXXXXXXXXX",
        });
        this.openai = new OpenAIApi(this.configuration);
    },

    // Send a message to the chatGPT API and receive a response
    getResponse: function(prompt) {
        return new Promise(async (resolve, reject) => {
            try {
                const response = await this.openai.createCompletion({
                    model: "text-davinci-003",
                    prompt: prompt,
                    temperature: 0.7,
                });
                console.log("Received response from API: ", response);
                resolve(response);
            } catch (error) {
                console.log("Error in getResponse: ", error);
                reject(error);
            }
        });
    },


  // Handle socket notifications
    socketNotificationReceived: function(notification, payload) {
        if (notification === "ASK_QUESTION") {
            console.log("Received ASK_QUESTION notification with payload: ", payload);
            this.getResponse(payload)
                .then((response) => {
                    // create a new object and update the answer property
                    var responsePayload = {answer: response};
                    console.log("Sending RESPONSE notification with payload: ", responsePayload);
                    this.sendSocketNotification("RESPONSE", responsePayload);
                })
                .catch((error) => {
                    console.log("Error in getResponse: ", error);
                });
        }
    },

});

the api call is being made and everything else is working but as soon as i say “jarvis chatgpt say banana” or any other input i get the error

[sdetweil]

@SILLEN-0 what is the data format of the response?, text, json, ???

you said

‘say banana’

did it return a wav file?

if u add the MMM-Logging module, then u can see all the logs in one place (output of npm start)

socket-io requires a serializable object

says error is in getResponse() function,

so, did your module get multiple requests concurrently and send them on?

I would make the notification string more specific. ‘gpt question’

there are hundreds of notifications going on, possible there was another module sending that same string…

[sdetweil]

@SILLEN-0 also that is the error part of the pm2 logs --lines output

when I am developing

I don’t use pm2,
I just do

npm start  >somefile.txt 2>&1

in the MagicMirror folder

then all the console output is in one file.
adding the logging module will reflect all the modulename.js log statements too

AND you can debug on the mm UI , ctrl-shift-i,
select the sources tab, find your module name.js in the left nav,

and you can put stops on lines of code and step thru it

[SILLEN 0]

@sdetweil hey. I’m sorry for not being able too answer but i have other stuff going on and a math test coming up. The text is sent over as a string and the module does recieved the string and gets a response from the API it is after that the issue is caused. I Google the error and people say that there is probably a loop in the code somewhere. I will try with the debug module when i have time. I really want too get this too work.

[sdetweil]

@SILLEN-0 the data back from the api looks like this

    status: 200,
    statusText: 'OK',
    headers: {
      date: 'Sun, 29 Jan 2023 23:56:49 GMT',
      'content-type': 'application/json',
      'content-length': '343',
      connection: 'close',
      'access-control-allow-origin': '*',
      'cache-control': 'no-cache, must-revalidate',
      'openai-model': 'text-davinci-003',
      'openai-organization': 'user-ieyrbalt3azhd9sd82splktg',
      'openai-processing-ms': '2790',
      'openai-version': '2020-10-01',
      'strict-transport-security': 'max-age=15724800; includeSubDomains',
      'x-request-id': 'd341b29147db89ee20886107e22b41a4'
    },
    config: {
      transitional: [Object],
      adapter: [Function: httpAdapter],
      transformRequest: [Array],
      transformResponse: [Array],
      timeout: 0,
      xsrfCookieName: 'XSRF-TOKEN',
      xsrfHeaderName: 'X-XSRF-TOKEN',
      maxContentLength: -1,
      maxBodyLength: -1,
      validateStatus: [Function: validateStatus],
      headers: [Object],
      method: 'post',
      data: '{"model":"text-davinci-003","prompt":"What is the weather like today?","temperature":0.7}',
      url: 'https://api.openai.com/v1/completions'
    },
    request: ClientRequest {
      _events: [Object: null prototype],
      _eventsCount: 7,
      _maxListeners: undefined,
      outputData: [],
      outputSize: 0,
      writable: true,
      destroyed: false,
      _last: true,
      chunkedEncoding: false,
      shouldKeepAlive: false,
      maxRequestsOnConnectionReached: false,
      _defaultKeepAlive: true,
      useChunkedEncodingByDefault: true,
      sendDate: false,
      _removedConnection: false,
      _removedContLen: false,
      _removedTE: false,
      _contentLength: null,
      _hasBody: true,
      _trailer: '',
      finished: true,
      _headerSent: true,
      _closed: false,
      socket: [TLSSocket],
      _header: 'POST /v1/completions HTTP/1.1\r\n' +
        'Accept: application/json, text/plain, */*\r\n' +
        'Content-Type: application/json\r\n' +
        'User-Agent: OpenAI/NodeJS/3.1.0\r\n' +
        'Authorization: Bearer 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\r\n' +
        'Content-Length: 89\r\n' +
        'Host: api.openai.com\r\n' +
        'Connection: close\r\n' +
        '\r\n',
      _keepAliveTimeout: 0,
      _onPendingData: [Function: nop],
      agent: [Agent],
      socketPath: undefined,
      method: 'POST',
      maxHeaderSize: undefined,
      insecureHTTPParser: undefined,
      path: '/v1/completions',
      _ended: true,
      res: [IncomingMessage],
      aborted: false,
      timeoutCb: null,
      upgradeOrConnect: false,
      parser: null,
      maxHeadersCount: null,
      reusedSocket: false,
      host: 'api.openai.com',
      protocol: 'https:',
      _redirectable: [Writable],
      [Symbol(kCapture)]: false,
      [Symbol(kNeedDrain)]: false,
      [Symbol(corked)]: 0,
      [Symbol(kOutHeaders)]: [Object: null prototype],
      [Symbol(kUniqueHeaders)]: null
    },
    data: {
      id: 'cmpl-6eBpQkPEmW4z1PoxRTTprs8Lhoqn4',
      object: 'text_completion',
      created: 1675036608,
      model: 'text-davinci-003',
      choices: [Array],
      usage: [Object]
    }
  }

  answer: {
    status: 200,
    statusText: 'OK',
    headers: {
      date: 'Sun, 29 Jan 2023 23:56:49 GMT',
      'content-type': 'application/json',
      'content-length': '343',
      connection: 'close',
      'access-control-allow-origin': '*',
      'cache-control': 'no-cache, must-revalidate',
      'openai-model': 'text-davinci-003',
      'openai-organization': 'user-ieyrbalt3azhd9sd82splktg',
      'openai-processing-ms': '2790',
      'openai-version': '2020-10-01',
      'strict-transport-security': 'max-age=15724800; includeSubDomains',
      'x-request-id': 'd341b29147db89ee20886107e22b41a4'
    },
    config: {
      transitional: [Object],
      adapter: [Function: httpAdapter],
      transformRequest: [Array],
      transformResponse: [Array],
      timeout: 0,
      xsrfCookieName: 'XSRF-TOKEN',
      xsrfHeaderName: 'X-XSRF-TOKEN',
      maxContentLength: -1,
      maxBodyLength: -1,
      validateStatus: [Function: validateStatus],
      headers: [Object],
      method: 'post',
      data: '{"model":"text-davinci-003","prompt":"What is the weather like today?","temperature":0.7}',
      url: 'https://api.openai.com/v1/completions'
    },
    request: ClientRequest {
      _events: [Object: null prototype],
      _eventsCount: 7,
      _maxListeners: undefined,
      outputData: [],
      outputSize: 0,
      writable: true,
      destroyed: false,
      _last: true,
      chunkedEncoding: false,
      shouldKeepAlive: false,
      maxRequestsOnConnectionReached: false,
      _defaultKeepAlive: true,
      useChunkedEncodingByDefault: true,
      sendDate: false,
      _removedConnection: false,
      _removedContLen: false,
      _removedTE: false,
      _contentLength: null,
      _hasBody: true,
      _trailer: '',
      finished: true,
      _headerSent: true,
      _closed: false,
      socket: [TLSSocket],
      _header: 'POST /v1/completions HTTP/1.1\r\n' +
        'Accept: application/json, text/plain, */*\r\n' +
        'Content-Type: application/json\r\n' +
        'User-Agent: OpenAI/NodeJS/3.1.0\r\n' +
        'Authorization: Bearer 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\r\n' +
        'Content-Length: 89\r\n' +
        'Host: api.openai.com\r\n' +
        'Connection: close\r\n' +
        '\r\n',
      _keepAliveTimeout: 0,
      _onPendingData: [Function: nop],
      agent: [Agent],
      socketPath: undefined,
      method: 'POST',
      maxHeaderSize: undefined,
      insecureHTTPParser: undefined,
      path: '/v1/completions',
      _ended: true,
      res: [IncomingMessage],
      aborted: false,
      timeoutCb: null,
      upgradeOrConnect: false,
      parser: null,
      maxHeadersCount: null,
      reusedSocket: false,
      host: 'api.openai.com',
      protocol: 'https:',
      _redirectable: [Writable],
      [Symbol(kCapture)]: false,
      [Symbol(kNeedDrain)]: false,
      [Symbol(corked)]: 0,
      [Symbol(kOutHeaders)]: [Object: null prototype],
      [Symbol(kUniqueHeaders)]: null
    },
    data: {
      id: 'cmpl-6eBpQkPEmW4z1PoxRTTprs8Lhoqn4',
      object: 'text_completion',
      created: 1675036608,
      model: 'text-davinci-003',
      choices: [Array],
      usage: [Object]
    }
  }

i don’t see the text of the answer

[PraiseU]

@sdetweil Hey any updates on this?

[PraiseU]

@sdetweil Do you have any updates regarding the speech capture process?

[sdetweil]

@PraiseU I wasn’t working on any speech capture integration.

I outlined the possibilities

[PraiseU]

@sdetweil Oh okay! I found this Module https://github.com/TheStigh/MMM-VoiceCommander. Do you think it can be useful? or does it still have the problem with accuracy?

[sdetweil]

@PraiseU said in ChatGpt intergration:

@sdetweil Oh okay! I found this Module https://github.com/TheStigh/MMM-VoiceCommander. Do you think it can be useful? or does it still have the problem with accuracy?

yes, it is built on mmm-voice

[PraiseU]

@sdetweil Can you shed some light on what you mean by this “this is why the MMM-GoogleAssistant provides mechanisms (recipe) to use the captured text for non- google uses” And how can i approach this? Thanks a lot

[sdetweil]

@PraiseU it’s exactly what it says.

GoogleAssistant collects text from voice.
but many voice commands are not directed at Google itself. ($search, play, turn on/off lights…)

so, if you write a recipe you can direct the text to other purposes

[PraiseU]

@sdetweil Oh Okay so If I was to say “GPT Explain software engineering” It will get the text and I can forward it to the module it needs to go to? Do you ahave an examples that can help?

[sdetweil]

@PraiseU i mentioned how to do that before

[PraiseU]

@sdetweil I think you mis-understood my question? I meant to ask how does the recipes work? Like whats the logic behind it?

[sdetweil]

@PraiseU come on… think

and investigate, look at the files. maybe his wiki

if you wanted to take arbitrary text that means nothing to YOUR app, and let others do something, how would you do it?

then make it general purpose.