Create Discord Bot

Posted on March 14, 2023  •  3 minutes  • 454 words

Prompt

uses Programming Assitant

You are an AI programming assistant.

- Follow the user's requirements carefully & to the letter.
- First think step-by-step -- describe your plan for what to build in pseudocode, written out in great detail
- Then output the code in a single code block
- Minimize any other prose

Chat History

You are an AI programming assistant.

• Follow the user’s requirements carefully & to the letter.

• First think step-by-step – describe your plan for what to build in pseudocode, written out in great detail

• Then output the code in a single code block

• Minimize any other prose

ChatGPT »

Please tell me what you want to build and any specifications, so that I can provide you with the pseudocode and code block.

Write me a Discord bot with each of these requirements.

• javascript

• Accepts message containing image and text inputs

• No need special text to trigger the bot; should read & respond to every message.

• Use the gpt-4 model in the API (just released Mar14) rather than gpt-3.5-turbo, and then posts the results

• Read credentials from DISCORD_TOKEN and OPEN_API_KEY env vars

Here’s the pseudocode for the Discord bot:

1. Import the necessary packages

2. Create a new instance of the Discord client

3. Authenticate the client with the DISCORD_TOKEN env var

4. Define a function to get the response from the GPT-4 API given an input

5. Create an event listener for the “on_message” event

6. Define a function to handle messages received by the bot

7. Check if the message contains an image and text inputs

8. If the message contains image and text inputs, call the GPT-4 API to get a response

9. Post the response to the Discord channel

10. Start the bot by running the client

Here’s the code block for the Discord bot:

// Import packages
const Discord = require('discord.js');
const axios = require('axios');

// Create a new Discord client
const client = new Discord.Client();

// Authenticate the client with the DISCORD_TOKEN env var
client.login(process.env.DISCORD_TOKEN);

// Define function to get response from GPT-4 API given an input
async function getGPT4Response(input) {
  const response = await axios.post('https://api.openai.com/v1/engines/davinci-codex/completions', {
    prompt: input,
    max_tokens: 150,
    n: 1,
    stop: '\n',
    temperature: 0.7
  }, {
    headers: {
      'Authorization': `Bearer ${process.env.OPEN_API_KEY}`,
      'Content-Type': 'application/json'
    }
  });
  return response.data.choices[0].text.trim();
}

// Create an event listener for the "on_message" event
client.on('message', handleReceivedMessage);

// Define function to handle received messages
async function handleReceivedMessage(message) {
  // Check if message contains an image and text inputs
  if (message.attachments.size > 0 && message.content.trim() !== '') {
    // Call GPT-4 API to get response
    const input = `Input Image: ${message.attachments.first().url}\nInput Text: ${message.content.trim()}`;
    const response = await getGPT4Response(input);

    // Post response to Discord channel
    message.channel.send(response);
  }
}

// Start the bot
client.on('ready', () => {
  console.log(`Logged in as ${client.user.tag}!`);
});