Integrate ChatGPT with Slack with few Easy Steps: Create your own Slack Chatbot

Step 4: Launch the Application

To run the application, you need to insert the three tokens (Slack Bot Token, Slack App Token, and OpenAI API Key) into the script provided below. This application listens to events in which the bot is tagged and responds by displaying a message indicating that the bot is working on an answer. The question is then sent to a GPT-3 model, and the resulting answer is returned to the user.

When you successfully execute the code to start the Bolt app, you will see a message “⚡️ Bolt app is running!” in your Python environment. This message is a signal that the app is currently active and functioning properly, ready to receive and process requests.

SLACK_BOT_TOKEN = “YOUR_TOKEN”
SLACK_APP_TOKEN = “YOUR_TOKEN”
OPENAI_API_KEY  = “YOUR_TOKEN”

import os
import openai
from slack_bolt.adapter.socket_mode import SocketModeHandler
from slack import WebClient
from slack_bolt import App

# Event API & Web API
app = App(token=SLACK_BOT_TOKEN)
client = WebClient(SLACK_BOT_TOKEN)

# This gets activated when the bot is tagged in a channel   @app.event(“app_mention”)
def handle_message_events(body, logger):
  # Log message
  print(str(body[“event”][“text”]).split(“>”)[1])

# Create prompt for ChatGPT
  prompt = str(body[“event”][“text”]).split(“>”)[1]

  # Let thre user know that we are busy with the request
  response = client.chat_postMessage(channel=body[“event”][“channel”],
                                  thread_ts=body[“event”][“event_ts”],
                                      text=f”Hello from your bot! :robot_face: \nThanks for your request,

I’m on it!”)

  # Check ChatGPT
  openai.api_key = OPENAI_API_KEY
  response = openai.Completion.create(
      engine=”text-davinci-003″,
      prompt=prompt,
      max_tokens=1024,
      n=1,
      stop=None,
      temperature=0.5).choices[0].text

   # Reply to thread
  response = client.chat_postMessage(channel=body[“event”][“channel”],
                                  thread_ts=body[“event”][“event_ts”],
                                      text=f”Here you go: \n{response}”)

if __name__ == “__main__”:
  SocketModeHandler(app, SLACK_APP_TOKEN).start()