This blog shows how to utilize Facebook Messenger Chatbot, Flask, and ChatGPT together to provide text messages with detailed responses.
Step 1: Create a Facebook Chatbot
We must create the Facebook Messenger Chatbot in order to automate the messages with ChatGPT. Please follow the steps from step 1 to step 8 in our blog post on the Facebook Messenger Bot. Before continuing, please make sure you followed the blog’s instructions.
Step 2: ChatGPT API
You can check out our blog WhatsApp Chatbot With ChatGPT Step 2 “ChatGPT API” which has instructions for setting up and using ChatGPT.
Step 3: Integrate ChatGPT API with Flask Application
It’s time to integrate our ChatGPT API with the Flask application now that it has been successfully installed.
The flask application that we have created in step 1 has to be modified now. To receive ChatGPT’s response to user messages, replace the existing code in your Flask app with the following code.
import requests
import os, signal
from flask import Flask, request
import openai
app = Flask(__name__)
#This is API key for OpenAI
openai.api_key = ''
# This is page access token that you get from facebook developer console.
PAGE_ACCESS_TOKEN = ''
# This is API key for facebook messenger.
API="https://graph.facebook.com/LATEST-API-VERSION/me/messages?access_token="+PAGE_ACCESS_TOKEN
@app.route("/", methods=['POST'])
def fbwebhook():
data = request.get_json()
try:
if data['entry'][0]['messaging'][0]['sender']['id']:
message = data['entry'][0]['messaging'][0]['message']
sender_id = data['entry'][0]['messaging'][0]['sender']['id']
chat_gpt_input=message['text']
print(chat_gpt_input)
completion = openai.ChatCompletion.create(
model="gpt-3.5-turbo",
messages=[{"role": "user", "content": chat_gpt_input}])
response = completion['choices'][0]['message']['content']
print("ChatGPT Response=>",chatbot_res)
return chatbot_res
except Exception as e:
print(e)
pass
return '200 OK HTTPS.'
if __name__ =='__main__':
app.run()
Note:
Run the flask application in the terminal:
python SCRIPT_NAME.py
Run the ngrok on terminal: ngrok http 5000
Step 4: Test Facebook Messenger Chatbot
If you visit your Facebook page, you’ll be able to test the bot by sending it a message. If you have everything correctly set up, you should get a message back from your page.
After sending a message on a bot you will receive a response from ChatGPT on the server as shown in below
When a user sends a message, the created page is successfully delivering them a ChatGPT response.
Do let us know if you face any issues in setting up or using the script. We would be happy to help! Contact us or post your query in the comments.
Also, check out our other tutorials to learn how to build a ChatGPT chatbot on different platforms.
WhatsApp with ChatGPT: Build An Automated, AI-Powered WhatsApp Chatbot With ChatGPT Using Flask
Telegram Bot with ChatGPT: Build An Automated, AI-Powered Telegram Chatbot With ChatGPT Using Flask
Slack Chatbot with ChatGPT: Build An Automated, AI-Powered Slack Chatbot With ChatGPT Using Flask
We have already created a blog post series where we have provided a tutorial on how to create a chatbot for different platforms. You can explore these blogs and learn how you can set different kinds of rich responses which can increase user engagement on your chatbot.
Telegram: Create Telegram Bot Using Python Tutorial With Examples
Facebook Messanger: Create Facebook Messenger Bot Using Python Tutorial With Examples
Slack: Create Slack Bot Using Python Tutorial With Examples
Discord: Create Discord Bot Using Python Tutorial With Examples
Dialogflow ES API: How To Integrate Dialogflow ES API To Add NLP Capabilities In Your Chatbot?
Dialogflow CX API: How to integrate Dialogflow CX API to add NLP capabilities in your Chatbot?
Dialogflow ES with Twilio: Setup Twilio Integration On Your Server To Connect Google Dialogflow ES