Awesome

ChatGPT Telegram Bot in AWS Lambda

This a Telegram bot that lets you chat with ChatGPT. This bot is created using the brand new ChatGPT API. The Telegram bot is deployed in completely serverless in AWS Lambda. No need to setup a local server or do login in the browser.

Features

New ChatGPT API support. :brain:
Voice messages support! :fire:
Markdown rendering support.

Initial Setup

Create an OpenAI account and get an API Key.
Create an AWS account.
Setup your Telegram bot. You can follow this instructions to get your token.

<details> [<img src="./img/session_token.png" width="500"/>](/img/session_token.png) </details>

To enable support for voice messages you need to create a S3 bucket in your AWS account.

Go to the top search bar and write S3.

<details> [<img src="./img/s3_browser.png" width="500"/>](/img/s3_browser.png) </details>

Click the Create Bucket button.

<details> [<img src="./img/create_bucket_button.png" width="500"/>](/img/create_bucket_button.png) </details>

Configure the creation of your bucket. The name must be unique worldwide. Scroll to bottom and click Create Bucket and don't change any other configuration.

<details> [<img src="./img/create_bucket_config.png" width="500"/>](/img/create_bucket_config.png) </details>

Go to .chalice/config.json and stablish the configurations:

TELEGRAM_TOKEN with your Telegram token.
OPENAI_API_KEY with the value of your Open AI API Token.
VOICE_MESSAGES_BUCKET with the bucket name you created previously.

Installation

Install Python using pyenv or your prefered Python installation.
Create a virtual environment: python3 -m venv .venv.
Activate you virtual environment: source .venv/bin/activate.
Install dependencies: pip install -r requirements.txt.
Install the AWS CLI and configure your credentials.

Deployment

Run chalice deploy.
Go to the AWS Console -> Lambda -> chatgpt-telegram-bot-dev-message-handler-lambda -> Configuration -> Function URL.
Click Create Function URL and set Auth type to NONE.
Copy the created function URL.
Stablish your Telegram webhook to point to you AWS Lambda running curl --request POST --url https://api.telegram.org/bot<YOUR_TELEGRAM_TOKEN>/setWebhook --header 'content-type: application/json' --data '{"url": "YOUR_FUNCTION_URL"}'

Great! Everything is setup :) Now go to Telegram and find your bot name and use ChatGPT from there!

Coming soon!

Decoupled Token refresh in conversation.
Increase response performance.
Error handling from ChatGPT services.
Deploy solution with one-click using CloudFormation.