A Telegram bot that integrates with OpenAI's official ChatGPT APIs to provide answers. Ready to use with minimal configuration required.

• Support markdown in answers
• Reset conversation with the /reset command
• Typing indicator while generating a response
• Access can be restricted by specifying a list of allowed users
• Docker and Proxy support
• (NEW!) Image generation using DALL·E via the /image command
• (NEW!) Transcribe audio and video messages using Whisper (may require ffmpeg)
• (NEW!) Automatic conversation summary to avoid excessive token usage (fixes #34)
• (NEW!) Group chat support with inline queries
  • To use this feature, enable inline queries for your bot in BotFather via the /setinline command
• (NEW!) Track token usage per user (stored in /token_usage/user_id.json) - by @AlexHTW
• (NEW!) Get personal token usage statistics and cost per day/month via the /stats command - by @AlexHTW
• (NEW!) Group chat trigger keyword - by @tracking

• Add stream support (#43)
• Handle responses longer than telegram message limit (#44)
• Summarise conversation if (prompt_tokens + max_tokens) > 4096 (#45)

PRs are always welcome!

• Python 3.10+ and Pipenv
• A Telegram bot and its token (see tutorial)
• An OpenAI account (see configuration section)

Customize the configuration by copying .env.example and renaming it to .env, then editing the parameters as desired:

OPENAI_API_KEY="YOUR_OPENAI_API_KEY"
TELEGRAM_BOT_TOKEN="YOUR_TELEGRAM_BOT_TOKEN"

# Optional parameters
ALLOWED_TELEGRAM_USER_IDS="USER_ID_1,USER_ID_2,..." # Defaults to "*" (everyone)
PROXY="YOUR_PROXY" # e.g. "http://localhost:8080", defaults to none
ASSISTANT_PROMPT="Custom prompt" # Defaults to "You are a helpful assistant."
SHOW_USAGE=true # Defaults to false
MAX_TOKENS=2000 # Defaults to 1200
MAX_HISTORY_SIZE=15 # Defaults to 10
MAX_CONVERSATION_AGE_MINUTES=120 # Defaults to 180 (3h)
VOICE_REPLY_WITH_TRANSCRIPT_ONLY=false # Defaults to true
N_CHOICES=1 # Defaults to 1
TEMPERATURE=1.0 # Defaults to 1.0
IMAGE_SIZE="256x256" # Defaults to 512x512
GROUP_TRIGGER_KEYWORD="@bot" # Defaults to "" (no keyword required)
TOKEN_PRICE=0.002 # Defaults to 0.002, current price: https://openai.com/pricing
IMAGE_PRICES="0.016,0.018,0.02" # Defaults to OpenAI Dall-E pricing for sizes 256x256,512x512,1024x1024
TRANSCRIPTION_PRICE=0.006 # Defaults to minute price of OpenAI Whisper of 0.006

• OPENAI_API_KEY: Your OpenAI API key, you can get it from here
• TELEGRAM_BOT_TOKEN: Your Telegram bot's token, obtained using BotFather (see tutorial)
• ALLOWED_TELEGRAM_USER_IDS: A comma-separated list of Telegram user IDs that are allowed to interact with the bot (use getidsbot to find your user ID). Note: by default, everyone is allowed (*)
• PROXY: Proxy to be used for OpenAI and Telegram bot
• ASSISTANT_PROMPT: A system message that sets the tone and controls the behavior of the assistant
• SHOW_USAGE: Whether to show OpenAI token usage information after each response
• MAX_TOKENS: Upper bound on how many tokens the ChatGPT API will return
• MAX_HISTORY_SIZE: Max number of messages to keep in memory, after which the conversation will be summarised to avoid excessive token usage (#34)
• MAX_CONVERSATION_AGE_MINUTES: Maximum number of minutes a conversation should live, after which the conversation will be reset to avoid excessive token usage
• VOICE_REPLY_WITH_TRANSCRIPT_ONLY: Whether to answer to voice messages with the transcript only or with a ChatGPT response of the transcript (#38)
• N_CHOICES: Number of answers to generate for each input message
• TEMPERATURE: Number between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic
• IMAGE_SIZE: The DALL·E generated image size. Allowed values: "256x256", "512x512", or "1024x1024"
• GROUP_TRIGGER_KEYWORD: If set, the bot will only respond to messages that start with this keyword. This is useful for bots added to groups with privacy mode disabled. Note: by default, no keyword is required ("")
• TOKEN_PRICE: USD-price per 1000 tokens for cost information in usage statistics

{
    # 'gpt-3.5-turbo' or 'gpt-3.5-turbo-0301'
    'model': 'gpt-3.5-turbo',

    # Number between -2.0 and 2.0. Positive values penalize new tokens based on whether
    # they appear in the text so far, increasing the model's likelihood to talk about new topics. Defaults to 0
    'presence_penalty': 0,
    
    # Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing
    # frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim. Defaults to 0
    'frequency_penalty': 0
}

Check out the official API reference for more details.

1. Clone the repository and navigate to the project directory:

git clone https://github.com/n3d1117/chatgpt-telegram-bot.git
cd chatgpt-telegram-bot

2. Create a new virtual environment with Pipenv and install the required dependencies:

pipenv install

3. Activate the virtual environment:

pipenv shell

4. Use the following command to start the bot:

python main.py

2. Run the following command to build and run the Docker image:

docker-compose up

• ChatGPT from OpenAI
• python-telegram-bot
• jiaaro/pydub

This is a personal project and is not affiliated with OpenAI in any way.

This project is released under the terms of the GPL 2.0 license. For more information, see the LICENSE file included in the repository.