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
/resetcommand - 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
/imagecommand - (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
/setinlinecommand
- To use this feature, enable inline queries for your bot in BotFather via the
- (NEW!) Track token usage per user - by @AlexHTW
- (NEW!) Get personal token usage statistics and cost per day/month via the
/statscommand - by @AlexHTW - (NEW!) User budgets and guest budgets - by @AlexHTW
- (NEW!) Stream support
- (NEW!) GPT-4 support
- If you have access to the GPT-4 API, simply change the
OPENAI_MODELparameter togpt-4
- If you have access to the GPT-4 API, simply change the
If you'd like to help, check out the issues section and contribute!
PRs are always welcome!
- Python 3.9+
- 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 required parameters as desired:
| Parameter | Description |
|---|---|
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) |
ADMIN_USER_IDS |
Telegram user IDs of admins. These users have access to special admin commands, information and no budget restrictions. Admin IDs don't have to be added to ALLOWED_TELEGRAM_USER_IDS. Note: by default, no admin ('-') |
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 (*) |
| Parameter | Description | Default value |
|---|---|---|
ENABLE_QUOTING |
Whether to enable message quoting in private chats | true |
ENABLE_IMAGE_GENERATION |
Whether to enable image generation via the /image command |
true |
ENABLE_TRANSCRIPTION |
Whether to enable transcriptions of audio and video messages | true |
MONTHLY_USER_BUDGETS |
A comma-separated list of $-amounts per user from list ALLOWED_TELEGRAM_USER_IDS to set custom usage limit of OpenAI API costs for each. Note: by default, no limits for anyone (*) |
* |
MONTHLY_GUEST_BUDGET |
$-amount as usage limit for all guest users. Guest users are users in group chats that are not in the ALLOWED_TELEGRAM_USER_IDS list. Value is ignored if no usage limits are set in user budgets (MONTHLY_USER_BUDGETS="*") |
100.0 |
PROXY |
Proxy to be used for OpenAI and Telegram bot (e.g. https://localhost:8080) |
- |
OPENAI_MODEL |
The OpenAI model to use for generating responses | gpt-3.5-turbo |
ASSISTANT_PROMPT |
A system message that sets the tone and controls the behavior of the assistant | You are a helpful assistant. |
SHOW_USAGE |
Whether to show OpenAI token usage information after each response | false |
STREAM |
Whether to stream responses. Note: incompatible, if enabled, with N_CHOICES higher than 1 |
true |
MAX_TOKENS |
Upper bound on how many tokens the ChatGPT API will return | 1200 |
MAX_HISTORY_SIZE |
Max number of messages to keep in memory, after which the conversation will be summarised to avoid excessive token usage | 15 |
MAX_CONVERSATION_AGE_MINUTES |
Maximum number of minutes a conversation should live since the last message, after which the conversation will be reset | 180 |
VOICE_REPLY_WITH_TRANSCRIPT_ONLY |
Whether to answer to voice messages with the transcript only or with a ChatGPT response of the transcript | true |
N_CHOICES |
Number of answers to generate for each input message. Note: setting this to a number higher than 1 will not work properly if STREAM is enabled |
1 |
TEMPERATURE |
Number between 0 and 2. Higher values will make the output more random | 1.0 |
PRESENCE_PENALTY |
Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far | 0 |
FREQUENCY_PENALTY |
Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far | 0 |
IMAGE_SIZE |
The DALL·E generated image size. Allowed values: "256x256", "512x512" or "1024x1024" | "512x512" |
GROUP_TRIGGER_KEYWORD |
If set, the bot in group chats will only respond to messages that start with this keyword | "" |
IGNORE_GROUP_TRANSCRIPTIONS |
If set to true, the bot will not process transcriptions in group chats | true |
TOKEN_PRICE |
$-price per 1000 tokens used to compute cost information in usage statistics (https://openai.com/pricing) | 0.002 |
IMAGE_PRICES |
A comma-separated list with 3 elements of prices for the different image sizes: "256x256", "512x512" and "1024x1024" | "0.016,0.018,0.02" |
TRANSCRIPTION_PRICE |
USD-price for one minute of audio transcription | 0.002 |
Check out the official API reference for more details.
Clone the repository and navigate to the project directory:
git clone https://github.com/n3d1117/chatgpt-telegram-bot.git
cd chatgpt-telegram-bot- Create a virtual environment:
python -m venv venv- Activate the virtual environment:
# For Linux or macOS:
source venv/bin/activate
# For Windows:
venv\Scripts\activate- Install the dependencies using
requirements.txtfile:
pip install -r requirements.txt- Use the following command to start the bot:
python bot/main.py
Run the following command to build and run the Docker image:
docker compose upYou can also use the Docker image from Docker Hub:
docker pull n3d1117/chatgpt-telegram-bot:latestor using the GitHub Container Registry:
docker pull ghcr.io/n3d1117/chatgpt-telegram-bot:latestThis 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.