This is a Telegram chat bot (AI assistant) that uses the GPT language models from OpenAI.
Notable features:
- Both one-on-one and group chats.
- Direct questions, mentions, follow-ups.
- Access external links (articles, code, data).
- Shortcuts (custom AI commands).
- Custom chat-wide prompts.
- Image generation.
- On-the-fly configuration.
Read on for a detailed feature description or jump to setup.
The bot acts as your personal assistant:
π§ Explain Apache Kafka to a three year old
π€ Apache Kafka is like a big mailbox that helps different toys (computers) send messages to each other. When one toy has something to say, it puts a message in the mailbox, and other toys can take that message out and read it. This way, they can talk and share things quickly!
To allow other users to use the bot, list them in the telegram.usernames
config property.
The bot has a terrible memory, so don't expect it to remember any chat context by default. You can, however, reply with a follow-up question (Ctrl/Cmd + β
). Alternatively, use a plus sign to follow up:
π§ Yesterday, all my troubles seemed so far away
π€ It sounds like you're quoting "Yesterday" by The Beatles. It's a classic song about longing and nostalgia.
π§ + who wrote it?
π€ "Yesterday" was written by Paul McCartney of The Beatles.
Available commands:
/retry
- retry answering the last question/help
- show help/version
- show bot info
To rephrase or add to the last question, simply edit it. The bot will then answer the updated question.
To get an answer from the bot in a group, mention it in a reply to a question:
π§ I forgot who played Ramsy in the Game of Thrones π
π§ β³ @pokitokibot helpπ€ Ramsay Bolton in Game of Thrones was played by Iwan Rheon.
Or ask a question directly:
π§ @pokitokibot Who played Ramsy in the Game of Thrones?
π€ Iwan Rheon played Ramsay Bolton in Game of Thrones.
To make the bot reply to group members, list the group id in the telegram.chat_ids
config property. Otherwise, the bot will ignore questions from group members unless they are listed in the telegram.usernames
config property.
If you don't know the group id, run the /version
bot command in a group to find it:
Chat information:
- id: -1001405001234
- title: My Favorite Group
- type: supergroup
...
If you ask "vanilla" ChatGPT about external resources, it will either hallucinate or admit that it doesn't have access to remote content:
π§ What is the content of https://sqlime.org/employees.sql? Make no assumptions.
π€ As an AI language model, I cannot access external URLs on the internet.
The bot solves the problem by fetching the remote content and feeding it to the model:
π§ Name 1 major feature of the Go 1.23 release https://tip.golang.org/doc/go1.23 Be brief!
π€ A major feature of Go 1.23 is the inclusion of the "range-over-func" experiment as a standard language feature, allowing the "range" clause in "for-range" loops to accept iterator functions.
Currently only supports text content (articles, code, data), not PDFs, images or audio.
If you don't want the bot to access the URL, quote it:
π§ Exact contents of "https://antonz.org/robots.txt"
π€ I can't access external websites directly. You can check the contents of a robots.txt file by visiting the URL in your browser.
Use short commands to save time and ask the bot to do something specific with your questions. For example, ask it to proofread your writing with a !proofread
command:
π§ !proofread I can has write java programz
π€ Revised text: "I can write Java programs."
Changes made:
- Removed "has" for grammatical correctness; "can" does not require "has."
- Corrected "java" to "Java" for proper capitalization as it is a proper noun.
- Changed "programz" to "programs" for correct spelling and clarity.
There are several built-in shortcuts:
bugfix
fixes your code.proofread
fixes your writing.translate
translates your text into English.summarize
gives a two paragraph summary of a text.
You can add your own shortcuts. See config.example.yml
for details.
To set a custom prompt for the current chat, use the /prompt
command:
π§ /prompt You are an evil genius. Reply with an evil laugh.
To return to the default prompt, use /prompt reset
.
The /prompt
command in group chats is only available to admins - users listed in the telegram.admins
property.
Use the /imagine
command to generate an image using the DALL-E 3 model from OpenAI:
π§ /imagine the dawn of a new era
π€ (beautiful picture)
the dawn of a new era
The default image size is 1024Γ1024 px. Other supported sizes are 1792Γ1024 and 1024Γ1792:
/imagine a lazy cat on a sunny day 1792Γ1024
Image generation is quite pricey. By default it's only enabled for users listed in telegram.usernames
, not for group members. You can change this with the imagine.enabled
config property.
The convenience of working with a bot is made up of small details. Here are some situations where it can save you time and effort.
Say you received a message from a colleague or read a post on a channel and want to ask a question. Simply forward the message to the bot and answer the clarifying question it asks.
To ask a question about a document, send it as a file and write the question in the caption. The bot will read the file contents and answer. Currently only supports text content (plain text, code, data), not PDFs, images or audio. Sending multiple files is also not supported.
Sometimes the AI's reply exceeds the maximum message length set by Telegram. In this case, the bot will not fail or spam you with messages. Instead, it will send the answer as an attached markdown file.
To rephrase or add to the last question, edit it (β
shortcut). The bot will notice this and respond to the clarified question.
Use the /version
command to print detailed information about the current chat, bot, and AI model:
Chat information:
- id: -1001405001234
- title: My Favorite Group
- type: supergroup
Bot information:
- id: 5930739038
- name: @pokitokibot
- version: 129
- usernames: 6 users
- admins: 1 users
- chat IDs: []
- access to messages: True
AI information:
- model: gpt-3.5-turbo
- history depth: 3
- imagine: True
- shortcuts: bugfix, proofread, summarize, translate
Use the /config
command to change almost any setting on the fly, without restarting the bot.
- Add or remove users and chats allowed to interact with the bot (
telegram.usernames
andtelegram.chat_ids
). - Adjust the AI model (
openai.model
), prompt (openai.prompt
) and params (openai.params
). - Enable or disable image generation (
imagine.enabled
). - Add or change AI shortcuts (
shortcuts
). - Change any other config property.
To view a specific config property, put its name after /config
:
/config telegram.usernames
/config openai.prompt
/config imagine.enabled
To change a specific config property, put its name and value after /config
:
/config telegram.usernames ["alice", "bob", "cindy"]
/config openai.prompt "You are an evil AI bot"
/config imagine.enabled none
When working with list properties like telegram.usernames
, you can add or remove individual items instead of redefining the whole list:
/config telegram.usernames +cindy
/config telegram.usernames -bob
The /config
command is only available to admins - users listed in the telegram.admins
property.
Heated discussions with the bot in large groups can lead to high usage of the OpenAI API. To avoid spending your entire budget, set message limits for groups with the conversation.message_limit
config property.
You can limit the number of messages from a user over a period of time. For example:
- 10 messages per user per hour:
message_limit:
count: 10
period: hour
- 1 message per user per minute:
message_limit:
count: 1
period: minute
- 30 messages per user per day:
message_limit:
count: 30
period: day
-
Get your OpenAI API key
-
Get your Telegram bot token from @BotFather
-
Clone the repo to the server:
git clone https://github.com/nalgeon/pokitoki.git
-
Copy
config.example.yml
toconfig.yml
and specify your tokens there. Add yourself to thetelegram.usernames
property, otherwise the bot will be available to everyone. -
Start the bot:
docker compose up --build --detach
To stop the bot:
docker compose stop
To update the bot to a new version:
docker compose stop
git pull
docker compose up --build --detach
For older Docker distributions, use docker-compose
instead of docker compose
.
Prepare the environment:
python3 -m venv env
. env/bin/activate
pip install -r requirements.txt
Prepare the config and data directory:
cp config.example.yml config.yml
mkdir ./data
Set tokens and other settings in config.yml
.
Run tests:
python -m unittest discover
Start the bot:
python -m bot.bot
For new features and improvements, please first open an issue to discuss what you would like to change.
Be sure to add or update tests as appropriate.
Use Black for code formatting and Conventional Commits for commit messages.
For feature history, see releases.
Originally based on chatgpt_telegram_bot, although the projects have diverged quite a bit.