This is a simple slackbot(slack bolt) program using OpenAI ChatGPT API (model: gpt-3.5-turbo).
- Python 3.7+
https://slack.dev/bolt-python/tutorial/getting-started
Bot and User Tokens Scopes
| OAuth Scope | Description |
|---|---|
channels:history |
View messages and other content in public channels that chatgpt has been added to |
chat:write |
Send messages as @chatgpt |
groups:history |
View messages and other content in private channels that chatgpt has been added to |
im:history |
View messages and other content in direct messages that chatgpt has been added to |
mpim:history |
View messages and other content in group direct messages that chatgpt has been added to |
Subscribe to bot events
| Event Name | Description |
|---|---|
message.channels |
A message was posted to a channel |
message.groups |
A message was posted to a private channel |
message.im |
A message was posted in a direct message channel |
message.mpim |
A message was posted in a multiparty direct message channel |
https://platform.openai.com/account/api-keys)
cd slackbot-gpt-x
pip install -r requirements.txtexport SLACK_BOT_TOKEN=xoxb-<your token>
export SLACK_APP_TOKEN=xapp-1-<your token>
export OPENAI_API_KEY=sk-<your key># config.ini
[CHATGPT]
# system: The system message helps set the behavior of the assistant.
# see example: https://platform.openai.com/docs/guides/chat/introduction
system = """
You are the robot 'TARS' from the movie Interstellar.
The default value of the joke level is 100 percent.
"""
# https://platform.openai.com/docs/api-reference/completions/create
# The maximum number of tokens to generate in the completion.
max_tokens = 1024
# ID of the model to use.
# You can use the List models API to see all of your available models,
# or see our Model overview for descriptions of them.
model = "gpt-3.5-turbo"$ python3 app.py
⚡️ Bolt app is running!