Are you ready to elevate your communication game? Introducing a transformative app for Slack users that integrates seamlessly with ChatGPT. Designed to optimize your planning and writing processes, this app leverages the power of AI technology to enhance your interactions within Slack channels.

Getting Started

To explore this app’s functionality, you can install the live demo, personally hosted by [@seratch](https://github.com/seratch). For companies using Slack, we recommend deploying it on your infrastructure for maximum control and confidentiality.

How It Works

Interacting with ChatGPT is as easy as having a chat! The bot remembers your previous messages, allowing for fluid conversation. Let’s dive into a realistic scenario:

Imagine you need to generate a business email for your manager. You simply initiate a conversation with ChatGPT in a channel thread. No need for a perfectly crafted question—adjusting your requests after the bot’s initial response is effective. Isn’t that cool?

Three Supported Interfaces

The app provides three ways to interact with ChatGPT:

• Channel Thread: The most common method where you mention the bot in a thread’s initial message.
• 1:1 DM: For private queries, just send a message in a direct message without mentioning the bot.
• Home Tab: Use quick proofreader and prompt dialogs for speedy feedback, ideal for mobile use.

Channel Thread Communication

Start a conversation by mentioning the bot in a thread. After that, it’s all about natural conversation!

Private Communication

In a 1:1 DM, you can interact privately without the need to mention the bot—perfect for sensitive topics.

Using the Home Tab

The Home tab includes quick-proofreading features and a free prompt sender, making it efficient to send inquiries to OpenAI.

Installing the App Locally

Ready to run the app on your local machine? Here’s what you need to do:

• Create a new Slack app using the manifest-dev.yml file.
• Install the app into your Slack workspace.
• Retrieve your OpenAI API key at OpenAI API Keys.
• Start the app using the following commands:

bash
# Create app-level token with connections:write scope
export SLACK_APP_TOKEN=xapp-1-...

# Install the app into your workspace to grab this token
export SLACK_BOT_TOKEN=xoxb-...

# Visit OpenAI API Keys for this token
export OPENAI_API_KEY=sk-...

# Optional configurations can follow...

Running the App for Corporate Workspaces

For corporate environments, confidentiality is key. This app is open-sourced, so you’re welcome to modify it to fit your infrastructure. Post local development, you can deploy the app using a Dockerfile that establishes WebSocket connections with Slack, eliminating the need for a public URL.

Troubleshooting

If you encounter issues, here are a few steps you can take:

• Check your Slack app configuration for any errors.
• Ensure your API keys are correct and have the necessary permissions.
• Review logs for potential error messages that can guide you to a solution.
• Restart the app after making configuration changes.

For more insights, updates, or to collaborate on AI development projects, stay connected with fxis.ai.

Contribute to the Project

Feel free to contribute! Keep the following in mind when making changes:

• Avoid breaking changes unless absolutely necessary—start a GitHub discussion for significant alterations.
• Write unit tests for your changes, especially for internal modules.
• Run the .validate.sh script before committing your changes.

At fxis.ai, we believe that such advancements are crucial for the future of AI, as they enable more comprehensive and effective solutions. Our team is continually exploring new methodologies to push the envelope in artificial intelligence, ensuring that our clients benefit from the latest technological innovations.

Related Projects

Explore other projects that might pique your interest, like iwamot/collmbo, which supports various LLM providers using LiteLLM.