Skip to content
Chat-Lab.AI | Documentation

Other Deployment Options

This app can also be deployed on other services. For instance, all of Chat-Lab.AI’s Streamlit apps are hosted on the Digital Ocean App platform using this simple Docker template.

Streamlit’s documentation provides instructions on deploying on other cloud providers.

Local Hosting

Additionally, in the event you want to use the chat interface and don’t want to make it available online, you can run this app locally.

You will need a Python installation, then run the following command to install the streamlit package.

pip install streamlit

To run the app, open a new command prompt and run the following command from the directory containing your streamlit app.

streamlit run streamlit_app.py

The app will automatically open in your default browser. Streamlit will run a server on your localhost using port 8501 by default. You can change the default port using the config.toml file discussed in the Additional Customizations page.

Sharing your local app using Tailscale

There are many options for sharing local services, such as Streamlit apps, including nGrok. I used a Tailscale Funnel while developing Chat-Lab.AI and found it to be really easy to setup and use, so that’s what I’ll recommend for most users interested in local deployment.

Tailscale is a Wireguard-based VPN that securely connects all devices in your network (called a tailnet), whether or not they’re on the same internet connection. A free plan should be more than enough for sharing a simple Streamlit app. The nice thing about Tailscale is that they don’t appear to be lying in their marketing, it just works. Please don’t ask me how, it just does.

After installing Tailscale and running your Streamlit app, open a new command prompt and run the following command:

tailscale funnel 8501

You will see a system message indicating the address you can share with others.

To use an https:// you will have to enable HTTPS in the Tailscale admin options.

You can also start a Tailscale Funnel from VS Code.

Visit Tailscale to learn more about how to use their services.