joshmenden / chatbot-ui

The open-source AI chat app for everyone.

Chatbot UI (forked)

The original repo has moved onto a v2 which IMO is a trying to be everything to everyone and is significantly more complicated than what I need. I forked the repo and turned their legacy branch into the main branch here. For more details on the legacy branch, see the README.md in the original repo.

Deploy

Docker

Build locally:

docker build -t chatbot-ui .
docker run -e OPENAI_API_KEY=xxxxxxxx -p 3000:3000 chatbot-ui

Building for raspberry pi

Build on the pi if you can, or an AWS ARM instance will do it quickly with this command:

docker buildx build -t chatbot-ui:latest --platform linux/arm64/v8 . --push

Running Locally

1. Clone Repo

git clone https://github.com/joshmenden/chatbot-ui.git

2. Install Dependencies

npm i

3. Provide OpenAI API Key

Create a .env.local file in the root of the repo with your OpenAI API Key:

OPENAI_API_KEY=YOUR_KEY

You can set OPENAI_API_HOST where access to the official OpenAI host is restricted or unavailable, allowing users to configure an alternative host for their specific needs.

Additionally, if you have multiple OpenAI Organizations, you can set OPENAI_ORGANIZATION to specify one.

4. Run App

npm run dev

5. Use It

You should be able to start chatting.

Configuration

When deploying the application, the following environment variables can be set:

Environment Variable	Default value	Description
OPENAI_API_KEY		The default API key used for authentication with OpenAI
DEFAULT_MODEL	gpt-3.5-turbo	The default model to use on new conversations
DEFAULT_SYSTEM_PROMPT	see here	The defaut system prompt to use on new conversations

If you do not provide an OpenAI API key with OPENAI_API_KEY, users will have to provide their own key. If you don't have an OpenAI API key, you can get one here.

Contact

If you have any questions, feel free to reach out to me on Twitter.