title	emoji	colorFrom	colorTo	sdk	pinned	license	base_path	app_port
chat-ui	🔥	purple	purple	docker	false	apache-2.0	/chat	3000

Chat UI

A chat interface using open source models, eg OpenAssistant. It is a SvelteKit app and it powers the HuggingChat app on hf.co/chat.

1. Setup
2. Launch
3. Extra parameters
4. Deploying to a HF Space
5. Building

Setup

The default config for Chat UI is stored in the .env file. You will need to override some values to get Chat UI to run locally. This is done in .env.local.

Start by creating a .env.local file in the root of the repository. The bare minimum config you need to get Chat UI to run locally is the following:

MONGODB_URL=<the URL to your mongoDB instance>
HF_ACCESS_TOKEN=<your access token>

Database

The chat history is stored in a MongoDB instance, and having a DB instance available is needed for Chat UI to work.

You can use a local MongoDB instance. The easiest way is to spin one up using docker:

docker run -d -p 27017:27017 --name mongo-chatui mongo:latest

In which case the url of your DB will be MONGODB_URL=mongodb://localhost:27017.

Alternatively, you can use a free MongoDB Atlas instance for this, Chat UI should fit comfortably within the free tier. After which you can set the MONGODB_URL variable in .env.local to match your instance.

Hugging Face Access Token

You will need a Hugging Face access token to run Chat UI locally, using the remote inference endpoints. You can get one from your Hugging Face profile.

Launch

After you're done with the .env.local file you can run Chat UI locally with:

npm install
npm run dev

Extra parameters

OpenID connect

The login feature is disabled by default and users are attributed a unique ID based on their browser. But if you want to use OpenID to authenticate your users, you can add the following to your .env.local file:

OPENID_PROVIDER_URL=<your OIDC issuer>
OPENID_CLIENT_ID=<your OIDC client ID>
OPENID_CLIENT_SECRET=<your OIDC client secret>

These variables will enable the openID sign-in modal for users.

Theming

You can use a few environment variables to customize the look and feel of chat-ui. These are by default:

PUBLIC_APP_NAME=ChatUI
PUBLIC_APP_ASSETS=chatui
PUBLIC_APP_COLOR=blue
PUBLIC_APP_DATA_SHARING=
PUBLIC_APP_DISCLAIMER=

• PUBLIC_APP_NAME The name used as a title throughout the app.
• PUBLIC_APP_ASSETS Is used to find logos & favicons in static/$PUBLIC_APP_ASSETS, current options are chatui and huggingchat.
• PUBLIC_APP_COLOR Can be any of the tailwind colors.
• PUBLIC_APP_DATA_SHARING Can be set to 1 to add a toggle in the user settings that lets your users opt-in to data sharing with models creator.
• PUBLIC_APP_DISCLAIMER If set to 1, we show a disclaimer about generated outputs on login.

Web Search

You can enable the web search by adding either SERPER_API_KEY (serper.dev) or SERPAPI_KEY (serpapi.com) to your .env.local.

Custom models

You can customize the parameters passed to the model or even use a new model by updating the MODELS variable in your .env.local. The default one can be found in .env and looks like this :

MODELS=`[
  {
    "name": "OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5",
    "datasetName": "OpenAssistant/oasst1",
    "description": "A good alternative to ChatGPT",
    "websiteUrl": "https://open-assistant.io",
    "userMessageToken": "<|prompter|>",
    "assistantMessageToken": "<|assistant|>",
    "messageEndToken": "</s>",
    "preprompt": "Below are a series of dialogues between various people and an AI assistant. The AI tries to be helpful, polite, honest, sophisticated, emotionally aware, and humble-but-knowledgeable. The assistant is happy to help with almost anything, and will do its best to understand exactly what is needed. It also tries to avoid giving false or misleading information, and it caveats when it isn't entirely sure about the right answer. That said, the assistant is practical and really does its best, and doesn't let caution get too much in the way of being useful.\n-----\n",
    "promptExamples": [
      {
        "title": "Write an email from bullet list",
        "prompt": "As a restaurant owner, write a professional email to the supplier to get these products every week: \n\n- Wine (x10)\n- Eggs (x24)\n- Bread (x12)"
      }, {
        "title": "Code a snake game",
        "prompt": "Code a basic snake game in python, give explanations for each step."
      }, {
        "title": "Assist in a task",
        "prompt": "How do I make a delicious lemon cheesecake?"
      }
    ],
    "parameters": {
      "temperature": 0.9,
      "top_p": 0.95,
      "repetition_penalty": 1.2,
      "top_k": 50,
      "truncate": 1000,
      "max_new_tokens": 1024
    }
  }
]`

You can change things like the parameters, or customize the preprompt to better suit your needs. You can also add more models by adding more objects to the array, with different preprompts for example.

Running your own models using a custom endpoint

If you want to, you can even run your own models locally, by having a look at our endpoint project, text-generation-inference. You can then add your own endpoints to the MODELS variable in .env.local, by adding an "endpoints" key for each model in MODELS.

{
// rest of the model config here
"endpoints": [{"url": "https://HOST:PORT/generate_stream"}]
}

If endpoints is left unspecified, ChatUI will look for the model on the hosted Hugging Face inference API using the model name.

Custom endpoint authorization

Custom endpoints may require authorization, depending on how you configure them. Authentication will usually be set either with Basic or Bearer.

For Basic we will need to generate a base64 encoding of the username and password.

echo -n "USER:PASS" | base64

VVNFUjpQQVNT

For Bearer you can use a token, which can be grabbed from here.

You can then add the generated information and the authorization parameter to your .env.local.

"endpoints": [
{
"url": "https://HOST:PORT/generate_stream",
"authorization": "Basic VVNFUjpQQVNT",
}
]

Models hosted on multiple custom endpoints

If the model being hosted will be available on multiple servers/instances add the weight parameter to your .env.local. The weight will be used to determine the probability of requesting a particular endpoint.

"endpoints": [
{
"url": "https://HOST:PORT/generate_stream",
"weight": 1
}
{
"url": "https://HOST:PORT/generate_stream",
"weight": 2
}
...
]

Deploying to a HF Space

Create a DOTENV_LOCAL secret to your HF space with the content of your .env.local, and they will be picked up automatically when you run.

Building

To create a production version of your app:

npm run build

You can preview the production build with npm run preview.

To deploy your app, you may need to install an adapter for your target environment.