React Quick Start

Take your first steps with Hashbrown.

Install

npm install @hashbrownai/{core,react,openai} --save

Provider

export function Providers() {
  return (
    <HashbrownProvider url={url}>
      {children}
    </HashbrownProvider>
  )
}

1. Import the component from @hashbrownai/react.
2. Optionally specify options such as the url for chat requests.
3. Add the provider to your React application.

export function Providers() {
  const middleware = [
    function (request: RequestInit) {
      console.log({ request });
      return request;
    },
  ];

  return (
    <HashbrownProvider url={url} middleware={middleware}>
      {children}
    </HashbrownProvider>
  );
}

Node Adapters

To get started, we recommend running a local express server following the Hashbrown adapter documentation.

• OpenAI
• Azure OpenAI
• Google Gemini
• Writer

The useChat() Hook

The hook from @hashbrownai/react is the basic way to interact with the model. It provides a set of methods for sending and receiving messages, as well as managing the chat state.

useChat({
  model: 'gpt-5',
  system: 'hashbrowns should be covered and smothered',
  messages: [{ role: 'user', content: 'Write a short story about breakfast.' }],
});

1. First, we specify the model.
2. Second, we provide system instructions.
3. Third, we send some initial messages to the model.

UseChatOptions

UseChatResult

The hook returns a object.

API Reference

Render the Model Response

import { useChat } from '@hashbrownai/react';

export function App() {
  // 1. Generate the messages from a prompt
  const { messages } = useChat({
    model: 'gpt-5',
    system: 'hashbrowns should be covered and smothered',
    messages: [
      { role: 'user', content: 'Write a short story about breakfast.' },
    ],
  });

  // 2. Render the content of each message
  return (
    <>
      {messages.map((message, i) => (
        <p key={i}>{message.content}</p>
      ))}
    </>
  );
}

1. The hook creates a new chat instance.
2. We destructure the response object and set the messages constant.
3. We return the JSX to render the content of each message.

This creates a basic chat interface where messages are displayed automatically.

Send Messages

To send messages to the model, we can use the sendMessage() method.

import { useState } from 'react';
import { useChat } from '@hashbrownai/react';

export function App() {
  const [userMessage, setUserMessage] = useState('');
  const { messages, sendMessage } = useChat({
    model: 'gpt-5',
    debugName: 'chat',
    system: 'hashbrowns should be covered and smothered',
  });

  const handleSend = () => {
    if (userMessage.trim()) {
      sendMessage({ role: 'user', content: userMessage });
      setUserMessage('');
    }
  };

  return (
    <div>
      <div>
        <input
          type="text"
          value={userMessage}
          onChange={(e) => setUserMessage(e.target.value)}
          placeholder="Prompt..."
          onKeyDown={(e) => e.key === 'Enter' && handleSend()}
        />
        <button onClick={handleSend}>Send</button>
      </div>
      <div>
        {messages.map((message, i) => (
          <p key={i}>{message.content}</p>
        ))}
      </div>
    </div>
  );
}

1. We create an input field controlled by userMessage state for user input.
2. The handleSend() function sends the user message to the chat using sendMessage().
3. React renders the user message and the assistant response message.

Debugging with Redux Devtools

Hashbrown streams LLM messages and internal actions to the redux devtools.

To enable debugging, specify the debugName option.

import { useChat } from '@hashbrownai/react';

const chat = useChat({
  debugName: 'chat',
});

Beyond Chat

Large language models are highly intelligent and capable of more than just text and chatbots. With Hashbrown, you can expose your trusted, tested, and compliant components - in other words, you can generate user interfaces using your components as the building blocks!

Tool Calling

Tool calling enables the model to invoke callback function in your frontend web application code. The functions you expose can either have no arguments or you can specify the required and optional arguments. The model will choose if, and when, to invoke the function.

What can functions do?

• Expose application state to the model
• Allow the model to take an action
• Offer intelligent next actions for the user to take
• Automate user tasks

Streaming Responses

Streaming is baked into the core of Hashbrown. With Skillet, our LLM-optimized schema language, you can use the .streaming() keyword to enable streaming with eager JSON parsing.

Run LLM-generated JS Code (Safely)

Hashbrown ships with a JavaScript runtime for safe execution of LLM-generated code in the client.