AI SDK UIChatbot with Tools

Chatbot with Tools

The tool calling functionality described here is currently only available for React and SolidJS.

With useChat and streamText, you can use tools in your chatbot application. The Vercel AI SDK supports three types of tools in this context:

Automatically executed server-side tools
Automatically executed client-side tools
Tools that require user interaction, such as confirmation dialogs

The flow is as follows:

The user enters a message in the chat UI.
The message is sent to the API route.
The messages from the client are converted to AI SDK Core messages using convertToCoreMessages.
In your server side route, the language model generates tool calls during the streamText call.
All tool calls are forwarded to the client.
Server-side tools are executed using their execute method and their results are forwarded to the client.
Client-side tools that should be automatically executed are handled with the onToolCall callback. You can return the tool result from the callback.
Client-side tool that require user interactions can be displayed in the UI. The tool calls and results are available in the toolInvocations property of the last assistant message.
When the user interaction is done, addToolResult can be used to add the tool result to the chat.
When there are tool calls in the last assistant message and all tool results are available, the client sends the updated messages back to the server. This triggers another iteration of this flow.

The tool call and tool executions are integrated into the assistant message as toolInvocations. A tool invocation is at first a tool call, and then it becomes a tool result when the tool is executed. The tool result contains all information about the tool call as well as the result of the tool execution.

In order to automatically send another request to the server when all tool calls are server-side, you need to set maxToolRoundtrips to a value greater than 0 in the useChat options. It is disabled by default for backward compatibility.

Example

In this example, we'll use three tools:

getWeatherInformation: An automatically executed server-side tool that returns the weather in a given city.
askForConfirmation: A user-interaction client-side tool that asks the user for confirmation.
getLocation: An automatically executed client-side tool that returns a random city.

API route

app/api/chat/route.ts

import { openai } from '@ai-sdk/openai';
import { convertToCoreMessages, streamText } from 'ai';
import { z } from 'zod';

// Allow streaming responses up to 30 seconds
export const maxDuration = 30;

export async function POST(req: Request) {
  const { messages } = await req.json();

  const result = await streamText({
    model: openai('gpt-4-turbo'),
    messages: convertToCoreMessages(messages),
    tools: {
      // server-side tool with execute function:
      getWeatherInformation: {
        description: 'show the weather in a given city to the user',
        parameters: z.object({ city: z.string() }),
        execute: async ({}: { city: string }) => {
          const weatherOptions = ['sunny', 'cloudy', 'rainy', 'snowy', 'windy'];
          return weatherOptions[
            Math.floor(Math.random() * weatherOptions.length)
          ];
        },
      },
      // client-side tool that starts user interaction:
      askForConfirmation: {
        description: 'Ask the user for confirmation.',
        parameters: z.object({
          message: z.string().describe('The message to ask for confirmation.'),
        }),
      },
      // client-side tool that is automatically executed on the client:
      getLocation: {
        description:
          'Get the user location. Always ask for confirmation before using this tool.',
        parameters: z.object({}),
      },
    },
  });

  return result.toAIStreamResponse();
}

Client-side page

The client-side page uses the useChat hook to create a chatbot application with real-time message streaming. Tool invocations are displayed in the chat UI.

There are three things worth mentioning:

The onToolCall callback is used to handle client-side tools that should be automatically executed. In this example, the getLocation tool is a client-side tool that returns a random city.
The toolInvocations property of the last assistant message contains all tool calls and results. The client-side tool askForConfirmation is displayed in the UI. It asks the user for confirmation and displays the result once the user confirms or denies the execution. The result is added to the chat using addToolResult.
The maxToolRoundtrips option is set to 5. This enables several tool use iterations between the client and the server.

app/page.tsx

'use client';

import { ToolInvocation } from 'ai';
import { Message, useChat } from 'ai/react';

export default function Chat() {
  const { messages, input, handleInputChange, handleSubmit, addToolResult } =
    useChat({
      maxToolRoundtrips: 5,

      // run client-side tools that are automatically executed:
      async onToolCall({ toolCall }) {
        if (toolCall.toolName === 'getLocation') {
          const cities = [
            'New York',
            'Los Angeles',
            'Chicago',
            'San Francisco',
          ];
          return cities[Math.floor(Math.random() * cities.length)];
        }
      },
    });

  return (
    <div>
      {messages?.map((m: Message) => (
        <div key={m.id}>
          <strong>{m.role}:</strong>
          {m.content}
          {m.toolInvocations?.map((toolInvocation: ToolInvocation) => {
            const toolCallId = toolInvocation.toolCallId;
            const addResult = (result: string) =>
              addToolResult({ toolCallId, result });

            // render confirmation tool (client-side tool with user interaction)
            if (toolInvocation.toolName === 'askForConfirmation') {
              return (
                <div key={toolCallId}>
                  {toolInvocation.args.message}
                  <div>
                    {'result' in toolInvocation ? (
                      <b>{toolInvocation.result}</b>
                    ) : (
                      <>
                        <button onClick={() => addResult('Yes')}>Yes</button>
                        <button onClick={() => addResult('No')}>No</button>
                      </>
                    )}
                  </div>
                </div>
              );
            }

            // other tools:
            return 'result' in toolInvocation ? (
              <div key={toolCallId}>
                Tool call {`${toolInvocation.toolName}: `}
                {toolInvocation.result}
              </div>
            ) : (
              <div key={toolCallId}>Calling {toolInvocation.toolName}...</div>
            );
          })}
          <br />
        </div>
      ))}

      <form onSubmit={handleSubmit}>
        <input value={input} onChange={handleInputChange} />
      </form>
    </div>
  );
}