# `convertToCoreMessages()`

<Note title="warning">
  The `convertToCoreMessages` function is no longer required. The AI SDK now
  automatically converts the incoming messages to the `CoreMessage` format.
</Note>

The `convertToCoreMessages` function is used to transform an array of UI messages from the `useChat` hook into an array of `CoreMessage` objects. These `CoreMessage` objects are compatible with AI core functions like `streamText`.

```ts filename="app/api/chat/route.ts"
import { openai } from '@ai-sdk/openai';
import { convertToCoreMessages, streamText } from 'ai';

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

  const result = streamText({
    model: openai('gpt-4o'),
    messages: convertToCoreMessages(messages),
  });

  return result.toDataStreamResponse();
}
```

## Import

<Snippet text={`import { convertToCoreMessages } from "ai"`} prompt={false} />

## API Signature

### Parameters

<PropertiesTable
  content={[
    {
      name: 'messages',
      type: 'Message[]',
      description:
        'An array of UI messages from the useChat hook to be converted',
    },
    {
      name: 'options',
      type: '{ tools?: ToolSet }',
      description:
        'Optional configuration object. Provide tools to enable multi-modal tool responses.',
    },
  ]}
/>

### Returns

An array of [`CoreMessage`](/docs/reference/ai-sdk-core/core-message) objects.

<PropertiesTable
  content={[
    {
      name: 'CoreMessage[]',
      type: 'Array',
      description: 'An array of CoreMessage objects',
    },
  ]}
/>

## Multi-modal Tool Responses

The `convertToCoreMessages` function supports tools that can return multi-modal content. This is useful when tools need to return non-text content like images.

```ts
import { tool } from 'ai';
import { z } from 'zod';

const screenshotTool = tool({
  parameters: z.object({}),
  execute: async () => 'imgbase64',
  experimental_toToolResultContent: result => [{ type: 'image', data: result }],
});

const result = streamText({
  model: openai('gpt-4'),
  messages: convertToCoreMessages(messages, {
    tools: {
      screenshot: screenshotTool,
    },
  }),
});
```

Tools can implement the optional `experimental_toToolResultContent` method to transform their results into multi-modal content. The content is an array of content parts, where each part has a `type` (e.g., 'text', 'image') and corresponding data.


## Navigation

- [useChat](/v4/docs/reference/ai-sdk-ui/use-chat)
- [useCompletion](/v4/docs/reference/ai-sdk-ui/use-completion)
- [useObject](/v4/docs/reference/ai-sdk-ui/use-object)
- [useAssistant](/v4/docs/reference/ai-sdk-ui/use-assistant)
- [AssistantResponse](/v4/docs/reference/ai-sdk-ui/assistant-response)
- [convertToCoreMessages](/v4/docs/reference/ai-sdk-ui/convert-to-core-messages)
- [appendResponseMessages](/v4/docs/reference/ai-sdk-ui/append-response-messages)
- [appendClientMessage](/v4/docs/reference/ai-sdk-ui/append-client-message)
- [createDataStream](/v4/docs/reference/ai-sdk-ui/create-data-stream)
- [createDataStreamResponse](/v4/docs/reference/ai-sdk-ui/create-data-stream-response)
- [pipeDataStreamToResponse](/v4/docs/reference/ai-sdk-ui/pipe-data-stream-to-response)
- [StreamData](/v4/docs/reference/ai-sdk-ui/stream-data)


[Full Sitemap](/sitemap.md)