Saltar al contenido principal
POST
/
assistant
/
{domain}
/
message
Assistant message
curl --request POST \
  --url https://api-dsc.mintlify.com/v1/assistant/{domain}/message \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "fp": "<string>",
  "threadId": null,
  "messages": [
    {
      "id": "foobar",
      "role": "user",
      "content": "how do i get started",
      "parts": [
        {
          "type": "text",
          "text": "How do I get started"
        }
      ]
    }
  ],
  "retrievalPageSize": 5,
  "filter": null
}
'
{}

Integración con useChat

El hook useChat del AI SDK de Vercel es la forma recomendada de integrar la API del assistant en tu aplicación.
La API del assistant de Mintlify es compatible con AI SDK v4. Si usas AI SDK v5 o posterior, debes configurar un transporte personalizado.
1

Instalar el AI SDK v4

npm i ai@^4.1.15
2

Usar el hook

import { useChat } from 'ai/react';

function MyComponent({ domain }) {
  const { messages, input, handleInputChange, handleSubmit, isLoading } = useChat({
    api: `https://api-dsc.mintlify.com/v1/assistant/${domain}/message`,
    headers: {
      'Authorization': `Bearer ${process.env.MINTLIFY_TOKEN}`,
    },
    body: {
      fp: 'anonymous',
      retrievalPageSize: 5,
    },
    streamProtocol: 'data',
    sendExtraMessageFields: true,
  });

  return (
    <div>
      {messages.map((message) => (
        <div key={message.id}>
          {message.role === 'user' ? 'Usuario: ' : 'Assistant: '}
          {message.content}
        </div>
      ))}
      <form onSubmit={handleSubmit}>
        <input value={input} onChange={handleInputChange} />
        <button type="submit">Enviar</button>
      </form>
    </div>
  );
}
Configuración obligatoria para Mintlify:
  • streamProtocol: 'data' - Obligatorio para respuestas en streaming.
  • sendExtraMessageFields: true - Obligatorio para enviar metadata de los mensajes.
  • body.fp - Identificador de huella digital (usa ‘anonymous’ o un identificador de usuario).
  • body.retrievalPageSize - Número de resultados de búsqueda a usar (recomendado: 5).
Consulta useChat en la documentación del AI SDK para obtener más información.

Límites de uso

La API del assistant tiene los siguientes límites:
  • 10,000 usos por key al mes
  • 10,000 solicitudes por organización de Mintlify por hora
  • 10,000 solicitudes por IP al día

Authorizations

Authorization
string
header
required

The Authorization header expects a Bearer token. See the Assistant API Key documentation for details on how to get your API key.

Path Parameters

domain
string
required

The domain identifier from your domain.mintlify.app URL. Can be found at the end of your dashboard URL. For example, dashboard.mintlify.com/organization/domain has a domain identifier of domain.

Body

application/json
fp
string
required

Fingerprint identifier for tracking conversation sessions. Use 'anonymous' for anonymous users or provide a unique user identifier.

messages
object[]
required

Array of messages in the conversation. On the frontend, you will likely want to use the handleSubmit function from the @ai-sdk package's useChat hook to append user messages and handle streaming responses, rather than manually defining the objects in this array as they have so many parameters.

threadId
string

An optional identifier used to maintain conversation continuity across multiple messages. When provided, it allows the system to associate follow-up messages with the same conversation thread. The threadId is returned in the response as event.threadId when event.type === 'finish'.

retrievalPageSize
number
default:5

Number of documentation search results to use for generating the response. Higher values provide more context but may increase response time. Recommended: 5.

filter
object

Optional filter criteria for the search

Response

200 - application/json

Message generated successfully

Response object that streams formatted data stream parts with the specified status, headers, and content. This matches what is expected from the AI SDK as documented at ai-sdk.dev/docs/ai-sdk-ui/streaming-data. Instead of writing your own parser, it is recommended to use the useChat hook from ai-sdk as documented here.