Entrada multimodal

La API de Respuestas acepta texto, imágenes, audio y archivos en una sola solicitud. Utiliza input estructurado con arreglos de contenido para combinar modalidades.

Tipos de entrada soportados

Tipo	Tipo de contenido	Formatos	Entrega
Texto	`input_text`	Texto plano	En línea
Imagen	`input_image`	JPEG, PNG, WebP, GIF, TIFF	URL, URI de datos base64 o `file_id`
Audio	`input_audio`	WAV, MP3	Base64
Documento	`input_file`	PDF, DOCX, XLSX, PPTX, RTF, TXT, CSV	URL, URI de datos base64 o `file_id`
Video	`input_file`	MP4	URI de datos base64 o `file_id`

Entrada de imagen

Envía una imagen para que el modelo la describa, analice o responda preguntas sobre ella. Proporciona la imagen como una URL, una URI de datos base64 o un file_id previamente subido.

Imagen vía URL

mka1 llm responses create \
  -H 'X-On-Behalf-Of: <end-user-id>' \
  --body '{
    "model": "meetkai:functionary-es-mini",
    "input": [
      {
        "type": "message",
        "role": "user",
        "content": [
          { "type": "input_text", "text": "Describe what you see in this image." },
          {
            "type": "input_image",
            "image_url": "https://upload.wikimedia.org/wikipedia/commons/thumb/3/3a/Cat03.jpg/1200px-Cat03.jpg"
          }
        ]
      }
    ]
  }'

import { SDK } from '@meetkai/mka1';

const mka1 = new SDK({
  bearerAuth: `Bearer ${YOUR_API_KEY}`,
});

const result = await mka1.llm.responses.create({
  model: 'meetkai:functionary-es-mini',
  input: [
    {
      type: 'message',
      role: 'user',
      content: [
        { type: 'input_text', text: 'Describe what you see in this image.' },
        {
          type: 'input_image',
          image_url: 'https://upload.wikimedia.org/wikipedia/commons/thumb/3/3a/Cat03.jpg/1200px-Cat03.jpg',
        },
      ],
    },
  ],
}, { headers: { 'X-On-Behalf-Of': '<end-user-id>' } });

import OpenAI from 'openai';

const openai = new OpenAI({
  apiKey: '<mka1-api-key>',
  baseURL: 'https://apigw.mka1.com/api/v1/llm/',
  defaultHeaders: { 'X-On-Behalf-Of': '<end-user-id>' },
});

const response = await openai.responses.create({
  model: 'meetkai:functionary-es-mini',
  input: [
    {
      type: 'message',
      role: 'user',
      content: [
        { type: 'input_text', text: 'Describe what you see in this image.' },
        {
          type: 'input_image',
          image_url: 'https://upload.wikimedia.org/wikipedia/commons/thumb/3/3a/Cat03.jpg/1200px-Cat03.jpg',
        },
      ],
    },
  ],
  stream: false,
});

using MeetKai.MKA1;
using MeetKai.MKA1.Types.Components;

var sdk = new SDK(
    bearerAuth: $"Bearer {YOUR_API_KEY}",
    serverUrl: "https://apigw.mka1.com"
);

var res = await sdk.Llm.Responses.CreateAsync(new ResponsesCreateRequest()
{
    Model = "meetkai:functionary-es-mini",
    Input = ResponsesCreateRequestInput.CreateArrayOfItem(new List<Item>
    {
        Item.CreateInputMessage(new InputMessage()
        {
            Role = InputMessageRole.User,
            Content = InputMessageContent1.CreateArrayOfInputMessageContent(
                new List<InputMessageContent>
                {
                    InputMessageContent.CreateInputText(new InputText()
                    {
                        Text = "Describe what you see in this image.",
                    }),
                    InputMessageContent.CreateInputImage(new InputImage()
                    {
                        ImageUrl = "https://upload.wikimedia.org/wikipedia/commons/thumb/3/3a/Cat03.jpg/1200px-Cat03.jpg",
                    }),
                }),
        }),
    }),
});

from mka1 import SDK

sdk = SDK(bearer_auth="Bearer YOUR_API_KEY")

result = sdk.llm.responses.create(
    model="meetkai:functionary-es-mini",
    input=[{
        "type": "message",
        "role": "user",
        "content": [
            {"type": "input_text", "text": "Describe what you see in this image."},
            {
                "type": "input_image",
                "image_url": "https://upload.wikimedia.org/wikipedia/commons/thumb/3/3a/Cat03.jpg/1200px-Cat03.jpg",
            },
        ],
    }],
)

curl https://apigw.mka1.com/api/v1/llm/responses \
  --request POST \
  --header 'Content-Type: application/json' \
  --header 'Authorization: Bearer <mka1-api-key>' \
  --header 'X-On-Behalf-Of: <end-user-id>' \
  --data '{
    "model": "meetkai:functionary-es-mini",
    "input": [
      {
        "type": "message",
        "role": "user",
        "content": [
          { "type": "input_text", "text": "Describe what you see in this image." },
          {
            "type": "input_image",
            "image_url": "https://upload.wikimedia.org/wikipedia/commons/thumb/3/3a/Cat03.jpg/1200px-Cat03.jpg",
          }
        ]
      }
    ]
  }'

Imagen vía base64

Codifica la imagen como una URI de datos con el tipo MIME apropiado.

IMAGE_B64=$(base64 -i photo.jpg)

mka1 llm responses create \
  --body "{
    \"model\": \"meetkai:functionary-es-mini\",
    \"input\": [
      {
        \"type\": \"message\",
        \"role\": \"user\",
        \"content\": [
          { \"type\": \"input_text\", \"text\": \"What is in this photo?\" },
          {
            \"type\": \"input_image\",
            \"image_url\": \"data:image/jpeg;base64,${IMAGE_B64}\"
          }
        ]
      }
    ]
  }"

import { readFileSync } from 'fs';

const imageBase64 = readFileSync('photo.jpg').toString('base64');

const result = await mka1.llm.responses.create({
  model: 'meetkai:functionary-es-mini',
  input: [
    {
      type: 'message',
      role: 'user',
      content: [
        { type: 'input_text', text: 'What is in this photo?' },
        {
          type: 'input_image',
          image_url: `data:image/jpeg;base64,${imageBase64}`,
        },
      ],
    },
  ],
});

import { readFileSync } from 'fs';

const imageBase64 = readFileSync('photo.jpg').toString('base64');

const response = await openai.responses.create({
  model: 'meetkai:functionary-es-mini',
  input: [
    {
      type: 'message',
      role: 'user',
      content: [
        { type: 'input_text', text: 'What is in this photo?' },
        {
          type: 'input_image',
          image_url: `data:image/jpeg;base64,${imageBase64}`,
        },
      ],
    },
  ],
  stream: false,
});

var imageBytes = System.IO.File.ReadAllBytes("photo.jpg");
var imageBase64 = Convert.ToBase64String(imageBytes);

var res = await sdk.Llm.Responses.CreateAsync(new ResponsesCreateRequest()
{
    Model = "meetkai:functionary-es-mini",
    Input = ResponsesCreateRequestInput.CreateArrayOfItem(new List<Item>
    {
        Item.CreateInputMessage(new InputMessage()
        {
            Role = InputMessageRole.User,
            Content = InputMessageContent1.CreateArrayOfInputMessageContent(
                new List<InputMessageContent>
                {
                    InputMessageContent.CreateInputText(new InputText()
                    {
                        Text = "What is in this photo?",
                    }),
                    InputMessageContent.CreateInputImage(new InputImage()
                    {
                        ImageUrl = $"data:image/jpeg;base64,{imageBase64}",
                    }),
                }),
        }),
    }),
});

import base64

with open("photo.jpg", "rb") as f:
    image_base64 = base64.b64encode(f.read()).decode()

result = sdk.llm.responses.create(
    model="meetkai:functionary-es-mini",
    input=[{
        "type": "message",
        "role": "user",
        "content": [
            {"type": "input_text", "text": "What is in this photo?"},
            {
                "type": "input_image",
                "image_url": f"data:image/jpeg;base64,{image_base64}",
            },
        ],
    }],
)

# Codifica una imagen local y envíala en línea
IMAGE_B64=$(base64 -i photo.jpg)

curl https://apigw.mka1.com/api/v1/llm/responses \
  --request POST \
  --header 'Content-Type: application/json' \
  --header 'Authorization: Bearer <mka1-api-key>' \
  --data "{
    \"model\": \"meetkai:functionary-es-mini\",
    \"input\": [
      {
        \"type\": \"message\",
        \"role\": \"user\",
        \"content\": [
          { \"type\": \"input_text\", \"text\": \"What is in this photo?\" },
          {
            \"type\": \"input_image\",
            \"image_url\": \"data:image/jpeg;base64,${IMAGE_B64}\",
          }
        ]
      }
    ]
  }"

Imagen vía file_id

Sube una imagen primero con la API de Archivos y luego haz referencia a ella por su ID.

# Sube la imagen
FILE_ID=$(mka1 llm files upload \
  --file @photo.jpg \
  --purpose assistants | jq -r '.id')

# Usa el file_id
mka1 llm responses create \
  --body "{
    \"model\": \"meetkai:functionary-es-mini\",
    \"input\": [
      {
        \"type\": \"message\",
        \"role\": \"user\",
        \"content\": [
          { \"type\": \"input_text\", \"text\": \"Describe this image.\" },
          { \"type\": \"input_image\", \"file_id\": \"${FILE_ID}\" }
        ]
      }
    ]
  }"

// Sube la imagen
const uploadResult = await mka1.llm.files.create({
  file: { fileName: 'photo.jpg', content: imageBuffer },
  purpose: 'assistants',
});

// Usa el file_id en una respuesta
const result = await mka1.llm.responses.create({
  model: 'meetkai:functionary-es-mini',
  input: [
    {
      type: 'message',
      role: 'user',
      content: [
        { type: 'input_text', text: 'Describe this image.' },
        { type: 'input_image', file_id: uploadResult.id },
      ],
    },
  ],
});

// Sube la imagen
const file = await openai.files.create({
  file: new File([imageBuffer], 'photo.jpg', { type: 'image/jpeg' }),
  purpose: 'assistants',
});

// Usa el file_id en una respuesta
const response = await openai.responses.create({
  model: 'meetkai:functionary-es-mini',
  input: [
    {
      type: 'message',
      role: 'user',
      content: [
        { type: 'input_text', text: 'Describe this image.' },
        { type: 'input_image', file_id: file.id },
      ],
    },
  ],
  stream: false,
});

using MeetKai.MKA1.Types.Requests;

// Sube la imagen
var uploadResult = await sdk.Llm.Files.UploadAsync(new UploadFileRequestBody()
{
    File = new UploadFileFile()
    {
        FileName = "photo.png",
        Content = System.IO.File.ReadAllBytes("photo.png"),
    },
    Purpose = UploadFilePurpose.Assistants,
});

// Usa el file_id en una respuesta
var res = await sdk.Llm.Responses.CreateAsync(new ResponsesCreateRequest()
{
    Model = "meetkai:functionary-es-mini",
    Input = ResponsesCreateRequestInput.CreateArrayOfItem(new List<Item>
    {
        Item.CreateInputMessage(new InputMessage()
        {
            Role = InputMessageRole.User,
            Content = InputMessageContent1.CreateArrayOfInputMessageContent(
                new List<InputMessageContent>
                {
                    InputMessageContent.CreateInputText(new InputText()
                    {
                        Text = "Describe this image.",
                    }),
                    InputMessageContent.CreateInputImage(new InputImage()
                    {
                        FileId = uploadResult.File!.Id,
                    }),
                }),
        }),
    }),
});

# Sube la imagen
upload_result = sdk.llm.files.upload(
    file={"file_name": "photo.jpg", "content": open("photo.jpg", "rb")},
    purpose="assistants",
)

# Usa el file_id en una respuesta
result = sdk.llm.responses.create(
    model="meetkai:functionary-es-mini",
    input=[{
        "type": "message",
        "role": "user",
        "content": [
            {"type": "input_text", "text": "Describe this image."},
            {"type": "input_image", "file_id": upload_result.id},
        ],
    }],
)

# Sube la imagen
FILE_ID=$(curl -s https://apigw.mka1.com/api/v1/llm/files \
  --header 'Authorization: Bearer <mka1-api-key>' \
  --form file=@photo.jpg \
  --form purpose=assistants | jq -r '.id')

# Usa el file_id
curl https://apigw.mka1.com/api/v1/llm/responses \
  --request POST \
  --header 'Content-Type: application/json' \
  --header 'Authorization: Bearer <mka1-api-key>' \
  --data "{
    \"model\": \"meetkai:functionary-es-mini\",
    \"input\": [
      {
        \"type\": \"message\",
        \"role\": \"user\",
        \"content\": [
          { \"type\": \"input_text\", \"text\": \"Describe this image.\" },
          { \"type\": \"input_image\", \"file_id\": \"${FILE_ID}\" }
        ]
      }
    ]
  }"

Entrada de audio

Envía audio para que el modelo lo procese. El audio se transcribe automáticamente y el modelo responde al contenido hablado. Formatos soportados: WAV y MP3 (máx 25 MB).

AUDIO_B64=$(base64 -i recording.wav)

mka1 llm responses create \
  --body "{
    \"model\": \"meetkai:functionary-es-mini\",
    \"input\": [
      {
        \"type\": \"message\",
        \"role\": \"user\",
        \"content\": [
          {
            \"type\": \"input_audio\",
            \"input_audio\": {
              \"data\": \"${AUDIO_B64}\",
              \"format\": \"wav\"
            }
          }
        ]
      }
    ]
  }"

import { readFileSync } from 'fs';

const audioBase64 = readFileSync('recording.wav').toString('base64');

const result = await mka1.llm.responses.create({
  model: 'meetkai:functionary-es-mini',
  input: [
    {
      type: 'message',
      role: 'user',
      content: [
        {
          type: 'input_audio',
          input_audio: {
            data: audioBase64,
            format: 'wav',
          },
        },
      ],
    },
  ],
}, { headers: { 'X-On-Behalf-Of': '<end-user-id>' } });

import { readFileSync } from 'fs';

const audioBase64 = readFileSync('recording.wav').toString('base64');

const response = await openai.responses.create({
  model: 'meetkai:functionary-es-mini',
  input: [
    {
      type: 'message',
      role: 'user',
      content: [
        {
          type: 'input_audio',
          input_audio: {
            data: audioBase64,
            format: 'wav',
          },
        },
      ],
    },
  ],
  stream: false,
});

var audioBytes = System.IO.File.ReadAllBytes("recording.wav");
var audioBase64 = Convert.ToBase64String(audioBytes);

var res = await sdk.Llm.Responses.CreateAsync(new ResponsesCreateRequest()
{
    Model = "meetkai:functionary-es-mini",
    Input = ResponsesCreateRequestInput.CreateArrayOfItem(new List<Item>
    {
        Item.CreateInputMessage(new InputMessage()
        {
            Role = InputMessageRole.User,
            Content = InputMessageContent1.CreateArrayOfInputMessageContent(
                new List<InputMessageContent>
                {
                    InputMessageContent.CreateInputAudio(new InputAudio()
                    {
                        InputAudioValue = new InputAudioInputAudio()
                        {
                            Data = audioBase64,
                            Format = InputAudioFormat.Wav,
                        },
                    }),
                }),
        }),
    }),
});

import base64

with open("recording.wav", "rb") as f:
    audio_base64 = base64.b64encode(f.read()).decode()

result = sdk.llm.responses.create(
    model="meetkai:functionary-es-mini",
    input=[{
        "type": "message",
        "role": "user",
        "content": [
            {
                "type": "input_audio",
                "input_audio": {
                    "data": audio_base64,
                    "format": "wav",
                },
            },
        ],
    }],
)

AUDIO_B64=$(base64 -i recording.wav)

curl https://apigw.mka1.com/api/v1/llm/responses \
  --request POST \
  --header 'Content-Type: application/json' \
  --header 'Authorization: Bearer <mka1-api-key>' \
  --header 'X-On-Behalf-Of: <end-user-id>' \
  --data "{
    \"model\": \"meetkai:functionary-es-mini\",
    \"input\": [
      {
        \"type\": \"message\",
        \"role\": \"user\",
        \"content\": [
          {
            \"type\": \"input_audio\",
            \"input_audio\": {
              \"data\": \"${AUDIO_B64}\",
              \"format\": \"wav\"
            }
          }
        ]
      }
    ]
  }"

El modelo transcribe automáticamente el audio y responde al contenido hablado. Por ejemplo, enviar un archivo WAV que contiene “Hello, how are you today?” devuelve:

{
  "status": "completed",
  "output": [
    {
      "type": "message",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "Hello! I'm doing well, thank you for asking. I'm here and ready to help you with any questions or tasks you might have. How can I assist you today?"
        }
      ]
    }
  ]
}

Entrada de documento

Envía documentos para que el modelo los lea y razone sobre ellos. Los documentos PDF y escaneados se procesan automáticamente con OCR — no se necesita configuración adicional.

Documento vía URL

mka1 llm responses create \
  --body '{
    "model": "meetkai:functionary-es-mini",
    "input": [
      {
        "type": "message",
        "role": "user",
        "content": [
          { "type": "input_text", "text": "Summarize this document in three bullet points." },
          {
            "type": "input_file",
            "file_url": "https://example.com/report.pdf",
            "filename": "report.pdf"
          }
        ]
      }
    ]
  }'

const result = await mka1.llm.responses.create({
  model: 'meetkai:functionary-es-mini',
  input: [
    {
      type: 'message',
      role: 'user',
      content: [
        { type: 'input_text', text: 'Summarize this document in three bullet points.' },
        {
          type: 'input_file',
          file_url: 'https://example.com/report.pdf',
          filename: 'report.pdf',
        },
      ],
    },
  ],
});

const response = await openai.responses.create({
  model: 'meetkai:functionary-es-mini',
  input: [
    {
      type: 'message',
      role: 'user',
      content: [
        { type: 'input_text', text: 'Summarize this document in three bullet points.' },
        {
          type: 'input_file',
          file_url: 'https://example.com/report.pdf',
          filename: 'report.pdf',
        },
      ],
    },
  ],
  stream: false,
});

var res = await sdk.Llm.Responses.CreateAsync(new ResponsesCreateRequest()
{
    Model = "meetkai:functionary-es-mini",
    Input = ResponsesCreateRequestInput.CreateArrayOfItem(new List<Item>
    {
        Item.CreateInputMessage(new InputMessage()
        {
            Role = InputMessageRole.User,
            Content = InputMessageContent1.CreateArrayOfInputMessageContent(
                new List<InputMessageContent>
                {
                    InputMessageContent.CreateInputText(new InputText()
                    {
                        Text = "Summarize this document in three bullet points.",
                    }),
                    InputMessageContent.CreateInputFile(new InputFile()
                    {
                        FileUrl = "https://example.com/report.pdf",
                        Filename = "report.pdf",
                    }),
                }),
        }),
    }),
});

result = sdk.llm.responses.create(
    model="meetkai:functionary-es-mini",
    input=[{
        "type": "message",
        "role": "user",
        "content": [
            {"type": "input_text", "text": "Summarize this document in three bullet points."},
            {
                "type": "input_file",
                "file_url": "https://example.com/report.pdf",
                "filename": "report.pdf",
            },
        ],
    }],
)

curl https://apigw.mka1.com/api/v1/llm/responses \
  --request POST \
  --header 'Content-Type: application/json' \
  --header 'Authorization: Bearer <mka1-api-key>' \
  --header 'X-On-Behalf-Of: <end-user-id>' \
  --data '{
    "model": "meetkai:functionary-es-mini",
    "input": [
      {
        "type": "message",
        "role": "user",
        "content": [
          { "type": "input_text", "text": "Summarize this document in three bullet points." },
          {
            "type": "input_file",
            "file_url": "https://example.com/report.pdf",
            "filename": "report.pdf"
          }
        ]
      }
    ]
  }'

Documento vía base64

Codifica el archivo como una URI de datos. Incluye el tipo MIME para que la API pueda enviarlo al procesador correcto.

PDF_B64=$(base64 -i contract.pdf)

mka1 llm responses create \
  --body "{
    \"model\": \"meetkai:functionary-es-mini\",
    \"input\": [
      {
        \"type\": \"message\",
        \"role\": \"user\",
        \"content\": [
          { \"type\": \"input_text\", \"text\": \"What are the key terms in this contract?\" },
          {
            \"type\": \"input_file\",
            \"file_data\": \"data:application/pdf;base64,${PDF_B64}\",
            \"filename\": \"contract.pdf\"
          }
        ]
      }
    ]
  }"

import { readFileSync } from 'fs';

const pdfBase64 = readFileSync('contract.pdf').toString('base64');

const result = await mka1.llm.responses.create({
  model: 'meetkai:functionary-es-mini',
  input: [
    {
      type: 'message',
      role: 'user',
      content: [
        { type: 'input_text', text: 'What are the key terms in this contract?' },
        {
          type: 'input_file',
          file_data: `data:application/pdf;base64,${pdfBase64}`,
          filename: 'contract.pdf',
        },
      ],
    },
  ],
});

import { readFileSync } from 'fs';

const pdfBase64 = readFileSync('contract.pdf').toString('base64');

const response = await openai.responses.create({
  model: 'meetkai:functionary-es-mini',
  input: [
    {
      type: 'message',
      role: 'user',
      content: [
        { type: 'input_text', text: 'What are the key terms in this contract?' },
        {
          type: 'input_file',
          file_data: `data:application/pdf;base64,${pdfBase64}`,
          filename: 'contract.pdf',
        },
      ],
    },
  ],
  stream: false,
});

var pdfBytes = System.IO.File.ReadAllBytes("contract.pdf");
var pdfBase64 = Convert.ToBase64String(pdfBytes);

var res = await sdk.Llm.Responses.CreateAsync(new ResponsesCreateRequest()
{
    Model = "meetkai:functionary-es-mini",
    Input = ResponsesCreateRequestInput.CreateArrayOfItem(new List<Item>
    {
        Item.CreateInputMessage(new InputMessage()
        {
            Role = InputMessageRole.User,
            Content = InputMessageContent1.CreateArrayOfInputMessageContent(
                new List<InputMessageContent>
                {
                    InputMessageContent.CreateInputText(new InputText()
                    {
                        Text = "What are the key terms in this contract?",
                    }),
                    InputMessageContent.CreateInputFile(new InputFile()
                    {
                        FileData = $"data:application/pdf;base64,{pdfBase64}",
                        Filename = "contract.pdf",
                    }),
                }),
        }),
    }),
});

import base64

with open("contract.pdf", "rb") as f:
    pdf_base64 = base64.b64encode(f.read()).decode()

result = sdk.llm.responses.create(
    model="meetkai:functionary-es-mini",
    input=[{
        "type": "message",
        "role": "user",
        "content": [
            {"type": "input_text", "text": "What are the key terms in this contract?"},
            {
                "type": "input_file",
                "file_data": f"data:application/pdf;base64,{pdf_base64}",
                "filename": "contract.pdf",
            },
        ],
    }],
)

PDF_B64=$(base64 -i contract.pdf)

curl https://apigw.mka1.com/api/v1/llm/responses \
  --request POST \
  --header 'Content-Type: application/json' \
  --header 'Authorization: Bearer <mka1-api-key>' \
  --data "{
    \"model\": \"meetkai:functionary-es-mini\",
    \"input\": [
      {
        \"type\": \"message\",
        \"role\": \"user\",
        \"content\": [
          { \"type\": \"input_text\", \"text\": \"What are the key terms in this contract?\" },
          {
            \"type\": \"input_file\",
            \"file_data\": \"data:application/pdf;base64,${PDF_B64}\",
            \"filename\": \"contract.pdf\"
          }
        ]
      }
    ]
  }"

Documentos escaneados y OCR

Los PDFs escaneados y las imágenes de documentos se procesan automáticamente. La API utiliza OCR para extraer texto de:

Páginas PDF escaneadas (convertidas a imágenes a 150 DPI, luego OCR)
Fotos de documentos (JPEG, PNG, TIFF)
Archivos de Office (DOCX, XLSX, PPTX — convertidos a PDF primero, luego OCR)

Los documentos de varias páginas se procesan en paralelo. El texto extraído se devuelve como Markdown y se pasa al modelo para razonamiento. No se necesitan parámetros especiales — solo envía el archivo como input_file y la canalización se encarga de la detección, conversión y OCR.

Formatos de documento soportados

Formato	Tipo MIME	Procesamiento
PDF	`application/pdf`	OCR por página a 150 DPI
JPEG / PNG / TIFF / WebP / GIF	`image/*`	OCR directo
Word (.doc, .docx)	`application/msword`, `application/vnd.openxmlformats-officedocument.wordprocessingml.document`	Convertir a PDF, luego OCR
Excel (.xls, .xlsx)	`application/vnd.ms-excel`, `application/vnd.openxmlformats-officedocument.spreadsheetml.sheet`	Convertir a PDF, luego OCR
PowerPoint (.ppt, .pptx)	`application/vnd.ms-powerpoint`, `application/vnd.openxmlformats-officedocument.presentationml.presentation`	Convertir a PDF, luego OCR
RTF	`application/rtf`	Convertir a PDF, luego OCR
Texto plano / CSV	`text/plain`, `text/csv`	Leer directamente

Límite de tamaño: 30 MB por archivo.

Entrada mixta

Combina múltiples tipos de contenido en un solo mensaje. El modelo ve todas las entradas juntas y puede razonar entre ellas.

mka1 llm responses create \
  --body '{
    "model": "meetkai:functionary-es-mini",
    "input": [
      {
        "type": "message",
        "role": "user",
        "content": [
          { "type": "input_text", "text": "Compare the chart in the image with the data in the spreadsheet. Are the numbers consistent?" },
          {
            "type": "input_image",
            "image_url": "https://example.com/chart.png"
          },
          {
            "type": "input_file",
            "file_url": "https://example.com/data.xlsx",
            "filename": "data.xlsx"
          }
        ]
      }
    ]
  }'

const result = await mka1.llm.responses.create({
  model: 'meetkai:functionary-es-mini',
  input: [
    {
      type: 'message',
      role: 'user',
      content: [
        { type: 'input_text', text: 'Compare the chart in the image with the data in the spreadsheet. Are the numbers consistent?' },
        {
          type: 'input_image',
          image_url: 'https://example.com/chart.png',
        },
        {
          type: 'input_file',
          file_url: 'https://example.com/data.xlsx',
          filename: 'data.xlsx',
        },
      ],
    },
  ],
});

const response = await openai.responses.create({
  model: 'meetkai:functionary-es-mini',
  input: [
    {
      type: 'message',
      role: 'user',
      content: [
        { type: 'input_text', text: 'Compare the chart in the image with the data in the spreadsheet. Are the numbers consistent?' },
        {
          type: 'input_image',
          image_url: 'https://example.com/chart.png',
        },
        {
          type: 'input_file',
          file_url: 'https://example.com/data.xlsx',
          filename: 'data.xlsx',
        },
      ],
    },
  ],
  stream: false,
});

var res = await sdk.Llm.Responses.CreateAsync(new ResponsesCreateRequest()
{
    Model = "meetkai:functionary-es-mini",
    Input = ResponsesCreateRequestInput.CreateArrayOfItem(new List<Item>
    {
        Item.CreateInputMessage(new InputMessage()
        {
            Role = InputMessageRole.User,
            Content = InputMessageContent1.CreateArrayOfInputMessageContent(
                new List<InputMessageContent>
                {
                    InputMessageContent.CreateInputText(new InputText()
                    {
                        Text = "Compare the chart in the image with the data in the spreadsheet. Are the numbers consistent?",
                    }),
                    InputMessageContent.CreateInputImage(new InputImage()
                    {
                        ImageUrl = "https://example.com/chart.png",
                    }),
                    InputMessageContent.CreateInputFile(new InputFile()
                    {
                        FileUrl = "https://example.com/data.xlsx",
                        Filename = "data.xlsx",
                    }),
                }),
        }),
    }),
});

result = sdk.llm.responses.create(
    model="meetkai:functionary-es-mini",
    input=[{
        "type": "message",
        "role": "user",
        "content": [
            {"type": "input_text", "text": "Compare the chart in the image with the data in the spreadsheet. Are the numbers consistent?"},
            {
                "type": "input_image",
                "image_url": "https://example.com/chart.png",
            },
            {
                "type": "input_file",
                "file_url": "https://example.com/data.xlsx",
                "filename": "data.xlsx",
            },
        ],
    }],
)

curl https://apigw.mka1.com/api/v1/llm/responses \
  --request POST \
  --header 'Content-Type: application/json' \
  --header 'Authorization: Bearer <mka1-api-key>' \
  --header 'X-On-Behalf-Of: <end-user-id>' \
  --data '{
    "model": "meetkai:functionary-es-mini",
    "input": [
      {
        "type": "message",
        "role": "user",
        "content": [
          { "type": "input_text", "text": "Compare the chart in the image with the data in the spreadsheet. Are the numbers consistent?" },
          {
            "type": "input_image",
            "image_url": "https://example.com/chart.png"
          },
          {
            "type": "input_file",
            "file_url": "https://example.com/data.xlsx",
            "filename": "data.xlsx"
          }
        ]
      }
    ]
  }'

Próximos pasos

Salida multimodal — genera audio e imágenes en las respuestas
Archivos y almacenes vectoriales — sube y gestiona archivos para reutilización
Generar una respuesta — solicitudes solo de texto e intercambios multi-turno
Modo de voz avanzado — conversaciones de voz en tiempo real con LiveKit

​Tipos de entrada soportados

​Entrada de imagen

​Imagen vía URL

​Imagen vía base64

​Imagen vía file_id

​Entrada de audio

​Entrada de documento

​Documento vía URL

​Documento vía base64

​Documentos escaneados y OCR

​Formatos de documento soportados

​Entrada mixta

​Próximos pasos