Generar una respuesta

Utiliza el recurso de Respuestas cuando quieras que la API MKA1 devuelva texto. Comienza con una cadena simple para prompts sencillos. Utiliza elementos de mensaje cuando necesites roles explícitos o estado de conversación.

Enviar un prompt simple

Pasa una cadena en input para una solicitud de un solo turno. La respuesta incluye el texto generado en output_text.

mka1 llm responses create \
  --model meetkai:functionary-es-mini \
  --input '"Write a one-sentence summary of the MKA1 API."' \
  -H 'X-On-Behalf-Of: <end-user-id>'

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: 'Write a one-sentence summary of the MKA1 API.',
}, { 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: 'Write a one-sentence summary of the MKA1 API.',
  stream: false,
});

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

var sdk = new SDK(bearerAuth: "Bearer YOUR_API_KEY");

var res = await sdk.Llm.Responses.CreateAsync(new ResponsesCreateRequest()
{
    Model = "meetkai:functionary-es-mini",
    Input = ResponsesCreateRequestInput.CreateStr(
        "Write a one-sentence summary of the MKA1 API."),
});

from mka1 import SDK

sdk = SDK(bearer_auth="Bearer YOUR_API_KEY")

res = sdk.llm.responses.create(
    model="meetkai:functionary-es-mini",
    input="Write a one-sentence summary of the MKA1 API.",
    http_headers={"X-On-Behalf-Of": "<end-user-id>"},
)

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": "Write a one-sentence summary of the MKA1 API."
  }'

Si no estás actuando en nombre de un usuario final, omite X-On-Behalf-Of.

Agregar instrucciones

Utiliza instructions para definir el comportamiento antes de que el modelo vea la entrada del usuario. Mantén las instrucciones cortas y específicas.

mka1 llm responses create \
  --model meetkai:functionary-es-mini \
  --instructions 'You are a support assistant. Reply in plain English. Keep answers under 80 words.' \
  --input '"Explain what embeddings are used for."'

const result = await mka1.llm.responses.create({
  model: 'meetkai:functionary-es-mini',
  instructions: 'You are a support assistant. Reply in plain English. Keep answers under 80 words.',
  input: 'Explain what embeddings are used for.',
});

const response = await openai.responses.create({
  model: 'meetkai:functionary-es-mini',
  instructions: 'You are a support assistant. Reply in plain English. Keep answers under 80 words.',
  input: 'Explain what embeddings are used for.',
  stream: false,
});

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

var sdk = new SDK(bearerAuth: "Bearer YOUR_API_KEY");

var res = await sdk.Llm.Responses.CreateAsync(new ResponsesCreateRequest()
{
    Model = "meetkai:functionary-es-mini",
    Instructions = "You are a support assistant. Reply in plain English. Keep answers under 80 words.",
    Input = ResponsesCreateRequestInput.CreateStr("Explain what embeddings are used for."),
});

res = sdk.llm.responses.create(
    model="meetkai:functionary-es-mini",
    instructions="You are a support assistant. Reply in plain English. Keep answers under 80 words.",
    input="Explain what embeddings are used for.",
)

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",
    "instructions": "You are a support assistant. Reply in plain English. Keep answers under 80 words.",
    "input": "Explain what embeddings are used for."
  }'

Enviar mensajes estructurados

Utiliza un arreglo de elementos de mensaje en input cuando quieras roles explícitos. Cada elemento de mensaje utiliza type, role y content.

mka1 llm responses create --body '{
  "model": "meetkai:functionary-es-mini",
  "input": [
    { "type": "message", "role": "developer", "content": "Answer as a technical writer. Keep the reply concise." },
    { "type": "message", "role": "user", "content": "Draft a short product update about faster response times." }
  ]
}'

const result = await mka1.llm.responses.create({
  model: 'meetkai:functionary-es-mini',
  input: [
    { type: 'message', role: 'developer', content: 'Answer as a technical writer. Keep the reply concise.' },
    { type: 'message', role: 'user', content: 'Draft a short product update about faster response times.' },
  ],
});

const response = await openai.responses.create({
  model: 'meetkai:functionary-es-mini',
  input: [
    { type: 'message', role: 'developer', content: 'Answer as a technical writer. Keep the reply concise.' },
    { type: 'message', role: 'user', content: 'Draft a short product update about faster response times.' },
  ],
  stream: false,
});

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

var sdk = new SDK(bearerAuth: "Bearer YOUR_API_KEY");

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.Developer,
            Content = InputMessageContent1.CreateStr(
                "Answer as a technical writer. Keep the reply concise."),
        }),
        Item.CreateInputMessage(new InputMessage()
        {
            Role = InputMessageRole.User,
            Content = InputMessageContent1.CreateStr(
                "Draft a short product update about faster response times."),
        }),
    }),
});

res = sdk.llm.responses.create(
    model="meetkai:functionary-es-mini",
    input=[
        {"type": "message", "role": "developer", "content": "Answer as a technical writer. Keep the reply concise."},
        {"type": "message", "role": "user", "content": "Draft a short product update about faster response times."},
    ],
)

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": "developer", "content": "Answer as a technical writer. Keep the reply concise." },
      { "type": "message", "role": "user", "content": "Draft a short product update about faster response times." }
    ]
  }'

Este patrón es útil cuando quieres que el cuerpo de la solicitud lleve directamente el historial de mensajes.

Continuar un intercambio de varios turnos

Utiliza previous_response_id para continuar desde una respuesta anterior sin reenviar todo el historial.

mka1 llm responses create \
  --model meetkai:functionary-es-mini \
  --previous-response-id resp_123 \
  --input '"Now turn that into an email subject line."'

const second = await mka1.llm.responses.create({
  model: 'meetkai:functionary-es-mini',
  previousResponseId: 'resp_123',
  input: 'Now turn that into an email subject line.',
});

const second = await openai.responses.create({
  model: 'meetkai:functionary-es-mini',
  previous_response_id: 'resp_123',
  input: 'Now turn that into an email subject line.',
  stream: false,
});

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

var sdk = new SDK(bearerAuth: "Bearer YOUR_API_KEY");

// First request
var first = await sdk.Llm.Responses.CreateAsync(new ResponsesCreateRequest()
{
    Model = "meetkai:functionary-es-mini",
    Input = ResponsesCreateRequestInput.CreateStr("Write a one-line product tagline."),
});

res = sdk.llm.responses.create(
    model="meetkai:functionary-es-mini",
    previous_response_id="resp_123",
    input="Now turn that into an email subject line.",
)

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",
    "previous_response_id": "resp_123",
    "input": "Now turn that into an email subject line."
  }'

Si necesitas un contenedor de conversación reutilizable, créalo con el recurso de Conversaciones y luego pasa el ID de la conversación en conversation.

# Crear una conversación
mka1 llm conversations create --body '{
  "metadata": { "session_id": "web-42" }
}'

# Usar la conversación en una solicitud de respuesta
mka1 llm responses create \
  --model meetkai:functionary-es-mini \
  --conversation conv_123 \
  --input '"What should I ask next to refine this draft?"'

const conv = await mka1.llm.conversations.create({
  metadata: { session_id: 'web-42' },
});

const result = await mka1.llm.responses.create({
  model: 'meetkai:functionary-es-mini',
  conversation: conv.id,
  input: 'What should I ask next to refine this draft?',
});

const conv = await openai.conversations.create({
  metadata: { session_id: 'web-42' },
});

const response = await openai.responses.create({
  model: 'meetkai:functionary-es-mini',
  conversation: conv.id,
  input: 'What should I ask next to refine this draft?',
  stream: false,
});

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

var sdk = new SDK(bearerAuth: "Bearer YOUR_API_KEY");

var conv = await sdk.Llm.Conversations.CreateAsync(new CreateConversationRequest()
{
    Metadata = new Dictionary<string, string> { { "session_id", "web-42" } },
});

conv = sdk.llm.conversations.create(
    metadata={"session_id": "web-42"},
)

res = sdk.llm.responses.create(
    model="meetkai:functionary-es-mini",
    conversation=conv.id,
    input="What should I ask next to refine this draft?",
)

# Crear conversación
curl https://apigw.mka1.com/api/v1/llm/conversations \
  --request POST \
  --header 'Content-Type: application/json' \
  --header 'Authorization: Bearer <mka1-api-key>' \
  --header 'X-On-Behalf-Of: <end-user-id>' \
  --data '{
    "metadata": { "session_id": "web-42" }
  }'

# Usar conversación en una solicitud de respuesta
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",
    "conversation": "conv_123",
    "input": "What should I ask next to refine this draft?"
  }'

Consulta las páginas de Conversaciones y Respuestas en la Referencia de la API para ver el flujo de trabajo completo del recurso.

Transmitir texto a medida que se genera

Establece stream en true para recibir eventos enviados por el servidor en lugar de esperar la respuesta completa.

mka1 llm responses create \
  --model meetkai:functionary-es-mini \
  --input '"Write three release notes bullets for our docs update."' \
  --stream

import { CreateAcceptEnum } from '@meetkai/mka1/sdk/responses';

const result = await mka1.llm.responses.create({
  model: 'meetkai:functionary-es-mini',
  input: 'Write three release notes bullets for our docs update.',
  stream: true,
}, { acceptHeaderOverride: CreateAcceptEnum.TextEventStream });

const stream = await openai.responses.create({
  model: 'meetkai:functionary-es-mini',
  input: 'Write three release notes bullets for our docs update.',
  stream: true,
});

for await (const event of stream) {
  if (event.type === 'response.output_text.delta') {
    process.stdout.write(event.delta);
  }
}

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

var sdk = new SDK(bearerAuth: "Bearer YOUR_API_KEY");

var res = await sdk.Llm.Responses.CreateAsync(new ResponsesCreateRequest()
{
    Model = "meetkai:functionary-es-mini",
    Input = ResponsesCreateRequestInput.CreateStr(
        "Write three release notes bullets for our docs update."),
    Stream = true,
});

res = sdk.llm.responses.create(
    model="meetkai:functionary-es-mini",
    input="Write three release notes bullets for our docs update.",
    stream=True,
)

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": "Write three release notes bullets for our docs update.",
    "stream": true
  }'

Utiliza el streaming cuando quieras mostrar la salida parcial a medida que llega.

Próximos pasos

Revisa la visión general de la API para detalles de autenticación y URL base
Consulta respuestas en segundo plano cuando necesites delegar trabajos de larga duración y hacer polling o streaming para obtener resultados
Consulta gestionar conversaciones para organizar intercambios de varios turnos en contenedores de conversación reutilizables
Consulta gestionar agentes cuando necesites definiciones de agente reutilizables y ejecuciones persistentes

​Enviar un prompt simple

​Agregar instrucciones

​Enviar mensajes estructurados

​Continuar un intercambio de varios turnos

​Transmitir texto a medida que se genera

​Próximos pasos