Saltar al contenido principal
POST
/
agents
/
{id}
/
query
This let you query your AI Employee for a specific query.
curl --request POST \
  --url https://app.zappway.ai/api/agents/{id}/query \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "query": "<string>",
  "conversationId": "<string>",
  "visitorId": "<string>",
  "temperature": 123,
  "streaming": true,
  "modelName": "gpt_5_4",
  "maxTokens": 123,
  "presencePenalty": 123,
  "frequencyPenalty": 123,
  "topP": 123,
  "filters": {
    "custom_ids": [
      "<string>"
    ],
    "datasource_ids": [
      "<string>"
    ]
  },
  "systemPrompt": "<string>",
  "userPrompt": "<string>",
  "promptType": "raw",
  "promptTemplate": "<string>"
}
'
{
  "answer": "<string>",
  "conversationId": "<string>",
  "visitorId": "<string>",
  "sources": [
    {}
  ]
}

​
Streaming

When streaming is enabled, the endpoint will emit events “answer” (answer of the model) and “endpoint_response” (full response of the endpoint)
import {
  EventStreamContentType,
  fetchEventSource,
} from '@microsoft/fetch-event-source';

let buffer = '';
let bufferEndpointResponse = '';
const ctrl = new AbortController();

await fetchEventSource(queryAgentURL, {
        method: 'POST',
        headers: {
          'Content-Type': 'application/json',
        },
        signal: ctrl.signal,
        body: JSON.stringify({
          streaming: true,
          query,
          conversationId,
          visitorId,
        }),

        async onopen(response) {
          if (response.status === 402) {
            throw new ApiError(ApiErrorType.USAGE_LIMIT);
          }
        },
        onmessage: (event) => {
          if (event.data === '[DONE]') {
            // End of stream
            ctrl.abort();

            try {
              const { sources, conversationId, visitorId } = JSON.parse(
                bufferEndpointResponse
              ) as ChatResponse;
            } catch {}
          } else if (event.data?.startsWith('[ERROR]')) {
            // ...
          } else if (event.event === "endpoint_response") {
            bufferEndpointResponse += event.data;
          } else if (event.event === "answer") {
            buffer += event.data;
            // ...
          }
       },
  });

Autorizaciones

​
Authorization
string
header
requerido

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Parámetros de ruta

​
id
string
requerido

ID of the AI Employee

Cuerpo

application/json
​
query
string
requerido

This is the query you want to ask your AI Employee.

​
conversationId
string

ID of the conversation (If not provided a new conversation is created)

​
visitorId
string

ID of the participant that's sending the query (If not provided a new ID is created)

​
temperature
number

Temperature of the model (min 0.0, max 1.0)

​
streaming
boolean

Enable streaming

​
modelName
enum<string>

Override agent model

Opciones disponibles:
gpt_5_4,
gpt_5_4_chat,
gpt_5_4_mini,
gpt_5_4_nano,
gpt_5_3_chat_latest,
gpt_5_3_codex,
gpt_5_2,
gpt_5_2_chat,
gpt_5_2_chat_latest,
gpt_5_1,
gpt_5_1_chat,
gpt_5,
gpt_5_mini,
gpt_5_4_mini,
gpt_5_4_nano,
minimax_m2_7,
mimo_v2_omni,
mimo_v2_pro,
gpt_5_nano,
gpt_4o_2024_11_20,
gpt_4o_mini_2024_07_18,
gemini_3_flash_preview,
gemini_3_pro_image_preview,
gemini_3_pro_preview,
gemini_pro_2_5,
gemini_flash_2_5,
gemini_flash_2_0,
nova_premier_v1,
nova_2_lite_v1,
claude_opus_4_5,
claude_4_5_sonnet,
claude_4_5_haiku,
claude_4_sonnet,
claude_3_5_sonnet,
claude_3_5_haiku,
grok_4,
grok_4_1_fast_free,
llama_4_maverick,
llama_4_scout,
mistral_large_2512,
deepseek_r1_0528,
deepseek_v3_0324,
sonar_pro,
lfm2_8b_a1b,
lfm_2_24b_a2b,
mixtral_8x22b,
mixtral_8x7b,
dolphin_mixtral_8x7b,
gpt_5_4,
gpt_5_3_chat_latest,
gpt_5_2_chat_latest,
gpt_5_3_codex,
claude_opus_4_6,
claude_sonnet_4_6,
gemini_3_1_flash_lite_preview,
gemini_3_1_flash_image_preview,
gemini_3_1_pro_preview
​
maxTokens
number

The maximum number of tokens to generate in the chat completion.

​
presencePenalty
number

Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.

​
frequencyPenalty
number

Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.

​
topP
number

An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.

​
filters
object
​
systemPrompt
string

AI Employee System Prompt

​
userPrompt
string

AI Employee User Prompt

​
promptType
enum<string>
obsoleto

(DEPRECATED in favor of systemPrompt and userPrompt) Set the prompt type for this query

Opciones disponibles:
raw,
customer_support
​
promptTemplate
string
obsoleto

(DEPRECATED in favor of systemPrompt and userPrompt) Set the prompt template for this query

Respuesta

Success

​
answer
string

The answer of the AI Employee.

​
conversationId
string

ID of the conversation

​
visitorId
string

ID of the participant that's sending the query

​
sources
object[]