Endpoint

Endpoint

Request Headers

• Authorization: Bearer - The secret key for authenticating the API request.
• Content-Type: application/json - The content type of the request payload.

Request Body

• messages - (array, required): An array containing ALL the messages between the user and the assistant. Each message object should have content and role properties. The content field represents the text content of the message, and the role field can be either "user" or "assistant" to indicate the sender of the message.
• chatbotId - (string, required): Refers to the ID of the chatbot you want to interact with (found on the chatbot settings page).
• stream - (boolean, optional, defaults to false): A boolean value indicating whether to stream back partial progress or wait for the full response. If set to true, words will be sent back as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message. If set to false, the full response will be returned once it's ready.
• temperature - (number, optional, defaults to 0): What sampling temperature to use, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.
• conversationId - (string, optional): Refers to the ID of the current conversation. The only purpose of this is to save the conversation to the chatbot dashboard. If not provided, the conversation will not be saved. This ID should be generated on your end. You should have different IDs for different conversations and make requests using the same ID for the same conversation. Every time you send a message with a specific chatbotId, the last message in the messages array and the response will be added to the conversation.
• model - (string, optional): If this is added to the body, it takes precedence over the model set in the chatbot settings. If not set, the model set in the chatbot settings is used. The option for 'gpt-4 | gpt-4-turbo' only works on the Standard and the Unlimited plans.
• OpenAI models:
  • gpt-3.5-turbo
  • gpt-4-turbo
  • gpt-4
  • gpt-4o
  • gpt-4o-mini
• Claude models:
  • claude-3-5-sonnet
  • claude-3-haiku
  • claude-3-opus
• Gemini models:
  • gemini-1.5-flash
  • gemini-1.5-pro

Example Request

const response = await fetch('https://www.chatzuri.com/api/v1/chat', {
  method: 'POST',
  headers: {
    Authorization: 'Bearer '
  },
  body: JSON.stringify({
    messages: [
      { content: 'How can I help you?', role: 'assistant' },
      { content: 'What is chatzuri?', role: 'user' }
    ],
    chatbotId: '',
    stream: false,
    model: 'gpt-3.5-turbo',
    temperature: 0
  })
});

if (!response.ok) {
  const errorData = await response.json();
  throw Error(errorData.message);
}
const data = await response.json(); 
console.log(data); // { "text": "..."}

import requests
import json

url = 'https://www.chatzuri.com/api/v1/chat'
headers = {
    'Authorization': 'Bearer ',
    'Content-Type': 'application/json'
}
data = {
    "messages": [
        {"content": "How can I help you?", "role": "assistant"},
        {"content": "What is chatzuri?", "role": "user"}
    ],
    "chatbotId": "",
    "stream": False,
    "temperature": 0
}

response = requests.post(url, headers=headers, data=json.dumps(data))
json_data = response.json()

if response.status_code == 200:
  print("response:", json_data['text'])
else:
  print('Error:' + json_data['message'])

curl https://www.chatzuri.com/api/v1/chat \
  -H 'Authorization: Bearer ' \
  -d '{
  "messages": [
    {"content": "How can I help you?", "role": "assistant"},
    {"content": "What is chatzuri?", "role": "user"}
  ],
  "chatbotId": "",
  "stream": false,
  "temperature": 0
}'

POST /api/v1/chat HTTP/1.1
Host: www.chatzuri.com
Authorization: Bearer 
Content-Type: application/json

{
  "messages": [
    {"content": "How can I help you?", "role": "assistant"},
    {"content": "What is chatzuri?", "role": "user"}
  ],
  "chatbotId": "",
  "stream": false,
  "temperature": 0
}

Response

{
  "text": "Chatzuri is an AI chatbot builder that lets you create a GPT-based chatbot that knows data."
}

• chatbotName - (string, required): The name of the chatbot to be created.
• sourceText - (string, optional): The text data for the chatbot. This field is subject to the character limit based on your plan

Example Request with Streaming Functionality

const response = await fetch('https://www.chatzuri.com/api/v1/chat', {
  method: 'POST',
  headers: {
    Authorization: 'Bearer ',
    stream: true,
    temperature: 0,
    model: 'gpt-3.5-turbo'
  })
});

if (!response.ok) {
  const errorData = await response.json();
  throw Error(errorData.message);
}

const data = response.body;

if (!data) {
  // error happened
}

const reader = data.getReader();
const decoder = new TextDecoder();
let done = false;

while (!done) {
  const { value, done: doneReading } = await reader.read();
  done = doneReading;
  const chunkValue = decoder.decode(value);
  console.log(chunkValue); // This will log chunks of the chatbot reply until the reply is finished.
}

import requests
import json

url = 'https://www.chatzuri.com/api/v1/chat'
headers = {
    'Authorization': 'Bearer ',
    'Content-Type': 'application/json'
}
data = {
    "messages": [
        {"content": "How can I help you?", "role": "assistant"},
        {"content": "What is chatzuri?", "role": "user"}
    ],
    "chatbotId": "",
    "stream": True,
    "temperature": 0
}

response = requests.post(url, headers=headers, data=json.dumps(data), stream=True)

if response.status_code != 200:
    json_data = response.json()
    print('Error:' + json_data['message'])
  
else:
  decoder = response.iter_content(chunk_size=None)
  for chunk in decoder:
    chunk_value = chunk.decode('utf-8')
    print(chunk_value, end='', flush=True)