Update a Chatbot

This endpoint allows you to update the configuration of an existing chatbot in your Nexvio.ai account.

Endpoint

PATCH https://api.nexvio.ai/v1/chatbots/{chatbotId}

Headers

Name	Required	Description
`Authorization`	Yes	Your API key in the format: `Bearer YOUR_API_KEY`
`Content-Type`	Yes	Must be `application/json`

Path Parameters

Parameter	Type	Required	Description
`chatbotId`	string	Yes	The ID of the chatbot to update

Request Body

All fields are optional. Only include the fields you want to update.

Parameter	Type	Description
`name`	string	The name of your chatbot
`welcome_message`	string	Initial message displayed when a user opens the chatbot
`model`	string	AI model to use. Options: `gpt-3.5-turbo`, `gpt-4`
`instructions`	string	System instructions that define your chatbot’s personality and knowledge
`team_id`	string	The team ID if you want to reassign this chatbot to a different team
`appearance`	object	Configuration for the chatbot’s visual appearance (see below)

Appearance Object

Parameter	Type	Description
`primary_color`	string	Primary color for the chatbot UI (hex code)
`chat_bubble_button_style`	string	Style of the chat button. Options: `round`, `square`
`position`	string	Position of the chat widget. Options: `bottom-right`, `bottom-left`, `top-right`, `top-left`
`chatbox_header_text`	string	Text to display in the chatbox header
`hide_branding`	boolean	Whether to hide Nexvio.ai branding. Requires enterprise plan

Example Request

{
  "name": "Updated Sales Assistant",
  "welcome_message": "Welcome back! How can I help you with our products today?",
  "model": "gpt-4",
  "instructions": "You are a sales assistant for Acme Corp, specialized in our new premium CRM solution AcmeCRM Pro. Focus on highlighting the new AI-powered features and enterprise integrations. For detailed pricing, direct users to book a demo call.",
  "appearance": {
    "primary_color": "#2A52BE",
    "chatbox_header_text": "Acme Sales Team"
  }
}

Response

{
  "status": "success",
  "data": {
    "chatbot": {
      "id": "chatbot_456def",
      "team_id": "team_123abc",
      "name": "Updated Sales Assistant",
      "welcome_message": "Welcome back! How can I help you with our products today?",
      "model": "gpt-4",
      "instructions": "You are a sales assistant for Acme Corp, specialized in our new premium CRM solution AcmeCRM Pro...",
      "appearance": {
        "primary_color": "#2A52BE",
        "chat_bubble_button_style": "round",
        "position": "bottom-right",
        "chatbox_header_text": "Acme Sales Team",
        "hide_branding": false
      },
      "created_at": "2023-07-15T12:30:45Z",
      "updated_at": "2023-07-17T09:12:34Z"
    }
  }
}

Error Responses

Authentication Error

{
  "status": "error",
  "error": {
    "code": "unauthorized",
    "message": "Invalid API key"
  }
}

Not Found Error

{
  "status": "error",
  "error": {
    "code": "not_found",
    "message": "Chatbot not found"
  }
}

Validation Error

{
  "status": "error",
  "error": {
    "code": "validation_error",
    "message": "Invalid request data",
    "details": {
      "model": "Invalid model specified. Allowed values: gpt-3.5-turbo, gpt-4"
    }
  }
}

Notes

Only include the fields you want to update in the request body. Omitted fields will remain unchanged.
Changing the AI model may affect pricing based on your plan.
To update the chatbot’s sources, use the specific endpoints for managing sources.
To update the profile picture or icon, use the separate upload endpoints.

Special Considerations

Updating Instructions

When updating the instructions field, keep in mind:

The new instructions will apply to all future conversations
Existing conversations in progress will continue to use the previous instructions
Instructions should be comprehensive, as they define your chatbot’s personality and knowledge
Maximum length for instructions is 32,000 characters

Changing Models

When changing the AI model:

GPT-4 offers higher quality responses but may be slower and more expensive than GPT-3.5-Turbo
Make sure your plan supports the selected model
Consider testing the new model in a staging environment before updating a production chatbot

Code Examples

cURL

curl -X PATCH "https://api.nexvio.ai/v1/chatbots/chatbot_456def" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "Updated Sales Assistant",
    "welcome_message": "Welcome back! How can I help you with our products today?",
    "appearance": {
      "primary_color": "#2A52BE"
    }
  }'

JavaScript

const chatbotId = 'chatbot_456def';
const response = await fetch(`https://api.nexvio.ai/v1/chatbots/${chatbotId}`, {
  method: 'PATCH',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    name: 'Updated Sales Assistant',
    welcome_message: 'Welcome back! How can I help you with our products today?',
    appearance: {
      primary_color: '#2A52BE'
    }
  })
});

const data = await response.json();
console.log(data);

Python

import requests

chatbot_id = "chatbot_456def"
url = f"https://api.nexvio.ai/v1/chatbots/{chatbot_id}"
headers = {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json"
}
payload = {
    "name": "Updated Sales Assistant",
    "welcome_message": "Welcome back! How can I help you with our products today?",
    "appearance": {
        "primary_color": "#2A52BE"
    }
}

response = requests.patch(url, headers=headers, json=payload)
data = response.json()
print(data)