ReplyCX Documentation
Login
  • ⛩️Welcome to ReplyCX Knowledge Base! 📚
    • ReplyCX Basics
  • ▶️GETTING STARTED
    • Building a Chatbot
    • Testing a Chatbot
    • Channel Configurations
    • Deploying a Chatbot
    • Utility Tools
  • 🧩ACTION BLOCKS
    • Overview
    • Trigger
    • Send Message
    • Collect Input
    • Buttons
    • Carousel
    • Calendar
    • Send an Email
    • Condition
    • Image Carousel
    • Human Handover
    • Slider
    • Collect File
    • Delay
    • Form
    • Flow
    • Code-block
    • Options
    • Jump
    • List
    • Reply Button
    • AI Model
    • SET AI
    • Answer AI
    • AI AGENT
    • Webhook
    • Javascript
    • Send Status
    • Http Request
    • Dynamic data
    • Whatsapp flow
  • 🦾AI Studio
    • Building a GPT Chatbot
    • Knowledge Base
    • Training on historical live chat to generate response
    • Retrain frequency for URL data source
    • Custom Answers
    • Function Call
    • Prompts
    • Tokens
    • Setting up retrain
    • Advanced Crawling Criteria
  • ⛓️Integrations
    • Types of Integrations
    • Service Call
    • Google Sheets
      • Support for “Update Record” in Google Sheets
    • Codeblock
    • Google Calendar
    • Calendly
    • Zoho CRM
    • Hubspot
    • Dialog Flow
    • Events
    • Google Analytics
    • Freshdesk
    • Salesforce
    • Zapier
    • Airtable
    • Public API's
  • 🟢WhatsApp Business API
    • Prerequisites
    • WhatsApp Business API - Meta
    • Using a test WhatsApp Business API account
    • Product catalog on WhatsApp
    • Sync WhatsApp Template
    • Support for Carousel template message
  • Instagram
    • Using the Instagram Channel
  • 💬Live Chat
    • Overview
    • Saved Replies
    • Manage Saved Replies
    • Message status on live chat
    • Generating Response Using AI.
    • Rewriting existing response with AI
    • Labels
    • Managing Labels
    • Qualification details covered during a conversation
    • Settings
    • Filter conversations
    • Conversation History
    • Close a conversation
    • Related / Past Conversations
    • Elements on conversation card
    • Kind of Conversation Status
    • Copy Chat Transcript of a Conversation
    • Customize Live Chat Screen
    • Restart Conversation
    • Blocking Contacts
    • Agent status on live chat
  • ⚙️Troubleshooting
    • Variable Manager
    • Fallback Variables
    • Human Handover Configuration
    • Clone a bot
    • Preffered Image Dimensions
    • Working of Link Tracking
    • Setting up variables using trigger block
    • Availability of agents in Human Handover
    • Creating loop in the conversational flow
    • Requesting Edit Access
    • Cookies
  • 📢Outbound Bots
    • Outbound Action Blocks
      • Delay
      • Send WhatsApp
      • Send SMS
      • Send Email
    • Building a One-Off Campaign
    • Building a Ongoing Campaign
    • Creating WhatsApp Templates
  • 📱Chat Widget Customization
    • Embedding Chat Widgets
    • Customize Chat Widget UI using CSS
    • Display Chat Widget in iFrame
    • Change Appearance
    • Chat widget 3.0
  • 🏦Account Management
    • Manage Teams
    • Manage Teammates
    • Manage Roles
      • Channel configuration Permission
    • Opt Out Management
  • 📊Reporting
    • Custom Reports
    • Contacts Feature Recap
    • Scheduling Contact Report
    • Weekly Reports and Interactions
    • Export a contact list
    • Tracking link clicks on chatbot messages
    • Agent Report
    • AI Agent Report
    • Outbound Report
  • 🧑‍💻 Support
    • Forget Password
Powered by GitBook
On this page
  • Configuring the AI Model Block:
  • AI Model:
  • Variable:
  • Persona:
  • Restrict answer size:
  • Creativity in responses:
  • Allow external data:
  • Ask for feedback:

Was this helpful?

  1. ACTION BLOCKS

AI Model

PreviousReply ButtonNextSET AI

Last updated 11 months ago

Was this helpful?

The AI model action block is the perfect solution for providing intelligent and informative responses to open-ended queries from visitors.

By utilizing OpenAI APIs and leveraging trained data, this powerful tool enables you to deliver smarter replies that will impress and engage your audience.

With AI model block, you can confidently address any question / inquiry accuracy and efficiency.

Configuring the AI Model Block:

AI Model:

Here you will see all the AI Models which you have created in the AI Studio. Depending on the AI model that is selected, the chatbot will provide responses to inquiries. It is important to ensure that the AI model has been properly trained with accurate information.

Variable:

In order to obtain a response from the AI model, it is necessary to submit the question to it.

Prior to the "AI model" action block, it is important to utilize a "Collect input" action block to inquire about the question and store it in a variable.

The variable holding the question should be selected here.

Persona:

Create a persona text that serves as the basis for the AI model's response. This allows you to receive answers to your questions in a format that is easily understandable for you.

Some of the examples of persona are as follows:

  • Answer the questions asked in a simple and easy to understand manner.

  • Answer these questions as a 5-year old.

  • Give me answers considering me as a technical person.

  • For the duration of this conversation, please fully immerse yourself in the persona of Albert Einstein.

Restrict answer size:

When using the AI model, you have the option to specify the desired length of the responses when asking a question.

This length is determined based on tokens, which can be considered as fragments of words.

Specifically, 1 token is equivalent to 4 characters.

Creativity in responses:

Users have the option to customize their experience by choosing whether they prefer unique responses for each question or a consistent response for repeated inquiries.

This can be achieved by defining a number between 0 and 1. A value closer to 1 provides distinct responses, while a value closer to 0 delivers fixed responses.

By default, the system is set at 0.5, striking a balance between variety and consistency.

Allow external data:

The objective of constructing an AI model is to have the chatbot respond exclusively to queries derived from a particular domain or set of files.

This setup grants you the ability to determine whether you want the chatbot to address inquiries using the broader knowledge of the global ChatGPT model, or restrict its responses solely to the information it has been trained on within that specific AI model.

As a default setting, this configuration is deactivated.

Ask for feedback:

After responding to a query, the chatbot will prompt the user for feedback by providing options for a thumbs up or thumbs down.

The feedback received will be displayed on the AI studio page, allowing for visibility and assessment of performance.

🧩