Skip to main content

Knowledge Bot Node

The Knowledge Bot node is designed to facilitate engaging conversations with users. Flow designers can define the bot's name, icon, and introductory messages, placeholder to enhance chatbot UI. The tool also allows to provide additional user and system prompts and temperature setting to enrich interactions. Additionally, it features a knowledge bank for reference, enabling the bot to provide informed responses.

Knowledge Bot node

Basic Usage​

Use the Text Input, Display Text, Form Node, Text Join and Knowledge Bot for your process.

Overview​

Designed to facilitate engaging conversations. Flow designer can define the bot's name, icon, and introductory messages, placeholder to enhance chatbot UI. The tool also allows to provide additional user and system prompts and temperature setting to enrich interactions. Additionally, it features a knowledge bank for reference, enabling the bot to provide informed responses.

Inputs​

The Knowledge Bot node accepts multiple inputs to customize its behavior and knowledge:

The Bot Name​

  • Type: Text name for the chatbot
  • Mandatory: Optional
  • Works best with: Text Input, Text node

Define a custom name for your bot that will be displayed to users.

Icon Image​

  • Type: Image for the bot's avatar
  • Mandatory: Optional
  • Works best with: Image Input, File Upload

Upload a custom icon or avatar image to represent your bot visually.

Knowledge Reference​

  • Type: Knowledge base connection from Knowledge Bank
  • Mandatory: Optional
  • Works best with: Knowledge Bank output

Connect to a Knowledge Bank node to provide the bot with reference documents and information.

Bot Introduction - First Message​

  • Type: Text for the bot's initial greeting
  • Mandatory: Optional
  • Works best with: Text Input, Text node

Define the first message users see when they start a conversation with the bot.

Additional System Prompt​

  • Type: Text to supplement the bot's default behavior
  • Mandatory: Optional
  • Works best with: Text Input, Text node

Add instructions to guide how the bot should respond without replacing the default system prompt.

Overwrite System Prompt​

  • Type: Text to completely replace the bot's default behavior
  • Mandatory: Optional
  • Works best with: Text Input, Text node

Replace the entire system prompt with custom instructions for complete control over bot behavior.

First User Message​

  • Type: Text for the initial user message
  • Mandatory: Optional
  • Works best with: Text Input, Text node

Pre-populate the first message from the user to start the conversation.

Placeholder​

  • Type: Text shown in the input field
  • Mandatory: Optional
  • Works best with: Text Input, Text node

Define placeholder text that appears in the user's message input field.

Outputs​

Full Chat Log​

  • Type: Complete conversation history
  • Works best with: Display Text, Document Download, AI General Prompt

Captures the entire conversation between the user and the bot, useful for analysis, record-keeping, or further processing.

Configuration​

Process Type​

Select the AI model to power your Knowledge Bot:

GPT-4o (Default in first screenshot)​

GPT-4o is OpenAI's advanced multimodal model, providing sophisticated conversational abilities and excellent knowledge retrieval.

GPT-4o-mini (Example screenshot)​

GPT-4o-mini is a fast and cost-effective model suitable for most chatbot applications, offering reliable responses at lower cost.

Other Available Models​

Choose from various AI models based on your needs:

  • Claude Sonnet 4.5: Anthropic's conversational model with strong reasoning
  • Gemini 2.5 Pro: Google's advanced model for complex conversations
  • GPT-3.5: Efficient model for straightforward chatbot interactions
  • Gemini 2.5 Flash Lite: Fast model for quick responses

Temperature​

Control the creativity and randomness of bot responses:

  • Lower values (0.0-0.3): More focused, consistent, and deterministic responses
  • Medium values (0.4-0.7): Balanced between consistency and creativity
  • Higher values (0.8-1.0): More creative, varied, and exploratory responses

Adjust the slider to find the right balance for your use case.

Additional Options​

Math Input​

  • Description: Enable mathematical expression input and rendering
  • Use case: When users need to input equations or mathematical notation
  • Default: Unchecked

Handwriting Input​

  • Description: Enable handwriting recognition for user input
  • Use case: When users prefer to write messages by hand (touch/stylus devices)
  • Default: Unchecked

Example Workflow​

Loan Estimator Chatbot​

Scenario: Create an expert mortgage broker chatbot that helps users estimate loans based on specific guidelines and knowledge.

Knowledge Bot Example

Steps to Create the Flow:

  1. Add a Start Node.

  2. Add and connect a Text node with the bot name.

    • Example text:
    Loan Estimator
    • Connect to The Bot Name input

  3. Add and connect an Image node with the bot icon.

    • Upload or select an icon (e.g., house with calculator icon)
    • Connect to Icon Image input

  4. Add and connect a Text node with system instructions.

    • Example text:
    You are an expert-level mortgage broker in the real estate department. 
    Your task is to create a tailored Loan Estimate that aligns with the 
    guidelines provided in the knowledge base.
    • Connect to Additional System Prompt input

  5. Add and connect a Text node with the first user message.

    • Example text:
    Hi I want to estimate a loan..
    • Connect to First User Message input

  6. (Optional) Connect a Knowledge Bank to provide reference documents.

    • Upload loan guidelines, policies, and reference materials
    • Connect Knowledge Bank's output to Knowledge Reference input

  7. Configure the Knowledge Bot Node:

    • Select Process Type: GPT-4o-mini for cost-effective performance
    • Adjust Temperature: Set to medium (around 0.5) for balanced responses
    • Enable Math Input if loan calculations are needed
    • Set Placeholder text: "Ask about loan estimates..."

  8. Add and connect a Display Text to show the chat log (optional).

    • Connect Full Chat Log output to Display Text
    • Useful for monitoring or saving conversations

Result:

Users interact with a specialized loan estimator chatbot that:

  • Greets them with a professional introduction
  • Understands mortgage and loan terminology
  • Provides estimates based on knowledge base guidelines
  • Maintains context throughout the conversation
  • Offers expert-level advice on loan options

The chatbot appears with the custom "Loan Estimator" name and house icon, immediately establishing its purpose and building user trust.