Skip to main content

Floating Knowledge Bot Node

The Floating Knowledge Bot node creates an AI-powered chatbot interface that provides knowledge-based contextual responses using uploaded reference materials and customizable bot controls. This node enables sophisticated conversational experiences with support for multiple interaction modes, knowledge references, and user experience customizations.

Floating Knowledge Bot node

Basic Usage​

Use the Image, Knowledge Bank, Floating Knowledge Bot, Read Journal, and Display Text nodes for your process to create comprehensive knowledge-based chatbot experiences.

Inputs​

The Floating Knowledge Bot node accepts multiple inputs to customize the bot's behavior and appearance:

The Bot Name​

  • Type: Text for the chatbot's display name (green dot)
  • Mandatory: Optional
  • Works best with: Text node

Define a custom name that will be displayed to users when interacting with the bot.

Icon Image​

  • Type: Image for the bot's avatar (purple dot)
  • Mandatory: Optional
  • Works best with: Image node, File Upload

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

Bot Icon​

  • Type: Alternative bot icon input (green dot)
  • Mandatory: Optional
  • Works best with: Image node, File Upload

Provide an alternative icon for the bot's visual representation.

Bot Introduction - First Message​

  • Type: Text for the initial greeting (green dot)
  • Mandatory: Optional
  • Works best with: Text node

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

Additional System Prompt​

  • Type: Text to supplement default behavior (green dot)
  • Mandatory: Optional
  • Works best with: Text node

Add instructions that enhance the bot's default behavior without replacing it.

Overwrite System Prompt​

  • Type: Text to replace default behavior (green dot)
  • Mandatory: Optional
  • Works best with: Text node

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

Knowledge Reference​

  • Type: Knowledge base connection (yellow dot)
  • Mandatory: Optional
  • Works best with: Knowledge Bank output

Connect to uploaded reference documents to provide the bot with contextual knowledge.

Reference Text​

  • Type: Additional text references (green dot)
  • Mandatory: Optional
  • Works best with: Text node, Document content

Supply additional reference text that the bot can use to inform responses.

Outputs​

The Floating Knowledge Bot does not have explicit output connections in the standard flow, as it operates as an interactive UI element. However, it can be configured to write conversations to journals for later retrieval.

Configuration​

Process Type​

Select the AI model to power your chatbot:

  • GPT-5 Mini: Fast and efficient model for most chatbot applications
  • GPT-4o-mini: Cost-effective option with good performance
  • GPT-4o: Advanced reasoning for complex conversations
  • Other supported models: Additional AI models available in your instance

Bot Control​

The Bot Name​

Set a custom display name for your chatbot that users will see in the interface.

Icon Image​

Upload a visual representation for your bot to create a distinct identity.

Bot Icon​

Provide an alternative or additional icon for the bot interface.

Bot Introduction - First Message​

Configure the initial greeting message that welcomes users.

Additional System Prompt​

Add supplementary instructions to guide the bot's responses without replacing core behavior.

Overwrite System Prompt​

Replace all default instructions with your custom directives for complete behavioral control.

User Interaction​

First User Message​

  • Type: Text input (green dot)
  • Purpose: Pre-populate the initial user message
  • Works best with: Text node

Set the first message from the user to start conversations automatically.

Placeholder​

  • Type: Text input (green dot)
  • Purpose: Placeholder text in the user input field
  • Works best with: Text node

Define helpful placeholder text that appears in the message input area.

Knowledge Bot Theme​

  • Type: Theme selector (green dot)
  • Purpose: Customize the visual appearance of the bot interface
  • Options: Various theme options for different visual styles

Choose a theme that matches your application's design language.

Temperature​

Control the creativity and randomness of bot responses:

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

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

Interaction Options​

Math Input​

  • Type: Checkbox
  • Purpose: Enable mathematical expression input and rendering
  • Use case: When users need to input equations or mathematical notation

Handwriting Input​

  • Type: Checkbox
  • Purpose: Enable handwriting recognition for user input
  • Use case: For touch/stylus devices or handwritten responses

Attach File Input​

  • Type: Checkbox
  • Purpose: Allow users to upload files during conversation
  • Use case: When users need to share documents or images

Voice Typing​

  • Type: Checkbox
  • Purpose: Enable voice-to-text input for users
  • Use case: For hands-free input or accessibility

Journal Integration​

Write To Journal​

  • Type: Checkbox
  • Purpose: Automatically save conversations to journal
  • Use case: For record-keeping, analysis, or later retrieval

When enabled, all conversations will be stored in the specified journal for future reference.

Show Chatbot​

  • Type: Checkbox
  • Purpose: Control chatbot visibility on page load
  • Use case: Show or hide the chatbot interface initially

When unchecked, the chatbot will be hidden initially and can be triggered by user action.

Retrieve Chatbot History​

  • Type: Checkbox
  • Purpose: Load previous conversation history from journal
  • Use case: Maintain conversation continuity across sessions

When enabled, the bot will load and display previous conversations from the journal.

Journal Configuration​

Journal Name​

  • Type: Text field (green dot input)
  • Example: Enter journal name
  • Purpose: Specify the journal name for storing conversations
  • Placeholder: "Enter journal name"

Enter a descriptive journal identifier where conversations should be saved. Use a consistent naming convention for easy identification. This field appears when "Write To Journal" is enabled.

Journal Reference ID​

  • Type: Text field (green dot input)
  • Example: Enter journal ref id
  • Purpose: Unique identifier for journal entries
  • Placeholder: "Enter journal ref id"

Provide the reference ID for linking journal entries. This ID connects conversations to specific users, sessions, or contexts. This field appears when "Write To Journal" is enabled.

Set Character Limit​

  • Type: Checkbox
  • Purpose: Limit the number of characters in user responses
  • Use case: Enforce concise responses or manage input length

When enabled, restricts the length of user messages to prevent excessively long inputs.

Passthrough Mode​

  • Type: Checkbox
  • Purpose: Enable passthrough mode for the chatbot
  • Use case: Special mode for specific workflow behaviors

When enabled, allows the chatbot to operate in passthrough mode for integration with other workflow components.

Node Jump Scenarios​

+ Add scenario​

Add custom scenarios or branching logic for specific conversation flows.

Click the "+ Add scenario" button to create conditional jumps or redirects based on conversation states, user inputs, or bot responses. This enables complex conversational flows and workflow integrations.

Use Cases:

  • Redirect to specific flows based on user intent
  • Trigger different workflows based on conversation outcomes
  • Create exit conditions for the chatbot
  • Implement conditional logic for complex interactions

Example Workflows​

Knowledge-Based Customer Support Bot​

Scenario: Create a floating chatbot that provides customer support using uploaded documentation and knowledge base.

Floating Knowledge Bot Example

Steps to Create the Flow:

  1. Start with the Start Node.

  2. Add Image nodes for bot icons:

    • Upload 2-3 different icon images for the bot
    • Connect to Icon Image and Bot Icon inputs

  3. Add a Knowledge Bank node:

    • Upload your reference documents (PDFs, manuals, FAQs)
    • Connect Knowledge Output to Knowledge Reference input

  4. Configure the Floating Knowledge Bot Node:

    i. Select Process Type:

    • Choose "GPT-5 Mini" for fast, efficient support
    • Or "GPT-4o-mini" for cost-effective support
    • Or "GPT-4o" for advanced knowledge retrieval

    ii. Configure Bot Control:

    • Set Bot Name (e.g., "Support Assistant")
    • Upload Icon Image
    • Set Bot Introduction: "Hello! How can I help you today?"
    • Add Additional System Prompt if needed

    iii. Set User Interaction Options:

    • Enable "Attach File Input" for users to share screenshots
    • Enable "Voice Typing" for accessibility
    • Set Placeholder: "Ask me anything..."
    • Adjust Temperature (0.5 for balanced responses)

    iv. Configure Journal Integration:

    • Check "Write To Journal" to save conversations
    • Enter Journal Name in the provided field (e.g., "Support-Conversations-2025")
    • Enter Journal Reference ID in the provided field (unique identifier)
    • Check "Retrieve Chatbot History" for continuity
    • Optionally check "Show Chatbot" to display on page load
    • Check "Set Character Limit" if you want to restrict message length
    • Check "Passthrough Mode" if needed for workflow integration

    v. Customize Appearance:

    • Select Knowledge Bot Theme
    • Configure other visual options

  5. Add a Read Journal node (optional):

    • Connect to retrieve conversation history
    • Use Journal ID from configuration

  6. Add Display Text nodes (optional):

    • For displaying conversation summaries or analytics

Result:

Users interact with a floating knowledge-based chatbot that:

  • Provides accurate answers using reference documentation
  • Maintains conversation history through journal integration
  • Supports multiple input methods (text, voice, files)
  • Offers a customized, branded interface
  • Retrieves previous conversations for continuity

Notes​

  • The floating bot provides a non-disruptive user experience
  • Knowledge Bank integration enables accurate, source-based responses
  • Journal integration allows for conversation persistence and analysis
  • Multiple input modes enhance accessibility
  • Theme customization ensures brand consistency
  • Temperature control affects response style and creativity
  • Bot icon and name create recognizable identity
  • History retrieval maintains conversation context across sessions