Chat Node
Last updated: October 8, 2025
Search Toggle
Click search tab in chat interface
Activate web search when prompted
Model Selection and Think Toggle
Click model dropdown (bottom left)
Select preferred model
Click "Think" icon for deeper reasoning (supported models only)
RAG Mode Toggle
Retrieval Augmented Generation (RAG) selectively retrieves only the most relevant information from connected nodes. This optimizes token usage by filtering content before sending to the AI model.
Click scissor icon at bottom of chat to toggle RAG mode
Icon highlights when active
RAG token count appears at top of chat after LLM response
Only relevant context from connected nodes is used, not all content
Personas
Create and save custom system prompts:
Click "Select persona..." in input field
Click "Create Persona"
Set name, color, and prompt
Click "Create"
To use: Select from dropdown in input field
Audio Input
Click microphone icon or press Ctrl + M
Speak into microphone
Click "Done" or press Esc to stop
Edit transcribed text if needed
Send with send button or Cmd/Ctrl + Enter