Chat Node

Search Toggle

1. Click search tab in chat interface
2. Activate web search when prompted

---

Model Selection and Think Toggle

1. Click model dropdown (bottom left)
2. Select preferred model
3. 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.

1. Click scissor icon at bottom of chat to toggle RAG mode
2. Icon highlights when active
3. RAG token count appears at top of chat after LLM response
4. Only relevant context from connected nodes is used, not all content

Personas

Create and save custom system prompts:

1. Click "Select persona..." in input field
2. Click "Create Persona"
3. Set name, color, and prompt
4. Click "Create"

To use: Select from dropdown in input field

---

Audio Input

1. Click microphone icon or press Ctrl + M
2. Speak into microphone
3. Click "Done" or press Esc to stop
4. Edit transcribed text if needed
5. Send with send button or Cmd/Ctrl + Enter