How to use Elephas Super Chat
Introduction to Elephas Super Chat
Introduction
Elephas Super Chat is your primary interface for interacting with your Super Brain. This AI-powered chat assistant provides intelligent responses, generates content, and offers insights based on your indexed data.
Video Tutorial
For a complete walkthrough of Elephas Super Chat, refer to this video:
Smart Starter Questions
When you enter Brain, you'll see:
- Smart starter questions automatically generated based on your Role and indexed data (if you have no previous chats). Click any suggestion to start quickly, or type your own message.
- A list of your previous conversations (if you have chat history). Click any conversation to continue, or start a new one.
Starting a New Chat
To start a fresh conversation:
- Click the "+ New Chat" button at the top of the chat interface, or
- Press ⌘N (Command + N) on your keyboard
This creates a new conversation thread, separate from your previous chats.
System Message
System Messages (also called System Instructions or Custom Instructions) define how Elephas behaves during your chat session.
They set the AI’s tone, style, and context — helping you personalize responses to match your workflow.
To learn how to create and apply your own custom instructions, visit the detailed guide below:
Selecting AI Models
For Individual Sessions:
- Alternatively, open Chat Settings → General → Model to view and switch models
For Global Settings:
- Go to Preferences → Model Settings
- Choose your default AI model, which applies to all new chat sessions
Offline Model Indicator
If your selected Brain uses Elephas Offline for indexing and chat, an Offline badge appears in two places:
- Next to the brain name in the chat title (for example, "Chat with Offline Brain" with an Offline badge next to "Brain").
- In the top-right corner of the chat interface
This confirms that all indexing and chatting are occurring fully offline, so you don’t need to switch tabs or double-check — your private data stays secure and local.
For details on selecting and using Elephas Offline models, refer to this guide: Inbuilt Offline Models for 100% Privacy
Chat session
- You can type your question in the input box and click “Enter” to submit the question.
- Elephas will internally query the content indexed, then generate a response.
Citations
When you ask a question, Elephas generates response backed by your own data. Those references are listed under each response.
Every response includes citations from your indexed data, showing you exactly where the information came from. This helps you verify accuracy and explore source materials further.
New brain search
Click New brain search to trigger a fresh search across your Super Brain, useful when you want to ensure you're getting the most current results.
Unless you select "New brain search", follow-up questions will use the previous discussion context to respond.
Filters
To Focus your search on specific documents:
- Click the Filter icon to the left of the input box
- Select the documents you want to include
- Click Apply
Elephas will now only search within your selected documents.
Prompt Library
Access pre-built prompts designed to enhance your Elephas interactions. These templates help you get better results for common use cases.
Chat Settings
Customize your chat experience through various settings options. You can switch between different AI models to find the one that best suits your needs, adjust the AI's communication style and tone to match your preferences, and change the font appearance for better readability and visual comfort during extended chat sessions.
Default Chat
When you want to chat about general topics outside your Super Brain, use the default chat feature that Elephas offers. You can ask questions on any topic and even attach files for analysis.
To attach files:
- Click the Plus icon on the left of the input box
- Select the files you want to attach and Click Open to attach the files
- Ask questions about the attached files as usual
The entire file content will be processed, so consider using AI models that support higher token limits for large files
Got Questions?
We’ve got answers. Send us an email or join our Discord community for real time answers to your queries.
You will find links to both in the “Support” section of the Elephas app on your Mac -
