Features
AI Assistant
Chat with AI directly in Chatelope
AI Assistant
Chatelope includes a built-in AI chat feature. Connect your own API keys or use self-hosted models to chat without leaving the app.
Getting Started
- Go to Settings > AI Settings
- Select a provider
- Enter your API key or configure your server
- Start a new conversation and begin chatting
Supported Providers
Cloud Providers
| Provider | Models |
|---|---|
| OpenAI | GPT-4o, GPT-4 Turbo, GPT-3.5 |
| Anthropic | Claude 3.5 Sonnet, Claude 3 Opus, Claude 3 Haiku |
| Gemini 1.5 Pro, Gemini 1.5 Flash |
Self-Hosted
| Provider | Description |
|---|---|
| Ollama | Run models locally on your machine |
| LM Studio | Local model server with UI |
See Self-Hosted AI for setup instructions.
Features
Conversation Management
- Start new conversations
- Continue existing conversations
- Branch conversations to explore alternatives
- Export conversations as Markdown
Context Window
Chatelope manages the context window automatically:
- Recent messages are sent to the AI
- Older messages are summarized to fit the context
- You can adjust context settings per conversation
System Prompts
Customize the AI's behavior with system prompts:
- Click the gear icon in the chat header
- Enter your system prompt
- The AI will follow these instructions
Example system prompts:
You are a helpful coding assistant. Provide code examples when relevant.You are a writing tutor. Help improve my writing with constructive feedback.Model Switching
Switch models mid-conversation:
- Click the model name in the chat header
- Select a different model
- Continue the conversation
This is useful for using faster models for simple questions and more capable models for complex tasks.
Keyboard Shortcuts
| Shortcut | Action |
|---|---|
Enter | Send message |
Shift+Enter | New line |
Ctrl+N / Cmd+N | New conversation |
Escape | Stop generation |
Cost Tracking
If you're using API keys, Chatelope tracks your usage:
- View cost per conversation
- See monthly spending breakdown
- Set budget alerts
Go to Analytics to view your usage statistics.
Tips
- Be specific - Clear, detailed prompts get better responses
- Use context - Reference previous messages in the conversation
- Iterate - Ask follow-up questions to refine answers
- Try different models - Each model has strengths for different tasks