Configuration¶
This page provides information about configuring VT.ai to suit your needs.
Configuration Options¶
VT.ai offers several configuration options that can be set through various methods:
- Command-line arguments
- Environment variables
- UI settings
- Configuration files
Model Configuration¶
You can configure which models to use for different types of operations:
- Chat models
- Vision models
- Text-to-speech models
- Image generation models
Web Search Settings¶
Customize how VT.ai handles web searches:
- Summarize Search Results: Toggle between AI-summarized results and raw search output
- Enabled (default): Synthesizes multiple search results into a coherent summary
-
Disabled: Shows raw search results with minimal processing
-
Include URLs: Choose whether to include source URLs in the search results
-
Useful for citation and verification
-
Search Context Size: Control the depth of web searches
- Options: low, medium, high
- Higher values search more deeply but may take longer
Performance Settings¶
Fine-tune the performance of your models:
- Temperature
- Top-P
- Max tokens
- Response format
Routing Configuration¶
Configure the semantic routing system:
- Enable/disable dynamic routing
- Customize routing thresholds
- Add custom intents
API Key Management¶
Manage your API keys for different providers:
- OpenAI
- Anthropic
- Other providers
UI Customization¶
Customize the user interface to your preferences:
- Theme settings
- Display options
- Keyboard shortcuts
This page is under construction. More detailed configuration information will be added soon.