Skip to main content
Available for Pro plan and above
Path: Space → Settings → AI Settings

​
1. AI Capability Settings

  • Description:
    • Space administrators can independently control whether each AI feature is available within the space.
    • Features in the list include:
      • AI Basic Capabilitiy: AI Basic Capability, include AI table query tool, execute SQL query tool, generate script tool, table data visualization tool, update database information tool
      • Create Base: Create Base from scratch
      • Create App: Create App based on Base
      • Create Automation: Create Automation from scratch
      • Base Resource Operation: Create, modify, and delete tables, views, fields, and records through ai
      • Suggestions: Give suggestions based on the current database data and conversation content

​
2. Custom Model

  • Used to activate or deactivate all custom AI API configurations within the current space. When enabled, space AI configurations will take priority.
  • Description:
    • Off: Use official default AI models.
    • On: Use custom configured AI models. Please configure the large coding model before enabling.

​
3. LLM Providers

  • Manage the integration of third-party AI model providers.

​
4. Model Preferences

  • Specify default conversation models for different types of task scenarios. By matching the most suitable models for different tasks, achieve fine-grained management of cost and performance.
    • Advanced Conversation Model:
      • Scenario: For planning, coding, and other complex task scenarios, it is recommended to use claude-sonnet-4.
      • Recommended model: claude-sonnet-4
      • Purpose: When AI functions requiring high intelligence and strong logical reasoning are triggered within the application, the model selected here will be called.
    • Medium Conversation Model:
      • Scenario: For scenarios that require speed and quality, such as creating Base, it is recommended to use GPT-4o.
      • Recommended model: GPT-4o
      • Purpose: Used for most daily core AI tasks, balancing cost and performance.
    • Small Conversation Model:
      • Scenario: Used for tasks such as scene recommendation and simple quick operations.
      • Purpose: Used for simple tasks requiring fast response and low latency, such as auto-completion, quick classification, etc., with the lowest cost.

​
5. Advanced Conversation Model Capabilities

  • Test the multimodal processing capabilities of the selected “Advanced Conversation Model”.
  • Description:
    • You can use the “Test Model” button to verify whether the selected advanced model supports processing images and PDF content.

​
6. Embedding Model

  • Specify the model used for generating suggestions (based on current database data and conversation content to provide suggestions).

​
7. App Generation

  • Description: Configure the v0 API Key to enable APP Generation capabilities. Access v0 setting to obtain your API Key
  • Description: Configure Firecrawl API key to enable web search feature, access Firecrawl settings to get API key
For self-hosted , access the admin panel for AI Setting