Skip to main content

How to enable AI

Model​

  1. Add developer. The platform will add a batch of preset developers and models (OpenAI, Qwen, DeepSeek) by default, and the administrator can use them after completing the provider configuration (preset developers cannot be added repeatedly).

  2. Add model: add specific model under the developer

    • Name: the unique identifier of the model in the platform, which is used for model matching internally and cannot be duplicate. It must be modified carefully to avoid failure of function calls that have used this model
    • Display name: the display name on the use side
    • Price: under the platform version, set the charging price
    • Capability: the capability of the model will be used as the basis for the system AI function to automatically match the model
    • Performance: the comprehensive performance of the model will be used as the basis for the automatic matching of the system AI functions to the model. Comprehensive evaluation can be given from the dimensions of effect, speed, stability, cost, etc
    • Provider and Model ID: actually called supplier and model ID values. Multiple suppliers can be added to the model (currently only one of them can be set to enabled status)

  3. Support hiding developers and models on the use side. After hiding is set, the developer or model cannot be selected on the user side (i.e. the model selection layer of workflow AIGC related nodes), but the function configuration of Platform Mgt is still optional.

Provider​

Manage the provider's request interface address and call voucher (API key) for model call.

  1. Currently, it supports adding official providers of OpenAI, Qwen, DeepSeek, Azure, and also supports adding custom providers (Note that custom providers need to meet the OpenAI interface definition specification, see OpenAI Official Document)

  2. The Base URL of the official provider is not required and has a default address. If there is a network problem and a proxy address has been configured, you can set the Base URL

  3. It supports enabling agents. When enabled, the request will be forwarded using the proxy information configured by use Settings - Security - API Proxy managed by the platform

  4. In addition, it also supports setting custom request headers and enabling SSL certificate verification

Feature Config​

  1. Model Config: set the model of system AI function call. Click [Auto-set Model] to match the model with one key according to the model parameters and the matching rules of each system AI function. Manual editing and adjustment of the model are also supported. When the selected model does not meet the minimum functional requirements, the corresponding identification will also be displayed below the model input box. When the model is not set or the selected model is unavailable, the system will call the first model in the available list to ensure the availability of the function. System AI functions include:

    • Create Worksheet
    • Create Record
    • Generate Code (Worksheet Custom Fields)
    • Generate Code (Workflow Code Block Node)
    • Generate Prompt (Workflow AI Agent Node)
    • Generate Sample Data
    • App Multilingual Support
    • Auto-select Model (that is, automatically select models in the workflow AI Agent node)
    • Generate App/Worksheet Desc
    • Other Accessibility Features (refer to other functions that use AI services in addition to the above functions, such as generating dialog titles, pre recommendation of AI creation worksheets (table names, icons, etc.), and generating corresponding configurations of dialog robots based on descriptions, etc.)

  2. Others: support the configuration of Speech-to-Text Service (used in Mingo), Web Search (used in AI creation record)

AI capacity master switch​

After closing, use the side to hide all AI related function entries. The AIGC nodes and dialog robots that have been added in the application will also fail when calling the model.

Platform Pricing Settings​

If it is currently a platform version, you can set the unit price of third-party services for tenants in Platform Mgt - Operations - Billing Rules.

  1. Basic functions: SMS service, email service, text recognition (OCR), PDF generation
  2. Unit price of AI model, calculated per thousand tokens a. This unit price is the unit price of the AI model, not the provider called for the AI model, b. Note that the AI model currently only charges for the call of Workflow - AIGC related nodes, and the system AI function does not deduct the use of organization credit points temporarily

Historical configuration compatibility​

  1. If you have previously configured a model in AI Service - Basic AI Function, the model in the original configuration will still be used by default for the three functions of worksheet custom fields, workflow code block automatic generation, and application of multilingual intelligent translation (as shown below)

  2. If you have configured the model for the workflow AIGC node in the configuration file, the switch to use the configuration file will be turned on by default in the function configuration (as shown in the following figure). After closing, you can use the model configured in the new AI capability module. To ensure the normal operation of the AIGC node that has been added to the workflow, please keep the name of the new configuration model (that is, the model ID inside the platform) consistent with the value of the model parameter in the original configuration file (case sensitive).