When working with transforms in Zenera, you can import functions to process input data and shape it into the desired output. Zenera offers two ways to import functions:

• Using the import statement: you can pull in functions defined in the dialog script. Imported functions can be used to process data or apply specific logic as part of the query transformation.
• Using EJS (Embedded JavaScript): you can embed a function output directly in the transform instruction using EJS.

Import statement

Assume you want to import a function that returns a list of all cloud services from the database. To do this, you need to:

1. Define the getServices() function with the JSDOC description in the dialog script:

   async function getData() {
       // Make the GET request to fetch virtual infrastructure data from the database
       // ...
   }
   
   /**
   * @tool: Returns an array containing cloud services
   * @param:
   * @return: An array with a short description of objects with the following fields:
   * [
   *     {
   *         "errorRate": "Percentage representing the error rate",
   *         "id": "Unique identifier for the cloud service",
   *         "lastCheck": "ISO formatted date and time of the last status check",
   *         "name": "Name of the cloud service",
   *         "responseTime": "Average response time in milliseconds",
   *         "status": "Current status of the cloud service (e.g., operational, degraded)",
   *         "uptime": "Percentage representing the service uptime"
   *     },
   *     ...
   * ]
   */
   async function getServices() {
       const data = await getData();
       console.log(data.cloudServices);
       return data.cloudServices;
   }

2. Import the getServices() function in the general instruction of the query transform.
3. Provide a description in natural language how to use this function to get the desired output.
4. Add a dynamic corpus to use the created query transform:

   corpus({
       title: `Infrastructure requests`,
       query: transforms.query,
       priority: 1
   });

EJS

Zenera supports embedding function outputs directly into the transform instruction using EJS. To do this, use the <%- %> tag, which inserts content directly into the output without escaping.

Assume you want the AI-Native Interface to answer questions about common cloud abbreviations. You can:

1. Add a function to return a list of abbreviations and their definitions:

   function getCloudAbbreviations() {
       return `
           API, or Application Programming Interface, is a set of protocols and tools...
           CDN, or Content Delivery Network, is a distributed network of servers...
           DNS, or Domain Name System, is a service that translates human-readable domain names...
       `
   }

2. Import the getCloudAbbreviations() function in the general instruction of the query transform using the EJS syntax:

   <%- getCloudAbbreviations() %>

3. Provide a description in natural language how to use this function to get the desired output.
4. Add a dynamic corpus to use the created query transform:

   corpus({
       title: `Abbreviation requests`,
       query: transforms.query,
       priority: 1
   });