When working with static corpuses, you can apply the following types of transforms:

• Query transforms to fine-tune the AI-Native Interface reasoning and refine its decision-making logic
• Output transforms to modify and format responses provided by the AI-Native Interface

Query transforms

Query transforms used with static corpuses allow you to refine the AI-Native Interface's decision-making and direct it to the appropriate data corpus. To adjust the AI reasoning process, you can:

• Instruct the AI-Native Interface which corpus to use for particular types of queries
• Instruct the AI-Native Interface to omit specific data corpuses

Example of use

Assume you have two corpuses that provide information about HTTP requests:

• HTTP basics
• HTTP status codes

corpus({
    title: `HTTP basics`,
    urls: [`https://www.tutorialspoint.com/http/http_responses.htm`],
    depth: 1,
    maxPages: 10,
    priority: 1,
});

corpus({
    title: `HTTP status codes`,
    urls: [`https://developer.mozilla.org/en-US/docs/Web/HTTP/Status`],
    depth: 1,
    maxPages: 1,
    priority: 2,
});

The AI-Native Interface should retrieve information from corpuses in the following way:

• If the user asks question about status codes, the AI-Native Interface should use the HTTP status codes corpus.
• For all other questions, the AI-Native Interface should refer to the HTTP basics corpus.

Output transforms

Assume you want the AI-Native Interface to format responses in a specific way. For this, you can do the following:

1. To the dialog script, add the corpus() function, specify the data source and name of the transform that will be used to format the answer. In this example, we will use a transform named output.

   corpus({
       urls: [        
           `https://developer.mozilla.org/en-US/docs/Web/HTTP/Status`,                
       ],
       transforms: transforms.output,
       maxPages: 3,
       depth: 1
   });

2. In the AI-Native Interface project, under Transforms, create the output transform with the appropriate instructions and examples.
3. Use the Debugging Chat to test your transforms and refine them using the Transforms Explorer.