$caila.inference
Classifies the text with additional parameters.
Syntax
The method accepts the text for parsing in the string
argument and some additional parameters.
- ECMAScript 5
- ECMAScript 6
$caila.inference({"phrase":{"text":"greetings"}, "nBest": 5, knownSlots: [{"name":"a", "value":"b"}]});
In the ECMAScript 6 runtime, the method is asynchronous:
await $caila.inference({"phrase":{"text":"greetings"}, "nBest": 5, knownSlots: [{"name":"a", "value":"b"}]});
Here:
phrase
are the phrases for classification.nBest
is the number of hypotheses to be returned.knownSlots
are the known slots:name
— name of the slot;value
— value of the slot.
A JSON object with the phrase classification result is returned in response.
Let us define the hello
intent with the following training phrases: hello, hi. The classification result for the hello
phrase is:
{
"phrase":{
"text":"hello",
"entities":[
]
},
"variants":[
{
"intent":{
"id":12174, // intent id
"path":"/hello", // the path to the intent
"slots":[ // slots
]
},
"confidence":1, // confidence level
"slots":[
]
}
]
}
tip
You can also use the custom
clientId
identifier as a method argument. Specify the clientId
identifier as the last argument. When $caila.inference
is executed, entities will be recognized for the specified client.How to use
- ECMAScript 5
- ECMAScript 6
state: Example
q!: inference
script:
$reactions.answer(JSON.stringify($caila.inference({"phrase":{"text":"hello"}, "nBest": 5, knownSlots: [{"name":"a", "value":"b"}]})));
state: Example
q!: inference
scriptEs6:
$reactions.answer(JSON.stringify(await $caila.inference({"phrase":{"text":"hello"}, "nBest": 5, knownSlots: [{"name":"a", "value":"b"}]})));