- Notas relacionadas
- Primeros pasos
- Notificaciones
- Proyectos
- Conjuntos de datos
- Etiquetado de datos
- Paquetes ML
- Paquetes listos para usar
- Procesos
- Habilidades ML
- Logs de ML
- Document UnderstandingTM en AI Center
- API de AI Center
- Licencia
- Plantillas de soluciones de AI
- Tutorial
- Guía básica de resolución de problemas
Similitud semántica
Paquetes listos para usar > Análisis de idioma de UiPath > Similitud semántica
El modelo Similitud semántica está actualmente en vista previa pública.
UiPath® is committed to stability and quality of our products, but preview features are always subject to change based on feedback that we receive from our customers. Using preview features is not recommended for production deployments.
Este modelo te permite comparar una única frase de referencia con un grupo de otras frases candidatas y las clasifica por orden de similitud.
JSON con una cadena denominada "referencia" y una lista de cadenas denominada "candidatos". Esto significa que no se aceptan varias "frases" de referencia. "Candidatos" es una lista de frases candidatas.
{"reference": "I like trains because they are fast", "candidates": ["I like trains because they are quick", "I like trains because they are comfortable", "I do not like buses because they are slow", "I do not like trains because they are uncomfortable"]}
{"reference": "I like trains because they are fast", "candidates": ["I like trains because they are quick", "I like trains because they are comfortable", "I do not like buses because they are slow", "I do not like trains because they are uncomfortable"]}
JSON con los candidatos de referencia y los más similares, y la puntuación asociada a esa similitud (entre 0 y 1) ordenada de forma descendente por puntuación.
Ejemplo:
{
"response": [
{
"candidate": "I like trains because they are quick",
"score": 0.96463942527771
},
{
"candidate": "I like trains because they are comfortable",
"score": 0.81790685653686523
},
{
"candidate": "I do not like trains because they are uncomfortable",
"score": 0.53707438707351685
},
{
"candidate": "I do not like buses because they are slow",
"score": 0.48663735389709473
}
]
}
{
"response": [
{
"candidate": "I like trains because they are quick",
"score": 0.96463942527771
},
{
"candidate": "I like trains because they are comfortable",
"score": 0.81790685653686523
},
{
"candidate": "I do not like trains because they are uncomfortable",
"score": 0.53707438707351685
},
{
"candidate": "I do not like buses because they are slow",
"score": 0.48663735389709473
}
]
}
Se recomienda una GPU cuando el número de frases candidatas por referencia supera las 100.