GET /metadata — AI Model Features and Class Labels

The /metadata endpoint exposes the internal configuration of every model registered in the service. For each of the five models it returns the ordered list of input feature names expected in a prediction request and the full set of output class labels the model can produce. Use this endpoint to drive dynamic form validation in your React or Spring Boot frontend, or to auto-generate typed request schemas without hard-coding field names in client code.

Endpoint

GET http://localhost:8001/metadata

No parameters or request body are required.

Example Request

curl -X GET http://localhost:8001/metadata

Example Response

{
  "utp-risk": {
    "features": [
      "promedio_actual",
      "asistencia_pct",
      "tareas_entregadas_pct",
      "participacion_pct",
      "horas_estudio_semana",
      "nota_pc_anterior"
    ],
    "labels": ["RIESGO_ALTO", "RIESGO_BAJO", "RIESGO_MEDIO"]
  },
  "fraud-shield": {
    "features": [
      "monto",
      "hora_24",
      "intentos_previos",
      "antiguedad_cliente_meses",
      "dispositivo_nuevo",
      "pais_riesgo",
      "compras_ultima_hora"
    ],
    "labels": ["FRAUDE_PROBABLE", "REVISION_MANUAL", "TRANSACCION_SEGURA"]
  },
  "cyber-sentinel": {
    "features": [
      "intentos_login_fallidos",
      "puertos_abiertos",
      "vulnerabilidades_criticas",
      "trafico_anomalo_pct",
      "equipos_afectados",
      "parcheado_pct"
    ],
    "labels": ["ALTO", "BAJO", "CRITICO", "MEDIO"]
  },
  "smart-stock": {
    "features": [
      "precio",
      "stock_actual",
      "ventas_7d",
      "descuento_pct",
      "temporada",
      "dias_sin_reabastecer",
      "rating_producto"
    ],
    "labels": [
      "DEMANDA_ALTA_REABASTECER",
      "DEMANDA_BAJA_OPTIMIZAR",
      "DEMANDA_MEDIA_MONITOREAR"
    ]
  },
  "talent-match": {
    "features": [
      "javascript",
      "react",
      "spring_boot",
      "python_datos",
      "sql",
      "experiencia_proyectos",
      "preferencia"
    ],
    "labels": [
      "BACKEND_SPRING",
      "DATA_ANALYST_JUNIOR",
      "FRONTEND_REACT",
      "FULLSTACK_JUNIOR"
    ]
  }
}

Response Fields

The response is a JSON object keyed by model name. Each value is an object with the following structure:

{modelKey}

object

An object describing a single loaded model. The key is one of utp-risk, fraud-shield, cyber-sentinel, smart-stock, or talent-match.

Show Model object fields

features

array of strings

required

Ordered list of input feature names. The array order matches the positional input expected by the model’s feature vector. All field names in a /predict/* request body must match these exactly.

labels

array of strings

required

Complete set of class labels the model can return as a prediccion value. Labels are sorted alphabetically as they are derived from LabelEncoder.classes_.

Compare the features array from /metadata against your request payload’s keys before calling a prediction endpoint. A mismatch in field names will cause a 422 Unprocessable Entity response from FastAPI’s Pydantic validation layer.

Spring Boot API

Python AI API

GET /metadata — AI Model Features and Class Labels

Endpoint

Example Request

Example Response

Response Fields

Build docs developers (and LLMs) love

Spring Boot API

Python AI API

Documentation Index

​Endpoint

​Example Request

​Example Response

​Response Fields

Build docs developers (and LLMs) love

Endpoint

Example Request

Example Response

Response Fields