Respuestas y resultados

Lee las respuestas, las puntuaciones de confianza, el uso de tokens y los modelos disponibles que devuelve la API de TypeSafe.

Respuesta

typesafe_sdk.SystemOneResponse

pydantic-model

Bases: Response

Respuestas agrupadas por tipo de pregunta con metadatos del modelo y del uso.

Consulta System One para obtener más detalles.

Mostrar esquema JSON:

Detalles

{
  "$defs": {
    "ChoiceAnswer": {
      "description": "A selected label and its probabilities.\n\nSee the [choice primitive](../../../../primitives/choice) for details.",
      "properties": {
        "type": {
          "const": "choice",
          "default": "choice",
          "title": "Type",
          "type": "string"
        },
        "choice": {
          "description": "The name of the choice with the highest probability among the question's criteria.",
          "examples": [
            "angry"
          ],
          "title": "Choice",
          "type": "string"
        },
        "confidence": {
          "description": "Confidence in the selected choice, from 0 to 1. Higher values indicate greater certainty; use lower values to flag uncertain selections for review.",
          "examples": [
            0.9
          ],
          "title": "Confidence",
          "type": "number"
        },
        "probabilities": {
          "additionalProperties": {
            "type": "number"
          },
          "description": "Probability of each choice in criteria, keyed by choice name, from 0 to 1. Shows how likely the alternatives are; values sum to approximately 1.",
          "examples": [
            {
              "angry": 0.8,
              "calm": 0.1,
              "excited": 0.1
            }
          ],
          "title": "Probabilities",
          "type": "object"
        }
      },
      "required": [
        "choice",
        "confidence",
        "probabilities"
      ],
      "title": "ChoiceAnswer",
      "type": "object"
    },
    "NoulAnswer": {
      "description": "A yes/no answer.\n\nSee the [noul primitive](../../../../primitives/noul) for details.",
      "properties": {
        "type": {
          "const": "noul",
          "default": "noul",
          "title": "Type",
          "type": "string"
        },
        "noul": {
          "description": "Probability of a yes answer or a true statement, from 0 to 1. Values near 1 favor yes or true, values near 0 favor no or false, and values near 0.5 indicate uncertainty.",
          "examples": [
            0.98
          ],
          "title": "Noul",
          "type": "number"
        }
      },
      "required": [
        "noul"
      ],
      "title": "NoulAnswer",
      "type": "object"
    },
    "ScoreAnswer": {
      "description": "An expected score with its rubric and probabilities.\n\nSee the [score primitive](../../../../primitives/score) for details.",
      "properties": {
        "type": {
          "const": "score",
          "default": "score",
          "title": "Type",
          "type": "string"
        },
        "score": {
          "description": "Expected score: the probability-weighted average of the rubric levels. May fall between integer levels.",
          "examples": [
            1.7
          ],
          "title": "Score",
          "type": "number"
        },
        "confidence": {
          "description": "Confidence in the score, from 0 to 1. Higher values indicate greater certainty; use lower values to flag uncertain ratings for review.",
          "examples": [
            0.9
          ],
          "title": "Confidence",
          "type": "number"
        },
        "legend": {
          "additionalProperties": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "additionalProperties": true,
                "type": "object"
              },
              {
                "items": {},
                "type": "array"
              }
            ]
          },
          "title": "Legend",
          "type": "object"
        },
        "probabilities": {
          "additionalProperties": {
            "type": "number"
          },
          "title": "Probabilities",
          "type": "object"
        }
      },
      "required": [
        "score",
        "confidence",
        "legend",
        "probabilities"
      ],
      "title": "ScoreAnswer",
      "type": "object"
    },
    "Usage": {
      "description": "Token counts for a request, when reported by the API.",
      "properties": {
        "input_tokens": {
          "anyOf": [
            {
              "type": "integer"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "title": "Input Tokens"
        },
        "output_tokens": {
          "anyOf": [
            {
              "type": "integer"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "title": "Output Tokens"
        }
      },
      "title": "Usage",
      "type": "object"
    }
  },
  "description": "Answers grouped by question type with model and usage metadata.\n\nSee [System One](../../../../concepts/system-one) for details.",
  "properties": {
    "model": {
      "title": "Model",
      "type": "string"
    },
    "usage": {
      "$ref": "#/$defs/Usage"
    },
    "answers": {
      "additionalProperties": {
        "discriminator": {
          "mapping": {
            "choice": "#/$defs/ChoiceAnswer",
            "noul": "#/$defs/NoulAnswer",
            "score": "#/$defs/ScoreAnswer"
          },
          "propertyName": "type"
        },
        "oneOf": [
          {
            "$ref": "#/$defs/NoulAnswer"
          },
          {
            "$ref": "#/$defs/ChoiceAnswer"
          },
          {
            "$ref": "#/$defs/ScoreAnswer"
          }
        ]
      },
      "title": "Answers",
      "type": "object"
    }
  },
  "required": [
    "model",
    "usage"
  ],
  "title": "SystemOneResponse",
  "type": "object"
}

Configuración:

extra: ignore
frozen: True
strict: True

Campos:

model (str)
usage (Usage)
answers (dict[str, Answer])

request_id

cached property

request_id: str

La cabecera de respuesta x-typesafe-request-id.

raw_http_response

property

raw_http_response: httpx2.Response

El httpx2.Response subyacente, que expone el estado, las cabeceras y el cuerpo.

model_config

class-attribute instance-attribute

model_config = ConfigDict(
    extra="ignore", frozen=True, strict=True
)

model

pydantic-field

model: str

El modelo usado para responder a la solicitud.

usage

pydantic-field

usage: Usage

Uso de tokens de la solicitud.

answers

pydantic-field

answers: dict[str, Answer]

Todos los objetos de respuesta indexados por el nombre de la pregunta.

nouls

cached property

nouls: dict[str, NoulAnswer]

Respuestas de sí/no indexadas por el nombre de la pregunta.

choices

cached property

choices: dict[str, ChoiceAnswer]

Respuestas de choice indexadas por el nombre de la pregunta.

scores

cached property

scores: dict[str, ScoreAnswer]

Respuestas de score indexadas por el nombre de la pregunta.

typesafe_sdk.Usage

pydantic-model

Bases: wire.Usage

Recuentos de tokens de una solicitud, cuando la API los informa.

Mostrar esquema JSON:

Detalles

{
  "description": "Token counts for a request, when reported by the API.",
  "properties": {
    "input_tokens": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Input Tokens"
    },
    "output_tokens": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Output Tokens"
    }
  },
  "title": "Usage",
  "type": "object"
}

Configuración:

extra: ignore
frozen: True
strict: True

Campos:

input_tokens (int | None)
output_tokens (int | None)

model_config

class-attribute instance-attribute

model_config = ConfigDict(
    extra="ignore", frozen=True, strict=True
)

input_tokens

pydantic-field

input_tokens: int | None = None

Número de tokens de entrada usados, o None cuando la API no lo informó.

output_tokens

pydantic-field

output_tokens: int | None = None

Número de tokens de salida usados, o None cuando la API no lo informó.

Respuestas

typesafe_sdk.NoulAnswer

pydantic-model

Bases: wire.NoulAnswer

Una respuesta de sí/no.

Consulta la primitiva noul para obtener más detalles.

Mostrar esquema JSON:

Detalles

{
  "description": "A yes/no answer.\n\nSee the [noul primitive](../../../../primitives/noul) for details.",
  "properties": {
    "type": {
      "const": "noul",
      "default": "noul",
      "title": "Type",
      "type": "string"
    },
    "noul": {
      "description": "Probability of a yes answer or a true statement, from 0 to 1. Values near 1 favor yes or true, values near 0 favor no or false, and values near 0.5 indicate uncertainty.",
      "examples": [
        0.98
      ],
      "title": "Noul",
      "type": "number"
    }
  },
  "required": [
    "noul"
  ],
  "title": "NoulAnswer",
  "type": "object"
}

Configuración:

extra: ignore
frozen: True
strict: True

Campos:

noul (float)
type (Literal[‘noul’])

noul

pydantic-field

noul: float

Probabilidad de una respuesta afirmativa o de una afirmación verdadera, de 0 a 1. Los valores cercanos a 1 favorecen el sí o lo verdadero, los cercanos a 0 favorecen el no o lo falso, y los cercanos a 0.5 indican incertidumbre.

model_config

class-attribute instance-attribute

model_config = ConfigDict(
    extra="ignore", frozen=True, strict=True
)

typesafe_sdk.ChoiceAnswer

pydantic-model

Bases: wire.ChoiceAnswer

Una etiqueta seleccionada y sus probabilidades.

Consulta la primitiva choice para obtener más detalles.

Mostrar esquema JSON:

Detalles

{
  "description": "A selected label and its probabilities.\n\nSee the [choice primitive](../../../../primitives/choice) for details.",
  "properties": {
    "type": {
      "const": "choice",
      "default": "choice",
      "title": "Type",
      "type": "string"
    },
    "choice": {
      "description": "The name of the choice with the highest probability among the question's criteria.",
      "examples": [
        "angry"
      ],
      "title": "Choice",
      "type": "string"
    },
    "confidence": {
      "description": "Confidence in the selected choice, from 0 to 1. Higher values indicate greater certainty; use lower values to flag uncertain selections for review.",
      "examples": [
        0.9
      ],
      "title": "Confidence",
      "type": "number"
    },
    "probabilities": {
      "additionalProperties": {
        "type": "number"
      },
      "description": "Probability of each choice in criteria, keyed by choice name, from 0 to 1. Shows how likely the alternatives are; values sum to approximately 1.",
      "examples": [
        {
          "angry": 0.8,
          "calm": 0.1,
          "excited": 0.1
        }
      ],
      "title": "Probabilities",
      "type": "object"
    }
  },
  "required": [
    "choice",
    "confidence",
    "probabilities"
  ],
  "title": "ChoiceAnswer",
  "type": "object"
}

Configuración:

extra: ignore
frozen: True
strict: True

Campos:

choice (str)
confidence (float)
probabilities (dict[str, float])
type (Literal[‘choice’])

choice

pydantic-field

choice: str

El nombre del choice con la mayor probabilidad entre los criteria de la pregunta.

confidence

pydantic-field

confidence: float

Confianza en el choice seleccionado, de 0 a 1. Los valores más altos indican mayor certeza; usa los valores más bajos para marcar selecciones inciertas y revisarlas.

probabilities

pydantic-field

probabilities: dict[str, float]

Probabilidad de cada choice de criteria, indexada por el nombre del choice, de 0 a 1. Muestra qué probabilidad tienen las alternativas; los valores suman aproximadamente 1.

model_config

class-attribute instance-attribute

model_config = ConfigDict(
    extra="ignore", frozen=True, strict=True
)

typesafe_sdk.ScoreAnswer

pydantic-model

Bases: wire.ScoreAnswer

Una puntuación esperada con su rúbrica y sus probabilidades.

Consulta la primitiva score para obtener más detalles.

Mostrar esquema JSON:

Detalles

{
  "description": "An expected score with its rubric and probabilities.\n\nSee the [score primitive](../../../../primitives/score) for details.",
  "properties": {
    "type": {
      "const": "score",
      "default": "score",
      "title": "Type",
      "type": "string"
    },
    "score": {
      "description": "Expected score: the probability-weighted average of the rubric levels. May fall between integer levels.",
      "examples": [
        1.7
      ],
      "title": "Score",
      "type": "number"
    },
    "confidence": {
      "description": "Confidence in the score, from 0 to 1. Higher values indicate greater certainty; use lower values to flag uncertain ratings for review.",
      "examples": [
        0.9
      ],
      "title": "Confidence",
      "type": "number"
    },
    "legend": {
      "additionalProperties": {
        "anyOf": [
          {
            "type": "string"
          },
          {
            "additionalProperties": true,
            "type": "object"
          },
          {
            "items": {},
            "type": "array"
          }
        ]
      },
      "title": "Legend",
      "type": "object"
    },
    "probabilities": {
      "additionalProperties": {
        "type": "number"
      },
      "title": "Probabilities",
      "type": "object"
    }
  },
  "required": [
    "score",
    "confidence",
    "legend",
    "probabilities"
  ],
  "title": "ScoreAnswer",
  "type": "object"
}

Configuración:

extra: ignore
frozen: True
strict: True

Campos:

score (float)
confidence (float)
type (Literal[‘score’])
legend (dict[int, str | dict[str, Any] | list[Any]])
probabilities (dict[int, float])

score

pydantic-field

score: float

Puntuación esperada: la media ponderada por probabilidad de los niveles de la rúbrica. Puede quedar entre niveles enteros.

confidence

pydantic-field

confidence: float

Confianza en la puntuación, de 0 a 1. Los valores más altos indican mayor certeza; usa los valores más bajos para marcar valoraciones inciertas y revisarlas.

model_config

class-attribute instance-attribute

model_config = ConfigDict(
    extra="ignore", frozen=True, strict=True
)

legend

pydantic-field

legend: dict[
    int, str | dict[str, Any] | list[Any]
]

Descripciones de la rúbrica indexadas por la puntuación entera.

probabilities

pydantic-field

probabilities: dict[int, float]

Probabilidades indexadas por la puntuación entera.

typesafe_sdk.Answer

module-attribute

Answer: TypeAlias = Annotated[
    NoulAnswer | ChoiceAnswer | ScoreAnswer,
    Field(discriminator="type"),
]

Una respuesta a una sola pregunta, identificada por su type.

Modelos disponibles

typesafe_sdk.ListModelsResponse

pydantic-model

Bases: Response

Los modelos disponibles para la cuenta.

Mostrar esquema JSON:

Detalles

{
  "$defs": {
    "ModelMetadata": {
      "description": "Metadata describing a single available model.",
      "properties": {
        "name": {
          "title": "Name",
          "type": "string"
        },
        "description": {
          "title": "Description",
          "type": "string"
        },
        "release_date": {
          "title": "Release Date",
          "type": "string"
        }
      },
      "required": [
        "name",
        "description",
        "release_date"
      ],
      "title": "ModelMetadata",
      "type": "object"
    }
  },
  "description": "The models available to the account.",
  "properties": {
    "models": {
      "items": {
        "$ref": "#/$defs/ModelMetadata"
      },
      "title": "Models",
      "type": "array"
    }
  },
  "required": [
    "models"
  ],
  "title": "ListModelsResponse",
  "type": "object"
}

Campos:

models (tuple[ModelMetadata, …])

request_id

cached property

request_id: str

La cabecera de respuesta x-typesafe-request-id.

raw_http_response

property

raw_http_response: httpx2.Response

El httpx2.Response subyacente, que expone el estado, las cabeceras y el cuerpo.

model_config

class-attribute instance-attribute

model_config = ConfigDict(
    extra="ignore", frozen=True, strict=True
)

models

pydantic-field

models: tuple[ModelMetadata, ...]

Los modelos disponibles.

typesafe_sdk.ModelMetadata

pydantic-model

Bases: Schema

Metadatos que describen un único modelo disponible.

Mostrar esquema JSON:

Detalles

{
  "description": "Metadata describing a single available model.",
  "properties": {
    "name": {
      "title": "Name",
      "type": "string"
    },
    "description": {
      "title": "Description",
      "type": "string"
    },
    "release_date": {
      "title": "Release Date",
      "type": "string"
    }
  },
  "required": [
    "name",
    "description",
    "release_date"
  ],
  "title": "ModelMetadata",
  "type": "object"
}

Campos:

name (str)
description (str)
release_date (str)

name

pydantic-field

name: str

Nombre o alias del modelo aceptado por el campo model de una solicitud.

description

pydantic-field

description: str

Descripción legible del modelo y de sus capacidades.

release_date

pydantic-field

release_date: str

Fecha de lanzamiento del modelo, con el formato AAAA-MM-DD.