Esquema JSON: extraer un currículum

JSON Schema para extraer un currículum con un LLM: experiencia, competencias, idiomas y formación. Sin edad, foto ni otros datos sensibles.

Extrae los datos del currículum. No inventes nada: si falta un dato, deja el campo vacío. No deduzcas edad, estado civil, origen, religión ni salud.

JSON Schema

{
  "type": "object",
  "required": [
    "nombre",
    "experiencia",
    "competencias"
  ],
  "properties": {
    "nombre": {
      "type": "string"
    },
    "idiomas": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "nivel": {
            "type": "string"
          },
          "idioma": {
            "type": "string"
          }
        }
      }
    },
    "titular": {
      "type": "string",
      "description": "Puesto actual o buscado"
    },
    "formacion": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "ano": {
            "type": "string"
          },
          "centro": {
            "type": "string"
          },
          "titulo": {
            "type": "string"
          }
        }
      }
    },
    "experiencia": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "puesto",
          "empresa"
        ],
        "properties": {
          "fin": {
            "type": "string"
          },
          "inicio": {
            "type": "string"
          },
          "puesto": {
            "type": "string"
          },
          "empresa": {
            "type": "string"
          }
        }
      }
    },
    "competencias": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "anos_experiencia": {
      "type": "number"
    }
  }
}

Estimated cost

Input tokens per call : ≈ 578

Input cost only, excluding the model's answer. Providers' public standard prices (Mistral AI, DeepSeek, OpenAI, Anthropic) converted from USD to euros at the ECB rate of September 29, 2026. Estimate: 1 token ≈ 3.6 characters.

Identifier

contextetech--extraer-curriculum

Type

Output schemas

File

extraer-curriculum.schema.json

Format

JSON (application/json)

Size

1,458 bytes (1.4 KB)

Encoding

UTF-8

Estimated tokens

≈ 405

Language

Spanish

License

MIT

Commercial use

Allowed

Personal data

None

Version

1.0

Published on

October 3, 2026 at 5:20 AM

Updated on

October 3, 2026 at 5:20 AM

Storage

in database

Uses

0

Likes

0

extraer-curriculum.schema.json

{
  "type": "object",
  "required": [
    "nombre",
    "experiencia",
    "competencias"
  ],
  "properties": {
    "nombre": {
      "type": "string"
    },
    "idiomas": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "nivel": {
            "type": "string"
          },
          "idioma": {
            "type": "string"
          }
        }
      }
    },
    "titular": {
      "type": "string",
      "description": "Puesto actual o buscado"
    },
    "formacion": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "ano": {
            "type": "string"
          },
          "centro": {
            "type": "string"
          },
          "titulo": {
            "type": "string"
          }
        }
      }
    },
    "experiencia": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "puesto",
          "empresa"
        ],
        "properties": {
          "fin": {
            "type": "string"
          },
          "inicio": {
            "type": "string"
          },
          "puesto": {
            "type": "string"
          },
          "empresa": {
            "type": "string"
          }
        }
      }
    },
    "competencias": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "anos_experiencia": {
      "type": "number"
    }
  }
}

Anthropic API (Python)

import json, anthropic

schema = json.load(open("extraer-curriculum.schema.json"))
client = anthropic.Anthropic()
resp = client.messages.create(model="claude-sonnet-5", max_tokens=1024,
    tools=[{"name": "extraire", "description": "Renvoie les données extraites", "input_schema": schema}],
    tool_choice={"type": "tool", "name": "extraire"},
    messages=[{"role": "user", "content": "your input here"}])
print(resp.content[0].input)

OpenAI format (response_format)

{
  "type": "json_schema",
  "json_schema": {
    "name": "extraer-curriculum",
    "schema": {
      "type": "object",
      "required": [
        "nombre",
        "experiencia",
        "competencias"
      ],
      "properties": {
        "nombre": {
          "type": "string"
        },
        "idiomas": {
          "type": "array",
          "items": {
            "type": "object",
            "properties": {
              "nivel": {
                "type": "string"
              },
              "idioma": {
                "type": "string"
              }
            }
          }
        },
        "titular": {
          "type": "string",
          "description": "Puesto actual o buscado"
        },
        "formacion": {
          "type": "array",
          "items": {
            "type": "object",
            "properties": {
              "ano": {
                "type": "string"
              },
              "centro": {
                "type": "string"
              },
              "titulo": {
                "type": "string"
              }
            }
          }
        },
        "experiencia": {
          "type": "array",
          "items": {
            "type": "object",
            "required": [
              "puesto",
              "empresa"
            ],
            "properties": {
              "fin": {
                "type": "string"
              },
              "inicio": {
                "type": "string"
              },
              "puesto": {
                "type": "string"
              },
              "empresa": {
                "type": "string"
              }
            }
          }
        },
        "competencias": {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        "anos_experiencia": {
          "type": "number"
        }
      }
    },
    "strict": true
  }
}