Schéma JSON : extraire un CV

JSON Schema pour extraire un CV avec un LLM : expériences, compétences, langues et formation, prêt pour les sorties structurées.

Extrais les informations du CV. N'invente rien : si une information manque, laisse le champ vide. Ne déduis ni l'âge, ni la situation familiale, ni l'origine.

JSON Schema

{
  "type": "object",
  "required": [
    "nom",
    "experiences",
    "competences"
  ],
  "properties": {
    "nom": {
      "type": "string"
    },
    "titre": {
      "type": "string",
      "description": "Intitulé du poste recherché ou actuel"
    },
    "langues": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "langue": {
            "type": "string"
          },
          "niveau": {
            "type": "string"
          }
        }
      }
    },
    "formation": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "annee": {
            "type": "string"
          },
          "diplome": {
            "type": "string"
          },
          "etablissement": {
            "type": "string"
          }
        }
      }
    },
    "competences": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "experiences": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "poste",
          "entreprise"
        ],
        "properties": {
          "fin": {
            "type": "string"
          },
          "debut": {
            "type": "string"
          },
          "poste": {
            "type": "string"
          },
          "entreprise": {
            "type": "string"
          }
        }
      }
    },
    "annees_experience": {
      "type": "number"
    }
  }
}

Geschätzte Kosten

Eingabe-Tokens pro Aufruf : ≈ 578

Nur Eingabekosten, ohne die Antwort des Modells. Öffentliche Standardpreise der Anbieter (Mistral AI, DeepSeek, OpenAI, Anthropic) von USD in Euro umgerechnet zum EZB-Kurs vom 29. September 2026. Schätzung: 1 Token ≈ 3,6 Zeichen.

Kennung

contextetech--extraire-un-cv

Typ

Ausgabeschemas

Datei

extraire-un-cv.schema.json

Format

JSON (application/json)

Größe

1.479 Bytes (1,4 KB)

Kodierung

UTF-8

Geschätzte Tokens

≈ 410

Sprache

Französisch

Lizenz

MIT

Kommerzielle Nutzung

Erlaubt

Personenbezogene Daten

Keine

Version

1.0

Veröffentlicht am

1. Oktober 2026 um 18:55

Aktualisiert am

1. Oktober 2026 um 18:55

Speicherung

in der Datenbank

Nutzungen

0

Gefällt mir

0

extraire-un-cv.schema.json

{
  "type": "object",
  "required": [
    "nom",
    "experiences",
    "competences"
  ],
  "properties": {
    "nom": {
      "type": "string"
    },
    "titre": {
      "type": "string",
      "description": "Intitulé du poste recherché ou actuel"
    },
    "langues": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "langue": {
            "type": "string"
          },
          "niveau": {
            "type": "string"
          }
        }
      }
    },
    "formation": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "annee": {
            "type": "string"
          },
          "diplome": {
            "type": "string"
          },
          "etablissement": {
            "type": "string"
          }
        }
      }
    },
    "competences": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "experiences": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "poste",
          "entreprise"
        ],
        "properties": {
          "fin": {
            "type": "string"
          },
          "debut": {
            "type": "string"
          },
          "poste": {
            "type": "string"
          },
          "entreprise": {
            "type": "string"
          }
        }
      }
    },
    "annees_experience": {
      "type": "number"
    }
  }
}

Anthropic-API (Python)

import json, anthropic

schema = json.load(open("extraire-un-cv.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": "deine Eingabe hier"}])
print(resp.content[0].input)

OpenAI-Format (response_format)

{
  "type": "json_schema",
  "json_schema": {
    "name": "extraire-un-cv",
    "schema": {
      "type": "object",
      "required": [
        "nom",
        "experiences",
        "competences"
      ],
      "properties": {
        "nom": {
          "type": "string"
        },
        "titre": {
          "type": "string",
          "description": "Intitulé du poste recherché ou actuel"
        },
        "langues": {
          "type": "array",
          "items": {
            "type": "object",
            "properties": {
              "langue": {
                "type": "string"
              },
              "niveau": {
                "type": "string"
              }
            }
          }
        },
        "formation": {
          "type": "array",
          "items": {
            "type": "object",
            "properties": {
              "annee": {
                "type": "string"
              },
              "diplome": {
                "type": "string"
              },
              "etablissement": {
                "type": "string"
              }
            }
          }
        },
        "competences": {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        "experiences": {
          "type": "array",
          "items": {
            "type": "object",
            "required": [
              "poste",
              "entreprise"
            ],
            "properties": {
              "fin": {
                "type": "string"
              },
              "debut": {
                "type": "string"
              },
              "poste": {
                "type": "string"
              },
              "entreprise": {
                "type": "string"
              }
            }
          }
        },
        "annees_experience": {
          "type": "number"
        }
      }
    },
    "strict": true
  }
}