JSON schema: extract a resume

JSON Schema to extract a resume with an LLM: experience, skills, education and certifications. Leaves out age, photo and other protected data.

Extract the resume data. Invent nothing: if information is missing, leave the field empty. Never infer age, race, religion, national origin, marital status, pregnancy or disability: these are protected characteristics under U.S. equal employment law.

JSON Schema

{
  "type": "object",
  "required": [
    "name",
    "experience",
    "skills"
  ],
  "properties": {
    "name": {
      "type": "string"
    },
    "skills": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "headline": {
      "type": "string",
      "description": "Current or target job title"
    },
    "education": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "year": {
            "type": "string"
          },
          "degree": {
            "type": "string"
          },
          "school": {
            "type": "string"
          }
        }
      }
    },
    "experience": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "title",
          "company"
        ],
        "properties": {
          "end": {
            "type": "string"
          },
          "start": {
            "type": "string"
          },
          "title": {
            "type": "string"
          },
          "company": {
            "type": "string"
          }
        }
      }
    },
    "certifications": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "years_of_experience": {
      "type": "number"
    }
  }
}

Coût estimé

Tokens d'entrée par appel : ≈ 554

Coût d'entrée seulement, sans la réponse du modèle. Prix publics des fournisseurs (Mistral AI, DeepSeek, OpenAI, Anthropic), tarif standard en dollars converti en euros au taux BCE du 29 septembre 2026. Estimation : 1 token ≈ 3,6 caractères.

Identifiant

contextetech--extract-resume

Type

Schémas de sortie

Fichier

extract-resume.schema.json

Format

JSON (application/json)

Taille

1 292 octets (1,3 Ko)

Encodage

UTF-8

Tokens estimés

≈ 359

Langue

Anglais

Licence

MIT

Usage commercial

Autorisé

Données personnelles

Aucune

Version

1.0

Publié le

2 octobre 2026 à 21:54

Mis à jour le

2 octobre 2026 à 21:54

Stockage

en base

Utilisations

0

J'aime

0

extract-resume.schema.json

{
  "type": "object",
  "required": [
    "name",
    "experience",
    "skills"
  ],
  "properties": {
    "name": {
      "type": "string"
    },
    "skills": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "headline": {
      "type": "string",
      "description": "Current or target job title"
    },
    "education": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "year": {
            "type": "string"
          },
          "degree": {
            "type": "string"
          },
          "school": {
            "type": "string"
          }
        }
      }
    },
    "experience": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "title",
          "company"
        ],
        "properties": {
          "end": {
            "type": "string"
          },
          "start": {
            "type": "string"
          },
          "title": {
            "type": "string"
          },
          "company": {
            "type": "string"
          }
        }
      }
    },
    "certifications": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "years_of_experience": {
      "type": "number"
    }
  }
}

API Anthropic (Python)

import json, anthropic

schema = json.load(open("extract-resume.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": "votre entrée ici"}])
print(resp.content[0].input)

Format OpenAI (response_format)

{
  "type": "json_schema",
  "json_schema": {
    "name": "extract-resume",
    "schema": {
      "type": "object",
      "required": [
        "name",
        "experience",
        "skills"
      ],
      "properties": {
        "name": {
          "type": "string"
        },
        "skills": {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        "headline": {
          "type": "string",
          "description": "Current or target job title"
        },
        "education": {
          "type": "array",
          "items": {
            "type": "object",
            "properties": {
              "year": {
                "type": "string"
              },
              "degree": {
                "type": "string"
              },
              "school": {
                "type": "string"
              }
            }
          }
        },
        "experience": {
          "type": "array",
          "items": {
            "type": "object",
            "required": [
              "title",
              "company"
            ],
            "properties": {
              "end": {
                "type": "string"
              },
              "start": {
                "type": "string"
              },
              "title": {
                "type": "string"
              },
              "company": {
                "type": "string"
              }
            }
          }
        },
        "certifications": {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        "years_of_experience": {
          "type": "number"
        }
      }
    },
    "strict": true
  }
}