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"
    }
  }
}

Estimated cost

Input tokens per call : ≈ 554

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--extract-resume

Type

Output schemas

File

extract-resume.schema.json

Format

JSON (application/json)

Size

1,292 bytes (1.3 KB)

Encoding

UTF-8

Estimated tokens

≈ 359

Language

English

License

MIT

Commercial use

Allowed

Personal data

None

Version

1.0

Published on

October 2, 2026 at 9:54 PM

Updated on

October 2, 2026 at 9:54 PM

Storage

in database

Uses

0

Likes

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"
    }
  }
}

Anthropic API (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": "your input here"}])
print(resp.content[0].input)

OpenAI format (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
  }
}