{
  "fields": [
    {"name": "candidate_name", "description": "Full name of the candidate", "data_type": "string"},
    {"name": "email", "description": "Email address", "data_type": "string"},
    {"name": "phone", "description": "Phone number including country code if present", "data_type": "string"},
    {"name": "skills", "description": "List of technical skills, programming languages, tools, and professional competencies", "data_type": "list"},
    {"name": "years_of_experience", "description": "Total years of professional work experience", "data_type": "integer"},
    {
      "name": "education",
      "description": "Educational qualifications and degrees",
      "data_type": "object",
      "nested_fields": [
        {"name": "institution", "description": "University or school name", "data_type": "string"},
        {"name": "degree", "description": "Degree obtained (e.g., BSc Computer Science, MBA)", "data_type": "string"},
        {"name": "graduation_date", "description": "Date of graduation", "data_type": "date"}
      ]
    },
    {
      "name": "work_history",
      "description": "Previous jobs and roles, most recent first",
      "data_type": "object",
      "nested_fields": [
        {"name": "company", "description": "Company name", "data_type": "string"},
        {"name": "title", "description": "Job title", "data_type": "string"},
        {"name": "start_date", "description": "Start date of employment", "data_type": "date"},
        {"name": "end_date", "description": "End date of employment, or empty if current role", "data_type": "date"}
      ]
    }
  ]
}

# Poll for results
max_attempts = 60
base_delay = 5

for attempt in range(max_attempts):
    response = requests.get(
        f"https://api.anyformat.ai/v2/files/{file_id}/extraction/",
        headers={"Authorization": f"Bearer {API_KEY}"}
    )

    if response.status_code == 200:
        results = response.json()
        break
    elif response.status_code == 412:
        delay = min(base_delay * (1.5 ** min(attempt, 5)), 30)
        time.sleep(delay)
    else:
        raise Exception(f"Error: {response.json()['detail']}")
else:
    raise TimeoutError("Processing timed out")

# Use extracted data
print(f"Candidate: {results['candidate_name']['value']}")
print(f"Email: {results['email']['value']}")
print(f"Skills: {', '.join(results['skills']['value'])}")
print(f"Experience: {results['years_of_experience']['value']} years")

for job in results["work_history"]:
    print(f"  - {job['title']['value']} at {job['company']['value']}")

{
  "candidate_name": {"value": "Sarah Chen", "confidence": 98},
  "email": {"value": "sarah.chen@email.com", "confidence": 97},
  "phone": {"value": "+1-555-0142", "confidence": 93},
  "skills": {"value": ["Python", "TypeScript", "AWS", "PostgreSQL", "Docker", "React", "FastAPI"], "confidence": 88},
  "years_of_experience": {"value": 7, "confidence": 85},
  "education": [
    {
      "institution": {"value": "MIT", "confidence": 96},
      "degree": {"value": "BSc Computer Science", "confidence": 94},
      "graduation_date": {"value": "2017-06-15", "confidence": 90}
    }
  ],
  "work_history": [
    {
      "company": {"value": "Stripe", "confidence": 97},
      "title": {"value": "Senior Software Engineer", "confidence": 95},
      "start_date": {"value": "2021-03-01", "confidence": 88},
      "end_date": {"value": null, "confidence": 82}
    },
    {
      "company": {"value": "Datadog", "confidence": 96},
      "title": {"value": "Software Engineer", "confidence": 94},
      "start_date": {"value": "2018-01-15", "confidence": 87},
      "end_date": {"value": "2021-02-28", "confidence": 85}
    }
  ]
}