Skill Extraction API

Get each role's description, with the skills used, tied to the job where they were used. PDF to structured JSON with one API call.

How it works

1. 1

   Send a resume PDF

   Send a PDF (up to 5 MB) to POST /v1/parse as multipart/form-data with a single field named file. The PDF needs a text layer; scanned image-only PDFs are not supported.

2. 2

   LLM-powered content analysis

   The text is extracted from the PDF and processed by a large language model that understands section boundaries, job titles and descriptions. Unlike regex-based parsers, the model interprets meaning rather than matching patterns.

3. 3

   Skills in each role

   Each workExperiences entry has a skillsDescription field with the description written under that job. This keeps which skills were used at which job, so you know whether a candidate used Python in their current role or five years ago.

4. 4

   Structured JSON response

   The response returns each work experience with its title, organization, dates and skillsDescription. You can pull skill keywords from this field or use it directly for matching and search indexing.

Key Benefits

Code examples

import requests

response = requests.post(
    'https://api.resumeparser.cc/v1/parse',
    headers={'Authorization': 'Bearer rp_live_...'},
    files={'file': open('resume.pdf', 'rb')},
    timeout=60,
)

data = response.json()['data']
# Each work experience has a skillsDescription field
# with the description written under that role (markdown)
for exp in data.get('workExperiences', []):
    print(f"{exp['title']} at {exp['organization']}")
    print(f"  Description: {exp['skillsDescription']}")
    print(f"  Started: {exp['startMonth']}/{exp['startYear']}")

Related pages