Resume Parsing

Workflow fields

We recommend creating this workflow in the anyformat platform where you can test with sample resumes and iterate on field descriptions. Copy the workflow ID to use with the API.

Field	Type	Description
`candidate_name`	string	Full name of the candidate
`email`	string	Email address
`phone`	string	Phone number
`skills`	list	Technical and professional skills
`years_of_experience`	integer	Total years of professional experience
`education`	object	Educational background (institution / degree / graduation_date)
`work_history`	object	Previous employment (company / title / start_date / end_date)

End-to-end

curl
TypeScript
Python

# 1. Create the workflow
curl -X POST 'https://api.anyformat.ai/v2/workflows/' \
  -H 'Content-Type: application/json' \
  -H "Authorization: Bearer $ANYFORMAT_API_KEY" \
  -d '{
    "name": "Resume Parser",
    "description": "Extract candidate details from resumes",
    "nodes": [
      {"id": "parse_1", "type": "parse"},
      {
        "id": "extract_1",
        "type": "extract",
        "extraction_schema": {
          "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 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 CS, 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",    "data_type": "date"}
              ]
            }
          ]
        }
      }
    ],
    "edges": [{"source": "parse_1", "target": "extract_1"}]
  }'

# 2. Run a resume
curl -X POST 'https://api.anyformat.ai/v2/workflows/WORKFLOW_ID/run/' \
  -H "Authorization: Bearer $ANYFORMAT_API_KEY" \
  -F 'file=@resume.docx'

# 3. Poll for results (412 → keep polling; 200 → done)
curl -H "Authorization: Bearer $ANYFORMAT_API_KEY" \
  'https://api.anyformat.ai/v2/workflows/WORKFLOW_ID/files/COLLECTION_ID/results/'

import { Anyformat, Schema } from "@anyformat/sdk";

const af = new Anyformat({ apiKey: process.env.ANYFORMAT_API_KEY! });
const file: File = /* a File with .name set, e.g. new File([bytes], "resume.docx") */;

const workflow = await af
  .workflow("Resume Parser", "Extract candidate details from resumes")
  .parse()
  .extract([
    Schema.string("candidate_name",      "Full name of the candidate"),
    Schema.string("email",               "Email address"),
    Schema.string("phone",               "Phone number including country code if present"),
    Schema.string("skills",              "List of technical skills, programming languages, tools, and competencies"),
    Schema.integer("years_of_experience","Total years of professional work experience"),
    Schema.object("education", "Educational qualifications and degrees", [
      Schema.string("institution",     "University or school name"),
      Schema.string("degree",          "Degree obtained (e.g. BSc CS, MBA)"),
      Schema.date("graduation_date",   "Date of graduation"),
    ]),
    Schema.object("work_history", "Previous jobs and roles, most recent first", [
      Schema.string("company",    "Company name"),
      Schema.string("title",      "Job title"),
      Schema.date("start_date",   "Start date of employment"),
      Schema.date("end_date",     "End date of employment, or empty if current"),
    ]),
  ])
  .create();

const run = await workflow.run(file);
const result = await run.wait();

console.log(result.field("candidate_name")?.value);
console.log(result.field("email")?.value);
console.log(result.field("years_of_experience")?.value);
// Nested rows: result.extractions[0].fields.work_history

import os
from anyformat.sdk import Client
from anyformat.workflow import Schema

client = Client(api_key=os.environ["ANYFORMAT_API_KEY"])

workflow = (
    client.workflow("Resume Parser")
    .parse()
    .extract([
        Schema.string("candidate_name",      "Full name of the candidate"),
        Schema.string("email",               "Email address"),
        Schema.string("phone",               "Phone number including country code if present"),
        Schema.string("skills",              "List of technical skills, programming languages, tools, and competencies"),
        Schema.integer("years_of_experience","Total years of professional work experience"),
        Schema.object("education", "Educational qualifications and degrees", fields=[
            Schema.string("institution",     "University or school name"),
            Schema.string("degree",          "Degree obtained (e.g. BSc CS, MBA)"),
            Schema.date("graduation_date",   "Date of graduation"),
        ]),
        Schema.object("work_history", "Previous jobs and roles, most recent first", fields=[
            Schema.string("company",    "Company name"),
            Schema.string("title",      "Job title"),
            Schema.date("start_date",   "Start date of employment"),
            Schema.date("end_date",     "End date of employment, or empty if current"),
        ]),
    ])
    .create()
)

result = workflow.run("resume.docx").wait()

print(result.fields["candidate_name"].value)
print(result.fields["email"].value)
print(result.fields["years_of_experience"].value)
# Nested rows: result.raw["extractions"][0]["fields"]["work_history"]

Tips

DOCX resumes typically yield better results than scanned PDFs since the text is natively accessible.

Describe end_date as “empty if current role” so processing returns null for current positions.
years_of_experience as integer lets you filter directly without parsing.

Workflow fields

End-to-end

Tips

Next steps

Run workflow

Field types

​Workflow fields

​End-to-end

​Tips

​Next steps

Run workflow

Field types

Workflow fields

End-to-end

Tips

Next steps