Resume parsing

This example turns a resume into candidate data you can filter on: name, contact details, years of experience, and three tables of rows for skills, education and work history. Each table is an object field, which is how a repeating list is modelled on the typed graph.

The resume

→

What comes back

candidate_name98%

years_of_experience95%

skills

work_history

NodesParse → ExtractCredits60 per pageYou get

The workflow

{
  "name": "Resume parsing",
  "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": "years_of_experience", "description": "Total years of professional work experience", "data_type": "integer" },
          {
            "name": "skills",
            "description": "Technical skills, programming languages and tools, one row per skill",
            "data_type": "object",
            "nested_fields": [
              { "name": "skill", "description": "One skill, language or tool", "data_type": "string" }
            ]
          },
          {
            "name": "education",
            "description": "Educational qualifications and degrees, one row per degree",
            "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, one row per job",
            "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 this is the current role", "data_type": "date" }
            ]
          }
        ]
      }
    }
  ],
  "edges": [{ "source": "parse_1", "target": "extract_1" }]
}

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 parsing", "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.integer("years_of_experience", "Total years of professional work experience"),
        Schema.object("skills", "Technical skills, programming languages and tools, one row per skill", fields=[
            Schema.string("skill", "One skill, language or tool"),
        ]),
        Schema.object("education", "Educational qualifications and degrees, one row per degree", 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, one row per job", 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 this is the current role"),
        ]),
    ])
    .create()
)

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

const af = new Anyformat({ apiKey: process.env.ANYFORMAT_API_KEY! });

const workflow = await af
  .workflow("Resume parsing", "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.integer("years_of_experience", "Total years of professional work experience"),
    Schema.object("skills", "Technical skills, programming languages and tools, one row per skill", [
      Schema.string("skill", "One skill, language or tool"),
    ]),
    Schema.object("education", "Educational qualifications and degrees, one row per degree", [
      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, one row per job", [
      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 this is the current role"),
    ]),
  ])
  .create();

Run it and read the result

The files field accepts PDF, DOCX and images. Poll the run until its status is processed.

# 1. Create the workflow with the JSON above
curl -X POST 'https://api.anyformat.ai/v3/workflows/' \
  -H "Authorization: Bearer $ANYFORMAT_API_KEY" \
  -H 'Content-Type: application/json' \
  -d @resume-workflow.json
# → 201 { "id": "<workflow_id>", ... }

# 2. Upload the resume and start a run
curl -X POST "https://api.anyformat.ai/v3/workflows/$WORKFLOW_ID/upload/run/" \
  -H "Authorization: Bearer $ANYFORMAT_API_KEY" \
  -F 'files=@resume.docx'
# → 202 { "run_id": "<run_id>", "document_packet_id": "...", "status": "queued" }

# 3. Poll until "status" is "processed"
curl "https://api.anyformat.ai/v3/runs/$RUN_ID/" \
  -H "Authorization: Bearer $ANYFORMAT_API_KEY"

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

print(result.fields["candidate_name"].value)
print(result.fields["years_of_experience"].value)

skills = [row["skill"].value for row in result.fields["skills"]]
for job in result.fields["work_history"]:
    print(job["company"].value, job["title"].value, job["start_date"].value, job["end_date"].value)

import { readFileSync } from "node:fs";
import type { ExtractedField, ExtractedRows } from "@anyformat/sdk";

const file = new File([readFileSync("resume.docx")], "resume.docx");
const result = await (await workflow.run(file)).wait();

console.log((result.field("candidate_name") as ExtractedField<string> | undefined)?.value);
console.log((result.field("years_of_experience") as ExtractedField<string> | undefined)?.value);

const skills = (result.field("skills") as ExtractedRows).map((row) => row.skill?.value);
for (const job of result.field("work_history") as ExtractedRows) {
  console.log(job.company?.value, job.title?.value, job.start_date?.value, job.end_date?.value);
}

Response

The results envelope of a processed run, trimmed. A current role comes back with end_date.value: null.

Response

{
  "results": {
    "extractions": [{ "fields": {
      "candidate_name":      { "value": "Maria Gonzalez", "confidence": 98.0, "evidence": [{ "text": "MARIA GONZALEZ", "page_number": 1 }] },
      "years_of_experience": { "value": "9", "confidence": 95.0, "evidence": [{ "text": "9 years of professional experience", "page_number": 1 }] },
      "skills": [{ "skill": { "value": "Python", "confidence": 98.0 } }, { "skill": { "value": "Go", "confidence": 98.0 } }],
      "work_history": [
        { "company": { "value": "Fintonic", "confidence": 97.0 }, "title": { "value": "Staff Backend Engineer", "confidence": 97.0 }, "start_date": { "value": "2021-03-01", "confidence": 90.0 }, "end_date": { "value": null, "confidence": 90.0 } }
      ]
    } }]
  }
}

Every cell also carries verification_status and value_override. Runs and results has the full envelope, section by section.

When it goes wrong

A current job comes back with a made-up end date. The model fills a date field it was asked for. Describe end_date as “empty if this is the current role”, the way this schema does, and the current job returns end_date.value: null instead. Your skills list arrives as one long string. There is no list data type. A free-form list is an object field with one nested field, as skills does here, and each item comes back as its own row with its own confidence. Field types has the shapes. You cannot filter on years of experience. Every value is a string on the wire, so "9" sorts next to "10" the wrong way. Declare years_of_experience as integer and cast it once on the way in, rather than parsing text at query time. A scanned resume loses half the work history. A DOCX or born-digital PDF has native text, so nothing is lost to OCR. A scan does not. Where you control the intake, ask for DOCX. Where you do not, move the Parse node to the agentic tier (100 credits per page) for the scanned batch. Dates come back on the first of the month. Resumes write “March 2021”, which names no day. A date field normalises that to 2021-03-01. Compare on month, not on day, when you rank candidates by tenure.

Examples

Read the page

Messy piles

Money and compliance

At scale

The workflow

Run it and read the result

Response

When it goes wrong

Next steps

Upload and run

Field types

​The workflow

​Run it and read the result

​Response

​When it goes wrong

​Next steps

Upload and run

Field types

The workflow

Run it and read the result

Response

When it goes wrong

Next steps