SOC2

Extract IRS Form 1040 Extractor Data — Tax Season Ready

Tax preparation requires processing hundreds of documents per client. Manual data entry increases errors and delays filings.

115
Fields Extracted
300s
Max Processing

What This Template Does

AI-powered extraction using gemini-2.5-flash. Part of 113 production-ready templates.

Capabilities

  • Tax Extraction
  • 1040 Processing
  • Income Tax Analysis
  • 1040
  • Irs

Output Schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "title": "IRS Form 1040 Extraction Schema",
  "description": "JSON Schema for extracted IRS Form 1040 (U.S. Individual Income Tax Return) data",
  "type": "object",
  "required": [
    "document_type",
    "tax_year",
    "taxpayer",
    "filing_status",
    "income"
  ],
  "properties": {
    "document_type": {
      "type": "string",
      "const": "1040",
      "description": "Document type identifier"
    },
    "tax_year": {
      
...

Quick Start

$ pip install doclayer
$ doclayer process document.pdf --agent tax.1040

See It In Action

Real extraction example showing input document and structured output.

Input Document
Form 1040 U.S. Individual Income Tax Return 2024
Department of the Treasury - Internal Revenue Service

Your first name and middle initial: MARGARET A
Last name: THOMPSON
Your social security number: 000-00-1234

If joint return, spouse's first name and middle initial: N/A
Spouse's last name: N/A
Spouse's social security number: N/A

Home address (number and street): 742 EVERGREEN TERRACE
Apartment no.: APT 3B
City, town, or post office: SPRINGFIELD
State: IL
ZIP code: 62701

Foreign country nam
Extracted Data
{
  "document_type": "1040",
  "tax_year": "2024",
  "form_variant": "1040",
  "taxpayer": {
    "first_name": "MARGARET",
    "middle_initial": "A",
    "last_name": "THOMPSON",
    "ssn": "XXX-XX-1234",
    "occupation": "SOFTWARE ENGINEER",
    "phone": "(555) 123-4567",
    "email": ""
  },
  "spouse": {
    "first_name": "",
    "middle_initial": "",
    "last_name": "",
    "ssn": "",
    "occupation": ""
  },
  "address": {
    "street": "742 EVERGREEN TERRACE",
    "apt": "APT 3B",
    "city": "SPRINGFIELD",
    "state": "IL",
    "zip": "62701",
    "foreign_country": "",
    "foreign_province": "",
    "foreign_postal": ""
  },
  "filing_status": {
    "status": "single",
    "spouse_name_mfs": ""
  },
  "dependents": [],
  "income": {
    "line_1a_wages": "78500.00",
    "line_1z_total_wages": "78500.00",
    "line_2a_tax_exempt_interest": "250.00",
    "line_2b_taxable_interest": "1875.50",
    "line_3a_qualified_dividends": "2100.00",
    "line_3b_ordinary_dividends": "2450.00",
    "line_4a_ira_distributions": "0.00",
    "line_4b_taxable_ira": "0.00",
    "line_5a_pensions_annuities": "0.00",
    "line_5b_taxable_pensions": "0.00",
    "line_6a_social_security": "0.00",
    "line_6b_taxable_ss": "0.00",
    "line_7_capital_gain_loss": "3200.00",
    "line_8_schedule_1_income": "0.00",
    "line_9_total_income": "86025.50"
  },
  "adjustments": {
    "line_10_schedule_1_adjustments": "0.00",
    "line_11_adjusted_gross_income": "86025.50"
  },
  "deductions": {
    "line_12_standard_or_itemized": "14600.00",
    "deduction_type": "standard",
    "line_13_qualified_business_income": "0.00",
    "line_14_total_deductions": "14600.00",
    "line_15_taxable_income": "71425.50"
  },
  "tax_and_credits": {
    "line_16_tax": "10892.00",
    "line_17_schedule_2_taxes": "0.00",
    "line_18_total_tax": "10892.00",
    "line_19_child_tax_credit": "0.00",
    "line_20_schedule_3_credits": "0.00",
    "line_21_total_credits": "0.00",
    "line_22_tax_minus_credits": "10892.00",
    "line_23_other_taxes": "0.00",
    "line_24_total_tax": "10892.00"
  },
  "payments": {
    "line_25a_w2_withholding": "12500.00",
    "line_25b_1099_withholding": "375.00",
    "line_25c_other_withholding": "0.00",
    "line_25d_total_withholding": "12875.00",
    "line_26_estimated_payments": "0.00",
    "line_27_earned_income_credit": "0.00",
    "line_28_additional_child_credit": "0.00",
    "line_29_american_opportunity_credit": "0.00",
    "line_31_schedule_3_payments": "0.00",
    "line_32_total_other_payments": "0.00",
    "line_33_total_payments": "12875.00"
  },
  "refund_or_owed": {
    "line_34_overpaid": "1983.00",
    "line_35a_refund": "1983.00",
    "line_35b_routing": "071000013",
    "line_35c_account_type": "checking",
    "line_35d_account_number": "XXXXXX7890",
    "line_36_applied_next_year": "0.00",
    "line_37_amount_owed": "0.00",
    "line_38_estimated_penalty": "0.00"
  },
  "third_party": {
    "designee_name": "",
    "designee_phone": "",
    "designee_pin": ""
  },
  "signature": {
    "taxpayer_signed": true,
    "spouse_signed": false,
    "date": "2025-04-10",
    "occupation_taxpayer": "SOFTWARE ENGINEER",
    "occupation_spouse": ""
  },
  "preparer": {
    "name": "",
    "firm_name": "",
    "ptin": "",
    "firm_ein": "",
    "firm_address": "",
    "firm_phone": "",
    "self_employed": false
  },
  "schedules_attached": [],
  "validation": {
    "ssn_format_valid": true,
    "math_correct": true,
    "filing_status_selected": true,
    "signature_present": true
  }
}

Example demonstrating extraction of individual income tax return data from IRS Form 1040. Captures filing status, income sources (wages, interest, dividends), deductions, and refund/liability calculations.

Frequently Asked Questions

What documents can IRS Form 1040 Extractor process?

The IRS Form 1040 Extractor template processes tax documents including various formats and layouts. See the instructions for specific document types supported.

How accurate is the IRS Form 1040 Extractor extraction?

The IRS Form 1040 Extractor template uses Gemini 2.5 Flash for high-accuracy extraction. Results include confidence scores for each field.

Can I customize the IRS Form 1040 Extractor template?

Yes, you can modify the extraction schema, add custom fields, or adjust the instructions to match your specific requirements.

Start Extracting Data Today

Process your first document in under 5 minutes. No credit card required.