Extractions

Extractions (Granular Data)

Extractions involve the process of converting the unstructured data from the uploaded documents into a granular, usable format. This step is crucial for isolating specific pieces of data, such as individual fields, text segments, or tabular data, from the comprehensive content of the PDFs. This granular data serves as the building blocks for the final structured datasets.

Once an Upload has been created, we organize the data into "Extractions" these extractions are categories of data-sets that represent common objects for the underlying data. This is represented in JSON below. These become the building blocks for Exports, which usually combine multiple different extractions.

{
  "property_name": "Magnolia 4-Plex",
  "address": "1126 Magnolia Ave\nLos Angeles, CA 90006",
  "property_type": "Multi-family",
  "number_of_buildings": null,
  "building_size_sq_ft": 7300,
  "site_area": "7,000 SqFt",
  "year_built": 2021,
  "renovation_year": null,
  "zoning": "R3",
  "number_of_units_or_spaces": 4,
  "unit_type": "Townhome",
  "parking_spaces": 8,
  "hvac_systems": null,
  "elevators": null,
  "security_systems": null,
  "utilities": null,
  "amenities": null,
  "environmental_reports": null,
  "sustainability_features": null,
  "flood_zone": null,
  "seismic_risk": null,
  "asking_price_usd": 2795000,
  "cap_rate_percentage": 0.053,
  "noi_actual_usd": null,
  "gross_revenue_actual_usd": null,
  "operating_expenses_actual_usd": null,
  "property_taxes_actual_usd": null,
  "insurance_costs_actual_usd": null,
  "management_fees_actual_usd": null,
  "rent_per_unit_actual_usd": null,
  "rent_per_sqft_actual_usd": null,
  "noi_proforma_usd": 150700,
  "gross_revenue_proforma_usd": 189600,
  "operating_expenses_proforma_usd": 38840,
  "property_taxes_proforma_usd": 33540,
  "insurance_costs_proforma_usd": 2500,
  "management_fees_proforma_usd": null,
  "rent_per_unit_proforma_usd": null,
  "rent_per_sqft_proforma_usd": 2.45,
  "schema_version": "1.0.0"
}