A document-to-map pipeline built for government archives.
Apaluma reads scanned permit files, code violations, and inspection records. It extracts structured fields, matches records to parcels, and delivers a GIS layer your planning staff can query directly.
Request Early AccessWhat the platform does with your documents
Four capabilities that work together to turn a legacy archive into a queryable data layer.
Reads permit numbers, parcel IDs, issue dates, work types, and final inspection status from scanned forms. Handles handwritten annotations, duplex shadows, and mixed page orientations typical of county archives.
Extracted values are normalized to consistent schemas. Addresses resolve to a standard format. Dates are parsed from handwritten shorthand. APN formats are matched to your county's parcel database conventions.
Each extracted record is resolved to an Assessor Parcel Number and linked to the geometry in your county's parcel layer. Where the APN is ambiguous, the match engine flags the record for staff review rather than silently guessing.
Matched records export as GeoJSON, Shapefile, KML, or CSV with WKT geometry. Compatible with ArcGIS, QGIS, and web map platforms without additional conversion steps.
The document pipeline, step by step
From upload to GIS-ready output, the pipeline runs end-to-end without manual intervention between steps.
Drop scanned PDFs or a zipped archive. Apaluma accepts batches of any size and queues them for processing.
Layout-aware OCR and field extraction identify document type, parse key fields, and normalize values to a consistent schema.
Each record resolves to an APN. Ambiguous matches are flagged for review rather than silently approximated.
Matched records export in your chosen GIS format. The resulting layer loads directly into ArcGIS, QGIS, or your web map platform.
Export to the format your GIS environment needs
Each output format delivers the same matched records. Choose based on your platform and downstream workflow.
Open standard format compatible with web maps, QGIS, and most modern GIS platforms. Geometry and attributes in a single file.
Industry-standard format for ArcGIS and legacy GIS workflows. Delivered as a correctly assembled zip with all required component files.
Keyhole Markup Language for Google Earth, Google Maps, and other visualization tools that consume spatial data via KML endpoints.
Flat tabular export with a well-known text geometry column. Useful for database import, custom reporting, and analysts who work primarily in spreadsheet tools.
Esri GDB format for organizations running ArcGIS workflows that require native geodatabase delivery with domain and subtype support.
Programmatic access to matched records and parcel queries. Available on the County Pro plan for integration with permitting software and custom dashboards.
Ready to see it work on your documents?
We scope each pilot around a specific document type and parcel set. Tell us about your archive and we will confirm what Apaluma can extract.
Start a Pilot Evaluation