Extract equipment data from submittals and product data sheets

Pull model numbers, capacities, electrical data, dimensions and certifications from equipment submittals, ready to compare line by line against the specified values.

Every item comes back with the page and quote it was taken from, checked against the document, so you can verify any value in seconds. Scanned PDFs work too: the Terminal reads scanned pages with AI vision, and the API can too.

Example request

Run it on many files at once in the Terminal, or save the schema as an extractor and send each file with its extractor_id.

curl -X POST https://api.jsonit.io/v1/extract-file \
  -H "Authorization: Bearer sk_live_your_key" \
  -F "file=@ahu-1-submittal.pdf" \
  -F "accuracy=high" \
  -F "evidence=true" \
  -F 'schema={"type":"object","properties":{"manufacturer":{"type":"string"},"equipment":{"type":"array","items":{"type":"object","properties":{"tag":{"type":["string","null"],"description":"e.g. AHU-1"},"model":{"type":"string"},"capacity":{"type":["number","null"]},"capacity_unit":{"type":["string","null"],"description":"e.g. CFM, tons, MBH"},"voltage":{"type":["number","null"]},"phase":{"type":["integer","null"]},"mca":{"type":["number","null"],"description":"minimum circuit ampacity"},"mocp":{"type":["number","null"],"description":"maximum overcurrent protection"},"weight_lb":{"type":["number","null"]},"certifications":{"type":"array","items":{"type":"string"}}}}}}}'