Robert Hibbeler kventil

Extracting financial disclosure reports and police blotter narratives using OpenAI's Structured Output

tl;dr this demo shows how to call OpenAI's gpt-4o-mini model, provide it with URL of a screenshot of a document, and extract data that follows a schema you define. The results are pretty solid even with little effort in defining the data — and no effort doing data prep. OpenAI's API could be a cost-efficient tool for large scale data gathering projects involving public documents.

OpenAI announced Structured Outputs for its API, a feature that allows users to specify the fields and schema of extracted data, and guarantees that the JSON output will follow that specification.

For example, given a Congressional financial disclosure report, with assets defined in a table like this:

	Fragen an alle:

	1. Was habt ihr gestern gemacht? -> Was habt ihr umgesetzt?
	2. Wann ist euer nächstes großes Release?
	3. Dokumentation?
	4. Was ist das größte Problem an dem ihr gerade arbeitet?
	5. Bisher Coolstes/Arbeitsintensivstes Feature?
	6. Wie steht ihr zu Büro-Hunden? / Hat jemand eine Hundeallergie?
	7. Wie sahen eure Firmenevents bisher aus?
	8. Gröster Durchbruch bisher?

	Result: 1
	Items {
	TemplateId: "BADGE_BATTLE_ATTACK_WON"
	Badge {
	BadgeType: BADGE_BATTLE_ATTACK_WON
	BadgeRanks: 4
	Targets: "\nd\350\007"
	}
	}
	Items {