Jonathan Sundqvist jonathan-s

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:

Anti-hype LLM reading list

Goals: Add links that are reasonable and good explanations of how stuff works. No hype and no vendor content if possible. Practical first-hand accounts of models in prod eagerly sought.

Foundational Concepts

Pre-Transformer Models

Brompton bags

ES6 HTMLElement Extensions

This is a small library for extending HTMLElement methods.

`Element.descendant()`

Returns the first descendant of the element which matches the given selector. This is identical to Element.querySelector().

Syntax

<HTMLElement> HTMLElement.descendant(<String> selector)

`Element.ancestor()`

Main docs

Videos

GraphQL Full Course - Novice to Expert (Walks through a full stack example using Authors and Books)

React lifecycle cheatsheet

Method	Side effects¹	State updates²	Example uses
Mounting
`componentWillMount`		✓	Constructor equivalent for `createClass`
`render`			Create and return element(s)
`componentDidMount`	✓	✓	DOM manipulations, network requests, etc.
Updating
`componentWillReceiveProps`		✓	Update `state` based on changed `props`

This document has moved!

It's now here, in The Programmer's Compendium. The content is the same as before, but being part of the compendium means that it's actively maintained.

	// I'm tired of extensions that automatically:
	// - show welcome pages / walkthroughs
	// - show release notes
	// - send telemetry
	// - recommend things
	//
	// This disables all of that stuff.
	// If you have more config, leave a comment so I can add it!!

	{

	#!/usr/bin/env bash
	#
	# Usage: dev_signed_cert.sh HOSTNAME
	#
	# Creates a CA cert and then generates an SSL certificate signed by that CA for the
	# given hostname.
	#
	# After running this, add the generated dev_cert_ca.cert.pem to the trusted root
	# authorities in your browser / client system.
	#

	from django.contrib.admin import ModelAdmin

	class MyTableAdmin(ModelAdmin):
	...
	paginator = LargeTablePaginator
	...