Thomas Gak-Deluen tgdn

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:

PostgreSQL is Enough

Background and Cron Jobs

macOS Internals

Understand your Mac and iPhone more deeply by tracing the evolution of Mac OS X from prelease to Swift. John Siracusa delivers the details.

Starting Points

How to use this gist

You've got two main options:

Top HN posts

Moved to skeeto/scratch/aidrivers

	-- vim: tabstop=2 shiftwidth=2 expandtab

	-- We almost always start by importing the wezterm module
	local wezterm = require 'wezterm'
	-- Define a lua table to hold _our_ module's functions
	local module = {}

	-- Returns a bool based on whether the host operating system's
	-- appearance is light or dark.
	function module.is_dark()

	'use client';

	import Script from 'next/script';
	import { useEffect, useRef, useState } from 'react';

	const scriptLink = 'https://challenges.cloudflare.com/turnstile/v0/api.js?render=explicit';

	type TurnstileRenderParameters = Turnstile.RenderParameters;

	export default function Captcha(

	NOTE: The MUI X License Key more than likely isn't going to work. It will have expired. The lifetime license key should... well... last forever...

	MUI X License Key (from https://mui.com):
	61628ce74db2c1b62783a6d438593bc5Tz1NVUktRG9jLEU9MTY4MzQ0NzgyMTI4NCxTPXByZW1pdW0sTE09c3Vic2NyaXB0aW9uLEtWPTI=
	Order Number: MUI-Doc
	Expiry Timestamp: 1683447821284(Sun May 7th 08:32:41)
	Scope: Premium
	Licensing Model: Subscription
	Key Version: 2

	import { useEffect, useState } from 'react';
	import { useRouter } from 'next/router';

	/** Ask for confirmation before changing page or leaving site.
	*
	* @see https://git.io/JOskG
	*/
	const useNavigationLock = (
	isEnabled = true,
	warningText = 'You have unsaved changes – are you sure you wish to leave this page?',

	import React, { useEffect, useRef } from 'react'
	import { useWindowSize } from '@react-hook/window-size'
	import StackGrid from 'react-stack-grid'

	export const Grid = ({ children }) => {
	const ANIMATION_DURATION = 400
	const [windowWidth] = useWindowSize()
	const grid = useRef(null)
	const resizeGrid = () => {
	if (grid.current) {