Stephan Burlot sburlot

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:

OS X Screencast to animated GIF

This gist shows how to create a GIF screencast using only free OS X tools: QuickTime, ffmpeg, and gifsicle.

Instructions

To capture the video (filesize: 19MB), using the free "QuickTime Player" application:

	# !/usr/bin/env python3
	# Nicolas Seriot
	# 2022-06-14
	# https://seriot.ch/visualization/truchet_2.png
	# loosely inspired by https://www.fxhash.xyz/gentk/slug/dirty-interlaced-truchet-tiles-18

	import cairo
	import math
	import random

	# !/usr/bin/env python3
	# Nicolas Seriot
	# 2022-06-10
	# https://seriot.ch/visualization/truchet_simple.png

	import cairo
	import math
	import random

	NB_COLS = 8

	<?php
	// https://en.wikipedia.org/wiki/Category:Coffee_brands
	$covfefes = [
	'alterracoffeeroasters',
	'angiangcoffee',
	'angelinus',
	'autocrat',
	'barcaffe',
	'batdorfbronson',
	'bewleys',

	@size = (1920, 1080);
	@center = (-.743653135, .131826563);
	$zoom = .000014628;
	$max_it = 700;
	$oversample = 2;

	$_ *= $oversample for (@size);
	open $fh, "\|-", "convert -size ".join("x",@size)." -depth 8 gray:- ".
	"-resize ".(100/$oversample)."% mandel.png";
	for $py (1 .. $size[1]) {

	#!/bin/bash

	# Creates a ramdisk and start Xcode with the DerivedData stored in ramdisk. Also deletes the ramdisk and reset Xcode prefs.
	# xc_ramdisk.sh
	# - creates a ramdisk, set Xcode DerivedData to this disk and start Xcode.
	# - umount a ramdisk, set Xcode DerivedData to default
	# Stephan Burlot, Coriolis Technologies, http://www.coriolis.ch
	#
	# based on Alex Shevchenko xcode_ramdisk.sh script (https://gist.github.com/skeeet/2367298)
	# based on Diego Freniche xc-launch.sh script (https://github.com/dfreniche/xc-launch)

	# BEGIN WordPress
	<IfModule mod_rewrite.c>
	RewriteEngine On
	#RewriteBase /blog/
	RewriteBase /~accountname/
	RewriteRule ^index\.php$ - [L]
	RewriteCond %{REQUEST_FILENAME} !-f
	RewriteCond %{REQUEST_FILENAME} !-d
	#RewriteRule . /blog/index.php [L]
	RewriteRule . /~accountname/index.php [L]

	#import <Foundation/Foundation.h>
	#import "sqlite3.h"

	typedef int64_t timestamp;

	NSUInteger randomNumberInRange(NSUInteger start, NSUInteger end);

	// Create a sample date using the ISO-8601 format.
	// 2013-04-23T16:29:05Z
	NSString* generateSampleDate();

	#!/usr/bin/php
	# Send SMS messages via Infomaniak.ch
	# You need an Infomaniak.ch account and have some credits to send SMS
	# Stephan Burlot, http://coriolis.ch Dec, 30 2012
	#
	<?php

	// Username (your email address)
	define('USER', '[email protected]');