dannguyen

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:

kepano

Source: https://stripe.com/annual-updates/2023

March 13, 2024

Dear Stripe community:

Charlie Munger described a two-part rule that works wonders in business, science, and elsewhere: 1) take a simple idea and 2) take it very seriously.

Stripe’s mission is to grow the GDP of the internet. The core idea behind the company—one we endeavor to take very seriously—is that we’re still early in the journey of software-driven innovation, and Stripe is an applied exercise in thinking through some of the corollaries of that. In particular, thanks to the new possi-bilities afforded by the internet, we believe that putting better—more global, easier to use, more flexible, faster, cheaper—economic infrastructure in the hands of companies and entrepreneurs will lead to a more vibrant and prosperous world. Remarkably, this journey was still in its infancy when Stripe launched in 2011. Thirteen years, and more than a doubling in internet users later, it’s still early. The world of 2034 is going to look very different.

veekaybee

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

dannberg

---
created: <% tp.file.creation_date() %>
---
tags:: [[+Daily Notes]]

# <% moment(tp.file.title,'YYYY-MM-DD').format("dddd, MMMM DD, YYYY") %>

<< [[Timestamps/<% tp.date.now("YYYY", -1) %>/<% tp.date.now("MM-MMMM", -1) %>/<% tp.date.now("YYYY-MM-DD-dddd", -1) %>|Yesterday]] | [[Timestamps/<% tp.date.now("YYYY", 1) %>/<% tp.date.now("MM-MMMM", 1) %>/<% tp.date.now("YYYY-MM-DD-dddd", 1) %>|Tomorrow]] >>

---

prologic

Learn Go in ~5mins

This is inspired by A half-hour to learn Rust and Zig in 30 minutes.

Basics

Your first Go program as a classical "Hello World" is pretty simple:

First we create a workspace for our project:

kcak11

Country Codes

List of all Country Codes (ISO & Dialing) sorted in alphabetical order.

konsbn

IanColdwater

Mute these words in your settings here: https://twitter.com/settings/muted_keywords

ActivityTweet
generic_activity_highlights
generic_activity_momentsbreaking
RankedOrganicTweet
suggest_activity
suggest_activity_feed
suggest_activity_highlights
suggest_activity_tweet

clowestab

const Parser  = require('rss-parser');
const request = require('request');
const fs      = require('fs');
const mime    = require('mime-types');
const slugify = require('slugify');

//Enter your ghost credentials here
const clientId     = "ghost-frontend";
const clientSecret = "enter-your-secret";
const username     = "enter-your-email";

rhythnic

// *******************************************************************
// ATTENTION
// This gist is now an npm module
// The API of some functions is altered slightly.
// All future work will happen in the repo.
// 
// https://gitlab.com/rhythnic/vuex-intern
// *******************************************************************

// *******************************************************************