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:

adtac

🖥️ See Demo

3.5 fps, Paperwhite 3
@adtac_

step 1: jailbreak your Kindle

mobileread.com is your best resource here, follow the instructions from the LanguageBreak thread

I didn't really follow the LanguageBreak instructions because I didn't care about most of the features + I was curious to do it myself, but the LanguageBreak github repo was invaluable for debugging

joepie91

Terminology

• View: Also called a "template", a file that contains markup (like HTML) and optionally additional instructions on how to generate snippets of HTML, such as text interpolation, loops, conditionals, includes, and so on.
• View engine: Also called a "template library" or "templater", ie. a library that implements view functionality, and potentially also a custom language for specifying it (like Pug does).
• HTML templater: A template library that's designed specifically for generating HTML. It understands document structure and thus can provide useful advanced tools like mixins, as well as more secure output escaping (since it can determine the right escaping approach from the context in which a value is used), but it also means that the templater is not useful for anything other than HTML.
• String-based templater: A template library that implements templating logic, but that has no understanding of the content it is generating - it simply concatenates together strings, potenti

subfuzion

Common Options

-#, --progress-bar Make curl display a simple progress bar instead of the more informational standard meter.

-b, --cookie <name=data> Supply cookie with request. If no =, then specifies the cookie file to use (see -c).

-c, --cookie-jar <file name> File to save response cookies to.

balzer82

pirafrank

#!/bin/bash

if [[ $EUID -ne 0 ]]; then
    echo -e "
    ROOT PRIVILEDGES NEEDED!
    You have to run this script as root.
    Aborting...
    "
    exit 1
else

nebw

CamDavidsonPilon

{
  "lines.linewidth": 2.0,
  "examples.download": true,
  "patch.linewidth": 0.5,
  "legend.fancybox": true,
  "axes.color_cycle": [
    "#30a2da",
    "#fc4f30",
    "#e5ae38",
    "#6d904f",

robschmuecker

This example pulls together various examples of work with trees in D3.js.

The panning functionality can certainly be improved in my opinion and I would be thrilled to see better solutions contributed.

One can do all manner of housekeeping or server related calls on the drop event to manage a remote tree dataset for example.

Dragging can be performed on any node other than root (flare). Dropping can be done on any node.

Panning can either be done by dragging an empty part of the SVG around or dragging a node towards an edge.

panisson

#  Copyright (C) 2013 Istituto per l'Interscambio Scientifico I.S.I.
#  You can contact us by email ([email protected]) or write to:
#  ISI Foundation, Via Alassio 11/c, 10126 Torino, Italy.
#
#  This work is licensed under a Creative Commons 4.0
#  Attribution-NonCommercial-ShareAlike License
#  You may obtain a copy of the License at
#  http://creativecommons.org/licenses/by-nc-sa/4.0/
#
#  This program was written by Andre Panisson <[email protected]> at