Drew Dresser drewdresser

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

Python relative imports in AWS Lambda fail with attempted relative import with no known parent package

The Problem

In AWS Lambda if I attempt an explicit relative import like this

.
├── lambda_file.py
└── example.py

Bridge Function between Kinesis Streams and Step Functions

For each record read from the Kinesis Stream, a StepFunction state machine will be executed asynchronously.

Required Environment Variables

region: the AWS region where your StepFunction state machine is defined.
stateMachineArn: the ARN of the StepFunction state machine you want to execute.

Notes

This gist contains lists of modules available in

Python 3.10
Python 3.9
Python 3.8
Python 3.7
Python 3.6
Python 2.7

in AWS Lambda.

	# Original instructions: https://forum.cursor.com/t/share-your-rules-for-ai/2377/3
	# Original original instructions: https://x.com/NickADobos/status/1814596357879177592

	You are an expert AI programming assistant that primarily focuses on producing clear, readable SwiftUI code.

	You always use the latest version of SwiftUI and Swift, and you are familiar with the latest features and best practices.

	You carefully provide accurate, factual, thoughtful answers, and excel at reasoning.

	- Follow the user’s requirements carefully & to the letter.

	#!/usr/bin/env bash

	# Small shell script to more easily automatically download and transcribe live stream VODs.
	# This uses YT-DLP, ffmpeg and the CPP version of Whisper: https://github.com/ggerganov/whisper.cpp
	# Use `./transcribe-vod help` to print help info.

	# MIT License

	# Copyright (c) 2022 Daniils Petrovs

	Updated 2025-01-17 thanks to Yemster's comment.

	This should work on any architecture of Amazon Linux 2.
	(_Although not tested , should also work for Amazon Linux 2023_).

	Prereq
	- visit https://johnvansickle.com/ffmpeg/ to grab the link to the relevant tarball for your specific server architecture.
	- Use `uname -a` to find out your arch if unknown

	### TL;DR

	###
	###
	### UPDATE: For Win 11, I recommend using this tool in place of this script:
	### https://christitus.com/windows-tool/
	### https://github.com/ChrisTitusTech/winutil
	### https://www.youtube.com/watch?v=6UQZ5oQg8XA
	### iwr -useb https://christitus.com/win \| iex
	###
	### OR take a look at
	### https://github.com/HotCakeX/Harden-Windows-Security