ExtractThinker: AI Document Intelligence with LLMs

Introduction

It’s been a long road to get here. I’ve been working with LLMs since October 2021 (OpenAI Codex) and immediately started working on extraction. I tried to build a solution in .NET similar to what is presented here, but creating an agnostic solution was not easy, especially without access to the useful tools available in Python.

I spent over a month migrating all the code that you’ll see in this GitHub repo. This is the first version, more …

access ai build codex document easy extraction gpt-4 intelligence llm llms ocr openai openai codex solution tools