Practical AI: Machine Learning, Data Science, LLM

What's up, DocQuery?

Oct 12, 2022

42:19

Creator website

Highlights

AI Chapters

Episode notes

DocQuery - What Are the Things That Matter?

01:42

Using Computer Vision to Reason About PDF Files

01:36

Is There a Problem With Pre-Trained Machine Learning Models?

02:29

Ocr

03:14

Introduction

2min

DocQuery - What's Your Story?

3min

Using Computer Vision to Reason About PDF Files

2min

Ocr

3min

What Kind of Problems Do You See in OCR?

2min

Is There a Problem With Pre-Trained Machine Learning Models?

2min

How Did You Identify the Landscape of Problems to Solve?

3min

DocQuery - What Are the Things That Matter?

2min

Empira DocQuery

5min

10.

Hugging Face and the Evolution of Deep Learning

4min

11.

What Motivated You to Release Stock Query as Open Source?

3min

12.

The Real Answer and the Inspiring Answer

3min

13.

DocQuery - What's Next for DocQuery?

4min

14.

DocQuery

4min

15.

Practical AI - What Is It All About?

2min

Chris sits down with Ankur Goyal to talk about DocQuery, Impira’s new open source ML model. DocQuery lets you ask questions about semi-structured data (like invoices) and unstructured documents (like contracts) using Large Language Models (LLMs). Ankur illustrates many of the ways DocQuery can help people tame documents, and references Chris’s real life tasks as a non-profit director to demonstrate that DocQuery is indeed practical AI.

Join the discussion

Changelog++ members support our work, get closer to the metal, and make the ads disappear. Join today!

Featuring: