# DocumentIQA: Document Insight Question/Answer

## Introduction

Question/Answering on documents. Upload your document and ask questions. 
In our implementation we use [Grobid](https://github.com/kermitt2/grobid) for text extraction instead of the raw PDF2Text converter.
Thanks to Grobid we are able to precisely extract abstract and full-text. 
This is just the beginning and publishing might help gathering more feedback. 

**Work in progress**

https://document-insights.streamlit.app/

**OpenAI Key required**: At the moment you need the OpenAi Key to use this app. 
Google or look for example [here](https://medium.com/geekculture/openai-a-step-by-step-guide-to-getting-your-api-key-gpt-usage-control-artificial-intelligence-2a0917c70f3f), on how to generate one.


### Screencast 
This is a screencast on an older version: 

https://github.com/lfoppiano/document-qa/assets/15426/b3882119-5a87-40f5-a2de-ad47447eb40c


### Acknolwedgement 

This project is developed at the [National Institute for Materials Science](https://www.nims.go.jp) (NIMS) in Japan.