Spaces:
Running
Running
update readme
Browse files
README.md
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
-
# DocumentIQA: Document Insight Question/Answer
|
| 2 |
|
| 3 |
## Introduction
|
| 4 |
|
| 5 |
-
Question/Answering on scientific documents.
|
| 6 |
In our implementation we use [Grobid](https://github.com/kermitt2/grobid) for text extraction instead of the raw PDF2Text converter.
|
| 7 |
Thanks to Grobid we are able to precisely extract abstract and full-text.
|
| 8 |
This is just the beginning and publishing might help gathering more feedback.
|
|
@@ -16,12 +16,6 @@ https://document-insights.streamlit.app/
|
|
| 16 |
**OpenAI or HuggingFace API KEY required**
|
| 17 |
|
| 18 |
|
| 19 |
-
### Screencast
|
| 20 |
-
This is a screencast on an older version:
|
| 21 |
-
|
| 22 |
-
https://github.com/lfoppiano/document-qa/assets/15426/b3882119-5a87-40f5-a2de-ad47447eb40c
|
| 23 |
-
|
| 24 |
-
|
| 25 |
### Acknolwedgement
|
| 26 |
|
| 27 |
This project is developed at the [National Institute for Materials Science](https://www.nims.go.jp) (NIMS) in Japan.
|
|
|
|
| 1 |
+
# DocumentIQA: Scientific Document Insight Question/Answer
|
| 2 |
|
| 3 |
## Introduction
|
| 4 |
|
| 5 |
+
Question/Answering on scientific documents.
|
| 6 |
In our implementation we use [Grobid](https://github.com/kermitt2/grobid) for text extraction instead of the raw PDF2Text converter.
|
| 7 |
Thanks to Grobid we are able to precisely extract abstract and full-text.
|
| 8 |
This is just the beginning and publishing might help gathering more feedback.
|
|
|
|
| 16 |
**OpenAI or HuggingFace API KEY required**
|
| 17 |
|
| 18 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
### Acknolwedgement
|
| 20 |
|
| 21 |
This project is developed at the [National Institute for Materials Science](https://www.nims.go.jp) (NIMS) in Japan.
|