Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,37 @@
|
|
1 |
---
|
2 |
license: openrail
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: openrail
|
3 |
---
|
4 |
+
|
5 |
+
|
6 |
+
<h3 align="center">PDF Paragraphs Extraction</h3>
|
7 |
+
<p align="center">A model for extracting paragraphs from PDFs</p>
|
8 |
+
|
9 |
+
This model uses features from the PDF to extract the text and paragraphs from it. It can be used as a service.
|
10 |
+
|
11 |
+
The paragraphs contain the page number, the position in the page, the size, and the text.
|
12 |
+
|
13 |
+
|
14 |
+
## Quick Start
|
15 |
+
|
16 |
+
Download the service that uses the model:
|
17 |
+
|
18 |
+
git clone https://github.com/huridocs/pdf_paragraphs_extraction.git
|
19 |
+
cd pdf_paragraphs_extraction
|
20 |
+
|
21 |
+
Start the service:
|
22 |
+
|
23 |
+
./run start
|
24 |
+
|
25 |
+
Get the paragraphs from a PDF:
|
26 |
+
|
27 |
+
curl -X GET -F 'file=@/PATH/TO/PDF/pdf_name.pdf' localhost:5051
|
28 |
+
|
29 |
+
To stop the server:
|
30 |
+
|
31 |
+
./run stop
|
32 |
+
|
33 |
+
|
34 |
+
## Performance
|
35 |
+
|
36 |
+
Accuracy: 93.9%
|
37 |
+
Speed: tbd
|