Spaces:
Running
Running
Create app.py
Browse files
app.py
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import gradio as gr
|
2 |
+
import pdfplumber
|
3 |
+
from transformers import pipeline
|
4 |
+
|
5 |
+
# Inicjalizacja modelu
|
6 |
+
extractor = pipeline("ner", model="opendatalab/PDF-Extract-Kit")
|
7 |
+
|
8 |
+
def extract_info(pdf_file):
|
9 |
+
with pdfplumber.open(pdf_file) as pdf:
|
10 |
+
text = ""
|
11 |
+
for page in pdf.pages:
|
12 |
+
text += page.extract_text()
|
13 |
+
|
14 |
+
# Przetwarzanie tekstu za pomoc膮 modelu
|
15 |
+
entities = extractor(text)
|
16 |
+
|
17 |
+
# Filtrowanie i formatowanie wynik贸w
|
18 |
+
results = {}
|
19 |
+
for entity in entities:
|
20 |
+
label = entity['entity']
|
21 |
+
word = entity['word']
|
22 |
+
if label not in results:
|
23 |
+
results[label] = []
|
24 |
+
results[label].append(word)
|
25 |
+
|
26 |
+
return results
|
27 |
+
|
28 |
+
# Interfejs u偶ytkownika
|
29 |
+
iface = gr.Interface(
|
30 |
+
fn=extract_info,
|
31 |
+
inputs=gr.inputs.File(label="Wybierz plik PDF"),
|
32 |
+
outputs=gr.outputs.JSON(label="Wykryte informacje"),
|
33 |
+
title="Ekstrakcja informacji z faktur PDF",
|
34 |
+
description="Prze艣lij plik PDF z faktur膮, aby wyodr臋bni膰 okre艣lone informacje."
|
35 |
+
)
|
36 |
+
|
37 |
+
if __name__ == "__main__":
|
38 |
+
iface.launch()
|