Update app.py

app.py

@@ -2,25 +2,25 @@ import gradio as gr
 import pdfplumber
 from transformers import pipeline
 
-# Inicjalizacja modelu do ekstrakcji informacji
-extractor = pipeline("ner", model="dslim/bert-base-NER")
+# Inicjalizacja modelu NER
+extractor = pipeline("ner", model="dslim/bert-base-NER", aggregation_strategy="simple")
 
 def extract_info(pdf_file):
     with pdfplumber.open(pdf_file) as pdf:
-        text = ""
-        for page in pdf.pages:
-            text += page.extract_text() + "\n"
+        text = "\n".join(page.extract_text() for page in pdf.pages if page.extract_text())
 
     # Przetwarzanie tekstu modelem NLP
     entities = extractor(text)
 
-    # Filtrowanie i formatowanie wyników
+    # Formatowanie wyników
     extracted_data = {}
     for entity in entities:
-        label = entity['entity']
-        word = entity['word']
+        label = entity["entity_group"]
+        word = entity["word"]
+
         if label not in extracted_data:
             extracted_data[label] = []
+
         extracted_data[label].append(word)
 
     return extracted_data