Create app.py

app.py

@@ -0,0 +1,52 @@
+import streamlit as st
+import torch
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import fitz
+import os
+
+# Load the model and tokenizer
+model = AutoModelForSequenceClassification.from_pretrained("REEM-ALRASHIDI/LongFormer-Paper-Citaion-Classifier")
+tokenizer = AutoTokenizer.from_pretrained("allenai/longformer-base-4096")
+
+def extract_text_from_pdf(file_path):
+    text = ''
+    with fitz.open(file_path) as pdf_document:
+        for page_number in range(pdf_document.page_count):
+            page = pdf_document.load_page(page_number)
+            text += page.get_text()
+    return text
+
+def predict_class(text):
+    try:
+        inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True)
+        with torch.no_grad():
+            outputs = model(**inputs)
+            logits = outputs.logits
+            predicted_class = torch.argmax(logits, dim=1).item()
+        return predicted_class
+    except Exception as e:
+        st.error(f"Error during prediction: {e}")
+        return None
+
+st.title("Paper Citation Classifier")
+
+# Input text boxes for abstract, full text, and affiliations
+abstract_input = st.text_area("Enter Abstract:")
+full_text_input = st.text_area("Enter Full Text:")
+affiliations_input = st.text_area("Enter Affiliations:")
+
+# PDF upload option
+uploaded_file = st.file_uploader("Upload a PDF file", type=["pdf"])
+if uploaded_file is not None:
+    file_text = extract_text_from_pdf(uploaded_file)
+    st.text("Extracted Text from PDF:")
+    st.text(file_text)
+
+    # Concatenate inputs with [SEP]
+    combined_text = f"{abstract_input} [SEP] {full_text_input} [SEP] {affiliations_input} [SEP] {file_text}"
+
+    if st.button("Predict"):
+        predicted_class = predict_class(combined_text)
+        if predicted_class is not None:
+            class_labels = ["Level 1", "Level 2", "Level 3", "Level 4"]
+            st.text(f"Predicted Class: {class_labels[predicted_class]}")