Update app.py

app.py

@@ -1,6 +1,57 @@
 import streamlit as st
+from transformers import pipeline
+from PyPDF2 import PdfReader
+import docx
 
-st.title("GK AI Detector")  # Your app title
-user_text = st.text_input("Enter text here")  # User input
-if user_text:
-    st.success(f"Your text: {user_text}")  # Display result
+# Page setup
+st.set_page_config(layout="wide")
+st.title("📄 AI Content Analyzer")
+st.markdown("Upload PDF/Word files to detect AI-generated text")
+
+# Load AI detection model
+@st.cache_resource
+def load_model():
+    return pipeline("text-classification", model="roberta-base-openai-detector")
+
+detector = load_model()
+
+# File uploader
+uploaded_file = st.file_uploader("Upload file (PDF or Word)", type=["pdf", "docx", "txt"])
+
+if uploaded_file:
+    # Extract text
+    text = ""
+    if uploaded_file.name.endswith(".pdf"):
+        reader = PdfReader(uploaded_file)
+        text = "".join([page.extract_text() or "" for page in reader.pages])
+    elif uploaded_file.name.endswith(".docx"):
+        doc = docx.Document(uploaded_file)
+        text = "\n".join([para.text for para in doc.paragraphs])
+    else:
+        text = uploaded_file.read().decode("utf-8")
+
+    # Analyze on button click
+    if st.button("Analyze Content"):
+        if len(text) < 50:
+            st.warning("Not enough text to analyze!")
+        else:
+            result = detector(text[:5000])  # First 5000 chars for speed
+            ai_prob = result[0]['score'] * 100 if result[0]['label'] == 'FAKE' else 100 - (result[0]['score'] * 100)
+            
+            # Display results
+            st.subheader("Analysis Results")
+            
+            # AI Probability Meter
+            st.metric("AI Content Probability", f"{ai_prob:.2f}%")
+            st.progress(int(ai_prob))
+            
+            # File details
+            st.markdown(f"""
+            - **File:** `{uploaded_file.name}`
+            - **Text Length:** {len(text)} characters
+            - **AI Probability:** {ai_prob:.2f}%
+            """)
+
+            # Text preview
+            with st.expander("View extracted text"):
+                st.text(text[:1000] + "...")  # First 1000 chars