Update app.py

app.py

@@ -1,21 +1,24 @@
 import streamlit as st
-from transformers import pipeline
+from transformers import pipeline, AutoTokenizer
 from PyPDF2 import PdfReader
 import docx
 import plotly.graph_objects as go
 
-# Page setup
+# Page configuration
 st.set_page_config(layout="wide")
 st.title("📄 AI Content Analyzer")
-st.markdown("Upload PDF/Word files (Max 1000 words analysis)")
+st.markdown("Upload PDF/Word files to detect AI-generated content")
 
 # Constants
-MAX_WORDS = 1000  # Word limit
-WORD_LIMIT_WARNING = 1500  # Warning threshold
+MAX_WORDS = 1000  # Maximum words to analyze
+WARNING_THRESHOLD = 1200  # Warning threshold for large files
 
+# Load AI detection model
 @st.cache_resource
 def load_model():
-    return pipeline("text-classification", model="roberta-base-openai-detector")
+    model_name = "roberta-base-openai-detector"
+    tokenizer = AutoTokenizer.from_pretrained(model_name)
+    return pipeline("text-classification", model=model_name, tokenizer=tokenizer)
 
 detector = load_model()
 
@@ -27,7 +30,7 @@ def create_gauge(score):
         mode = "gauge+number",
         value = score,
         domain = {'x': [0, 1], 'y': [0, 1]},
-        title = {'text': "AI Probability", 'font': {'size': 20}},
+        title = {'text': "AI Content Probability", 'font': {'size': 20}},
         gauge = {
             'axis': {'range': [None, 100], 'tickwidth': 1},
             'bar': {'color': "darkblue"},
@@ -39,7 +42,7 @@ def create_gauge(score):
     st.plotly_chart(fig, use_container_width=True)
 
 # File uploader
-uploaded_file = st.file_uploader("Choose file", type=["pdf", "docx", "txt"])
+uploaded_file = st.file_uploader("Upload file (PDF or Word)", type=["pdf", "docx"])
 
 if uploaded_file:
     # Extract text
@@ -47,30 +50,29 @@ if uploaded_file:
     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"):
+    else:
         doc = docx.Document(uploaded_file)
         text = " ".join([para.text for para in doc.paragraphs])
-    else:
-        text = uploaded_file.read().decode("utf-8")
 
     word_count = count_words(text)
     
-    if word_count > WORD_LIMIT_WARNING:
-        st.warning(f"⚠️ File has {word_count} words (Analyzing first {MAX_WORDS} words only)")
-    
-    if st.button("Analyze"):
+    # Word limit warning
+    if word_count > WARNING_THRESHOLD:
+        st.warning(f"⚠️ File contains {word_count} words (Analyzing first {MAX_WORDS} words only)")
+
+    if st.button("Analyze Content"):
         if word_count < 50:
-            st.error("❌ Not enough text (min 50 words required)")
+            st.error("❌ Insufficient text for analysis (minimum 50 words required)")
         else:
             # Process first 1000 words
             processed_text = " ".join(text.split()[:MAX_WORDS])
             
-            # Analysis
+            # Perform analysis
             result = detector(processed_text)
             ai_prob = result[0]['score']*100 if result[0]['label']=='FAKE' else 100-result[0]['score']*100
             
-            # Results
-            st.subheader("Results")
+            # Display results
+            st.subheader("Analysis Results")
             create_gauge(ai_prob)
             
             col1, col2 = st.columns(2)
@@ -79,7 +81,5 @@ if uploaded_file:
             with col2:
                 st.metric("AI Probability", f"{ai_prob:.1f}%")
             
-            with st.expander("View analysis details"):
-                st.write(f"**File:** {uploaded_file.name}")
-                st.write(f"**Model:** roberta-base-openai-detector")
-                st.text_area("Sample text", processed_text[:500]+"...", height=150)
+            with st.expander("View Text Sample"):
+                st.text(processed_text[:1000] + ("..." if word_count>1000 else ""))