Update src/streamlit_app.py

src/streamlit_app.py

@@ -6,7 +6,7 @@ import os
 from nltk.tokenize import sent_tokenize
 from transformers import DistilBertTokenizerFast, TFDistilBertForSequenceClassification
 
-# 📁 Use safe cache directory
+# 📁 Set Hugging Face cache directory (safe for deployments)
 os.environ["TRANSFORMERS_CACHE"] = "/tmp/huggingface"
 
 # 📥 Download NLTK tokenizer
@@ -14,7 +14,7 @@ nltk_data_path = "/tmp/nltk_data"
 nltk.download("punkt_tab", download_dir=nltk_data_path)
 nltk.data.path.append(nltk_data_path)
 
-# 🚀 Load model & tokenizer once using session state
+# 🚀 Load model & tokenizer once using cache
 @st.cache_resource
 def load_model_and_tokenizer():
     tokenizer = DistilBertTokenizerFast.from_pretrained(
@@ -35,7 +35,7 @@ def predict_sentence_ai_probability(sentence):
     prob_ai = tf.sigmoid(logits)[0][0].numpy()
     return prob_ai
 
-# 📊 Analyze all sentences
+# 📊 Analyze text
 def predict_ai_generated_percentage(text, threshold=0.15):
     text = text.strip()
     sentences = sent_tokenize(text)
@@ -53,30 +53,38 @@ def predict_ai_generated_percentage(text, threshold=0.15):
     ai_percentage = (ai_sentence_count / total_sentences) * 100 if total_sentences > 0 else 0.0
     return ai_percentage, results
 
-# 🖥️ Streamlit App UI
+# 🖥️ Streamlit UI setup
 st.set_page_config(page_title="AI Detector", layout="wide")
 st.title("🧠 AI Content Detector")
-st.markdown("This app detects the percentage of **AI-generated content** using DistilBERT.")
+st.markdown("This app detects the percentage of **AI-generated content** using sentence-level analysis with DistilBERT.")
 
-# Session state to track if user clicked analyze
+# 📋 Text input
+user_input = st.text_area("📋 Paste your text below to check for AI-generated sentences:", height=300)
+
+# ✅ Initialize session state
 if "analysis_done" not in st.session_state:
     st.session_state.analysis_done = False
+    st.session_state.analysis_results = None
+    st.session_state.ai_percentage = None
 
-# 📋 Input Area
-user_input = st.text_area("📋 Paste your text below to check for AI-generated sentences:", height=300)
-
-# 🔍 Analyze Button
+# 🔍 Analyze button logic
 if st.button("🔍 Analyze"):
+    # 🧹 Clear previous cache/state
+    st.session_state.analysis_done = False
+    st.session_state.analysis_results = None
+    st.session_state.ai_percentage = None
+
     if not user_input.strip():
         st.warning("⚠️ Please enter some text.")
     else:
+        # Run fresh analysis
         ai_percentage, analysis_results = predict_ai_generated_percentage(user_input)
         st.session_state.analysis_done = True
-        st.session_state.ai_percentage = ai_percentage
         st.session_state.analysis_results = analysis_results
+        st.session_state.ai_percentage = ai_percentage
 
-# 📤 Show results after button press
-if st.session_state.get("analysis_done", False):
+# 📤 Show results if analysis was done
+if st.session_state.analysis_done:
     st.subheader("🔍 Sentence-level Analysis")
     for i, (sentence, prob, is_ai) in enumerate(st.session_state.analysis_results, start=1):
         label = "🟢 Human" if not is_ai else "🔴 AI"