Update app.py

app.py

@@ -7,7 +7,6 @@ import numpy as np
 import os
 from huggingface_hub import upload_file, hf_hub_download
 
-# === Custom PUP-themed CSS ===
 PUP_Themed_css = """
 html, body, .gradio-container, .gr-app {
     height: 100% !important;
@@ -19,7 +18,6 @@ html, body, .gradio-container, .gr-app {
 }
 """
 
-# === Load Models and Data ===
 embedding_model = SentenceTransformer('paraphrase-mpnet-base-v2')
 llm = pipeline("text2text-generation", model="google/flan-t5-small")
 
@@ -39,7 +37,6 @@ feedback_embeddings = None
 feedback_path = "outputs/feedback.json"
 os.makedirs("outputs", exist_ok=True)
 
-# === Load feedback from Hugging Face if available ===
 try:
     hf_token = os.getenv("PUP_AI_Chatbot_Token")
     downloaded_path = hf_hub_download(
@@ -55,7 +52,6 @@ try:
         if feedback_questions:
             feedback_embeddings = embedding_model.encode(feedback_questions, convert_to_tensor=True)
 
-    # Save to local copy for later editing during runtime
     with open(feedback_path, "w") as f_local:
         json.dump(feedback_data, f_local, indent=4)
 
@@ -63,7 +59,6 @@ except Exception as e:
     print(f"[Startup] No feedback loaded from HF: {e}")
     feedback_data = []
 
-# === Hugging Face Upload ===
 def upload_feedback_to_hf():
     hf_token = os.getenv("PUP_AI_Chatbot_Token")
     if not hf_token:
@@ -81,11 +76,9 @@ def upload_feedback_to_hf():
     except Exception as e:
         print(f"Error uploading feedback to HF: {e}")
 
-# === Chatbot Response Function ===
 def chatbot_response(query, chat_history):
     query_embedding = embedding_model.encode([query], convert_to_tensor=True)
 
-    # === Feedback Matching ===
     if feedback_embeddings is not None:
         feedback_scores = cosine_similarity(query_embedding.cpu().numpy(), feedback_embeddings.cpu().numpy())[0]
         best_idx = int(np.argmax(feedback_scores))
@@ -103,7 +96,6 @@ def chatbot_response(query, chat_history):
             chat_history.append((query, response))
             return "", chat_history, gr.update(visible=True)
 
-    # === Main Handbook Matching ===
     similarity_scores = cosine_similarity(query_embedding.cpu().numpy(), question_embeddings.cpu().numpy())[0]
     best_idx = int(np.argmax(similarity_scores))
     best_score = similarity_scores[best_idx]
@@ -137,7 +129,6 @@ def chatbot_response(query, chat_history):
     chat_history.append((query, final_response))
     return "", chat_history, gr.update(visible=True)
 
-# === Feedback Save & Upvote/Downvote Tracking ===
 def record_feedback(feedback, chat_history):
     global feedback_embeddings
     if chat_history:
@@ -175,7 +166,6 @@ def record_feedback(feedback, chat_history):
 
     return gr.update(visible=False)
 
-# === Gradio UI ===
 with gr.Blocks(css=PUP_Themed_css, title="University Handbook AI Chatbot") as demo:
     gr.Markdown(
         "<div style='"
@@ -213,6 +203,5 @@ with gr.Blocks(css=PUP_Themed_css, title="University Handbook AI Chatbot") as de
     thumbs_up.click(lambda state: record_feedback("positive", state), inputs=[state], outputs=[feedback_row])
     thumbs_down.click(lambda state: record_feedback("negative", state), inputs=[state], outputs=[feedback_row])
 
-# === Launch App ===
 if __name__ == "__main__":
     demo.launch()