Update app.py

app.py

@@ -1,11 +1,10 @@
 import gradio as gr
 import json
 from sentence_transformers import SentenceTransformer
-from transformers import pipeline
 from sklearn.metrics.pairwise import cosine_similarity
 import numpy as np
 import os
-from huggingface_hub import upload_file, hf_hub_download
+from huggingface_hub import upload_file, hf_hub_download, InferenceClient
 
 PUP_Themed_css = """
 html, body, .gradio-container, .gr-app {
@@ -19,7 +18,11 @@ html, body, .gradio-container, .gr-app {
 """
 
 embedding_model = SentenceTransformer('paraphrase-mpnet-base-v2')
-llm = pipeline("text2text-generation", model="google/flan-t5-small")
+inference_token = os.getenv("HF_TOKEN") or os.getenv("PUP_AI_Chatbot_Token")
+inference_client = InferenceClient(
+    model="mistralai/Mixtral-8x7B-Instruct-v0.1",
+    token=inference_token
+)
 
 with open("dataset.json", "r") as f:
     dataset = json.load(f)
@@ -31,8 +34,8 @@ question_embeddings = embedding_model.encode(questions, convert_to_tensor=True)
 chat_history = []
 feedback_data = []
 feedback_questions = []
-feedback_answers = []
 feedback_embeddings = None
+dev_mode = {"enabled": False}  # DevMode flag
 
 feedback_path = "outputs/feedback.json"
 os.makedirs("outputs", exist_ok=True)
@@ -48,7 +51,6 @@ try:
     with open(downloaded_path, "r") as f:
         feedback_data = json.load(f)
         feedback_questions = [item["question"] for item in feedback_data]
-        feedback_answers = [item["response"] for item in feedback_data]
         if feedback_questions:
             feedback_embeddings = embedding_model.encode(feedback_questions, convert_to_tensor=True)
 
@@ -63,7 +65,7 @@ def upload_feedback_to_hf():
     hf_token = os.getenv("PUP_AI_Chatbot_Token")
     if not hf_token:
         raise ValueError("Hugging Face token not found in environment variables!")
-    
+
     try:
         upload_file(
             path_or_fileobj=feedback_path,
@@ -104,40 +106,33 @@ def chatbot_response(query, chat_history):
 
     if best_score < 0.4:
         response = "Sorry, but the PUP handbook does not contain such information."
-        chat_history.append((query, response))
-        return "", chat_history, gr.update(visible=True)
-
-    prompt = (
-        f"\"{matched_a}\"\n\n"
-        f"Please explain this to a student in a short, natural, and easy-to-understand way. "
-        f"Use simple words, and do not add new information."
-    )
-
-    llm_response = llm(prompt, max_length=200, do_sample=True, temperature=0.7, top_p=0.9)[0]["generated_text"].strip()
-    if not llm_response:
-        llm_response = "I'm sorry, I couldn't simplify that at the moment."
-
-    a_embedding = embedding_model.encode([matched_a], convert_to_tensor=True)
-    llm_embedding = embedding_model.encode([llm_response], convert_to_tensor=True)
-    explanation_similarity = cosine_similarity(a_embedding.cpu().numpy(), llm_embedding.cpu().numpy())[0][0]
-
-    if explanation_similarity >= 0.95:
-        final_response = f"According to the university handbook, {matched_a}"
     else:
-        final_response = f"According to the university handbook, {matched_a} In simpler terms, {llm_response}"
-
-    chat_history.append((query, final_response))
+        if dev_mode["enabled"]:
+            prompt = (
+                f"A student asked:\n\"{query}\"\n\n"
+                f"Relevant handbook info:\n\"{matched_a}\"\n\n"
+                f"Please answer based only on this handbook content."
+            )
+            try:
+                response = inference_client.text_generation(prompt, max_new_tokens=200, temperature=0.7)
+            except Exception as e:
+                print(f"[ERROR] HF inference failed: {e}")
+                response = f"(Fallback) {matched_a}"
+        else:
+            response = f"According to the university handbook, {matched_a}"
+
+    chat_history.append((query, response.strip()))
     return "", chat_history, gr.update(visible=True)
 
 def record_feedback(feedback, chat_history):
-    global feedback_embeddings
+    global feedback_embeddings, feedback_questions
     if chat_history:
         last_query, last_response = chat_history[-1]
         matched = False
+        new_embedding = embedding_model.encode([last_query], convert_to_tensor=True)
 
         for item in feedback_data:
             existing_embedding = embedding_model.encode([item["question"]], convert_to_tensor=True)
-            new_embedding = embedding_model.encode([last_query], convert_to_tensor=True)
             similarity = cosine_similarity(existing_embedding.cpu().numpy(), new_embedding.cpu().numpy())[0][0]
             if similarity >= 0.8 and item["response"] == last_response:
                 matched = True
@@ -168,23 +163,45 @@ def record_feedback(feedback, chat_history):
 
 with gr.Blocks(css=PUP_Themed_css, title="University Handbook AI Chatbot") as demo:
     gr.Markdown(
-        "<div style='"
-        "background-color: #ffffff; "
-        "border-radius: 16px; "
-        "padding: 24px 16px; "
-        "margin-bottom: 24px; "
-        "box-shadow: 0 6px 16px rgba(0, 0, 0, 0.15); "
-        "max-width: 700px; "
-        "margin-left: auto; "
-        "margin-right: auto; "
-        "text-align: center;'>"
-        "<h1 style='font-size: 2.2rem; margin: 0;'>University Inquiries AI Chatbot</h1>"
-        "</div>"
-    )
+    """
+    <div style='
+        background-color: var(--block-background-fill); 
+        border-radius: 16px; 
+        padding: 24px 16px; 
+        margin-bottom: 24px; 
+        box-shadow: 0 6px 16px rgba(0, 0, 0, 0.15); 
+        max-width: 700px; 
+        margin-left: auto; 
+        margin-right: auto; 
+        text-align: center;
+        color: var(--text-color);'>
+        <h1 style='font-size: 2.2rem; margin: 0;'>University Inquiries AI Chatbot</h1>
+    </div>
+    """
+)
 
     state = gr.State(chat_history)
     chatbot_ui = gr.Chatbot(label="Chat", show_label=False)
 
+    with gr.Row():
+        dev_btn = gr.Button("DevMode 🔐")
+        password_box = gr.Textbox(placeholder="Enter Dev password", type="password", visible=False, show_label=False)
+        confirm_btn = gr.Button("Confirm", visible=False)
+
+    dev_pass = os.getenv("DEV_MODE_PASSWORD", "letmein")
+
+    def show_password_input():
+        return gr.update(visible=True), gr.update(visible=True)
+
+    def enable_devmode(password_input):
+        if password_input == dev_pass:
+            dev_mode["enabled"] = True
+            return gr.update(visible=False), gr.update(visible=False), gr.update(value="DevMode ✅", interactive=False)
+        return gr.update(visible=True), gr.update(visible=True), gr.update(value="Wrong password. Try again.")
+
+    dev_btn.click(show_password_input, outputs=[password_box, confirm_btn])
+    confirm_btn.click(enable_devmode, inputs=[password_box], outputs=[password_box, confirm_btn, dev_btn])
+
     with gr.Row():
         query_input = gr.Textbox(placeholder="Type your question here...", show_label=False)
         submit_btn = gr.Button("Submit")