Update app.py

app.py

@@ -1,70 +1,115 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-
-def respond(
-    message,
-    history: list[dict[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-    hf_token: gr.OAuthToken,
-):
-    """
-    For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-    """
-    client = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b")
-
-    messages = [{"role": "system", "content": system_message}]
-
-    messages.extend(history)
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-chatbot = gr.ChatInterface(
-    respond,
-    type="messages",
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
+import json
+import os
+
+DATA_FILE = "student_profiles.json"
+
+# ---------- Data Storage ----------
+def load_student_data():
+    if not os.path.exists(DATA_FILE):
+        return {}
+    with open(DATA_FILE, "r", encoding="utf-8") as f:
+        return json.load(f)
+
+def save_student_data(data):
+    with open(DATA_FILE, "w", encoding="utf-8") as f:
+        json.dump(data, f, indent=4, ensure_ascii=False)
+
+def generate_new_student_id():
+    data = load_student_data()
+    if not data:
+        return "student_1"
+    numbers = [int(k.split("_")[1]) for k in data if k.startswith("student_")]
+    return f"student_{max(numbers) + 1}"
+
+def add_student_data(new_data):
+    data = load_student_data()
+    new_id = generate_new_student_id()
+    data[new_id] = new_data
+    save_student_data(data)
+    return new_id, new_data
+
+# ---------- Chat & Roadmap Simulation ----------
+def get_gemini_response(prompt, student_data):
+    # Replace with real LLM call later
+    return f"(Simulated AI Response based on {student_data['personality']} profile: {prompt})"
+
+def generate_ai_insights(student_data):
+    return f"(Insights: Your learning style is {student_data['learning_style']}, motivation is {student_data['motivation_level']})"
+
+# ---------- Gradio Interface ----------
+def create_profile(learning_style, academic_progress, personality, interests, goals,
+                   level, preferred_methods, iq_level, eq_level, decision_style,
+                   motivation_level, study_environment, community_groups):
+    new_data = {
+        "learning_style": learning_style,
+        "academic_progress": academic_progress,
+        "personality": personality,
+        "interests": interests,
+        "goals": goals,
+        "level": level,
+        "preferred_methods": [m.strip() for m in preferred_methods.split(",") if m.strip()],
+        "iq_level": iq_level,
+        "eq_level": eq_level,
+        "decision_making_style": decision_style,
+        "motivation_level": motivation_level,
+        "preferred_study_environment": study_environment,
+        "community_groups": [g.strip() for g in community_groups.split(",") if g.strip()]
+    }
+    new_id, saved_data = add_student_data(new_data)
+    return f"✅ New student created with ID: {new_id}", json.dumps(saved_data, indent=2, ensure_ascii=False), list(load_student_data().keys())
+
+def chat(student_id, message):
+    data = load_student_data()
+    student_data = data.get(student_id)
+    if not student_data:
+        return "❌ Student not found."
+
+    if message.lower() == "roadmap":
+        return get_gemini_response("roadmap", student_data)
+    elif message.lower() == "insights":
+        return generate_ai_insights(student_data)
+    else:
+        return get_gemini_response(message, student_data)
 
 with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
+    gr.Markdown("# 🎓 ThinkPal – Personalized Learning Assistant")
+
+    with gr.Tab("➕ Add Student"):
+        with gr.Row():
+            learning_style = gr.Textbox(label="Learning Style")
+            academic_progress = gr.Textbox(label="Academic Progress")
+        personality = gr.Textbox(label="Personality")
+        interests = gr.Textbox(label="Interests")
+        goals = gr.Textbox(label="Goals")
+        level = gr.Textbox(label="Level")
+        preferred_methods = gr.Textbox(label="Preferred Methods (comma-separated)")
+        iq_level = gr.Textbox(label="IQ Level")
+        eq_level = gr.Textbox(label="EQ Level")
+        decision_style = gr.Textbox(label="Decision Style")
+        motivation_level = gr.Textbox(label="Motivation Level")
+        study_environment = gr.Textbox(label="Study Environment")
+        community_groups = gr.Textbox(label="Community Groups (comma-separated)")
+
+        create_btn = gr.Button("Save Profile")
+        status = gr.Textbox(label="Status")
+        preview = gr.Textbox(label="Profile Preview", lines=8)
+        student_list = gr.Dropdown(label="Student IDs", choices=list(load_student_data().keys()), value=None)
+
+        create_btn.click(
+            fn=create_profile,
+            inputs=[learning_style, academic_progress, personality, interests, goals,
+                    level, preferred_methods, iq_level, eq_level, decision_style,
+                    motivation_level, study_environment, community_groups],
+            outputs=[status, preview, student_list]
+        )
+
+    with gr.Tab("💬 Chat"):
+        student_select = gr.Dropdown(label="Choose Student", choices=list(load_student_data().keys()))
+        chat_in = gr.Textbox(label="Message (type 'roadmap' or 'insights')")
+        chat_out = gr.Textbox(label="Chatbot Response", lines=6)
+        chat_btn = gr.Button("Send")
 
+        chat_btn.click(fn=chat, inputs=[student_select, chat_in], outputs=chat_out)
 
-if __name__ == "__main__":
-    demo.launch()
+demo.launch()