Update app.py

app.py

@@ -1,77 +1,63 @@
-import gradio as gr
-import requests
 import os
+import requests
+import gradio as gr
 from dotenv import load_dotenv
 
-# Load environment variables
+# Load API key from .env or Hugging Face secret
 load_dotenv()
-GROQ_API_KEY = os.getenv("GROQ_API_KEY")
+GROQ_API_KEY = os.getenv("GROQ_API_KEY", "").strip()
+
 if not GROQ_API_KEY:
-    raise ValueError("Missing GROQ_API_KEY. Set it in Hugging Face Secrets or .env.")
+    raise ValueError("Missing GROQ_API_KEY. Set it in your environment or Hugging Face secrets.")
 
-# GROQ API setup
+# API Config
 GROQ_API_URL = "https://api.groq.com/openai/v1/chat/completions"
 MODEL = "llama3-8b-8192"
-
-headers = {
-    "Authorization": f"Bearer {GROQ_API_KEY.strip()}",
+HEADERS = {
+    "Authorization": f"Bearer {GROQ_API_KEY}",
     "Content-Type": "application/json"
 }
 
-# Core logic for handling chatbot responses
-def echo(message, history):
-    messages = [
-        {
-            "role": "system",
-            "content": (
-                "You are an expert AI tutor. Answer student questions clearly and in short, "
-                "bite-sized explanations. Avoid jargon. Be patient and helpful like a good teacher."
-            )
-        }
-    ]
+# Core chatbot logic
+def chat(message, history):
+    messages = [{"role": "system", "content": "You are an expert AI tutor. Answer each question simply and clearly, using short and beginner-friendly explanations."}]
 
-    # Add chat history for context
-    for user_msg, bot_reply in history:
+    # Add full chat history
+    for user_msg, bot_msg in history:
         messages.append({"role": "user", "content": user_msg})
-        messages.append({"role": "assistant", "content": bot_reply})
+        messages.append({"role": "assistant", "content": bot_msg})
 
+    # Add latest user message
     messages.append({"role": "user", "content": message})
 
+    # Call Groq API
     try:
         response = requests.post(
             GROQ_API_URL,
-            headers=headers,
+            headers=HEADERS,
             json={
                 "model": MODEL,
-                "messages": messages
+                "messages": messages,
+                "temperature": 0.5,
+                "max_tokens": 500
             }
         )
-
-        if response.status_code == 200:
-            return response.json()["choices"][0]["message"]["content"]
-        else:
-            return f"❌ Error: {response.status_code}\n{response.text}"
+        response.raise_for_status()
+        reply = response.json()["choices"][0]["message"]["content"]
+        return reply
     except Exception as e:
-        return f"⚠️ Exception: {str(e)}"
+        return f"❌ Error: {str(e)}"
 
-# Gradio UI setup
+# Gradio UI
 demo = gr.ChatInterface(
-    fn=echo,
-    type="messages",
-    return_messages=True,
-    title="🤖 LLM Mentor - Your AI Tutor",
-    examples=[
-        "What is a language model?",
-        "How does machine learning work?",
-        "Explain RAG in simple terms.",
-        "What is fine-tuning?"
-    ],
-    description=(
-        "Ask me anything about LLMs, NLP, or AI! I'll explain in short, simple steps. "
-        "Great for beginners trying to learn how language models work."
-    )
+    fn=chat,
+    title="🧠 LLM Mentor",
+    description="Learn about LLMs, NLP, and AI with clear, short answers from your friendly tutor.",
+    examples=["What is a language model?", "Explain NLP in simple words", "How does RAG work?"],
+    theme="soft",
 )
 
-# Hugging Face Spaces fix
+# Disable SSR to prevent Hugging Face crash
 demo.launch(ssr_mode=False)
 
+