Update app.py

app.py

@@ -1,7 +1,7 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 
-# Your tokens (replace with real ones)
+# Your model + tokens
 HF_TOKENS = [
     "hf_token_1",
     "hf_token_2",
@@ -35,30 +35,29 @@ def chat_with_magana(user_input, history=None):
     global client
     if history is None:
         history = []
+
+    # Convert history into a conversation string
+    conversation = "System: You are Magana AI, an intelligent Hausa-first AI assistant.\n"
+    for user, bot in history:
+        conversation += f"User: {user}\nMaganaAI: {bot}\n"
+    conversation += f"User: {user_input}\nMaganaAI:"
+
     for attempt in range(len(HF_TOKENS)):
         try:
-            completion = client.chat_completion(
-                model=MODEL,
-                messages=[
-                    {
-                        "role": "system",
-                        "content": (
-                            "You are Magana AI, an intelligent Hausa-first AI assistant. "
-                            "Always greet in Hausa first, then continue in Hausa or English depending on user preference. "
-                            "Be clear, simple, friendly. Respect Hausa culture with proverbs/greetings. "
-                            "If you don’t know something, say so honestly. Default in Hausa unless asked for English. "
-                            "Origin: Developed by Ahmad Garba Adamu from Kano."
-                        )
-                    },
-                    {"role": "user", "content": user_input}
-                ]
+            output = client.text_generation(
+                MODEL,
+                conversation,
+                max_new_tokens=300,
+                temperature=0.7,
+                do_sample=True
             )
-            reply = completion["choices"][0]["message"]["content"]
+            reply = output.strip()
             history.append((user_input, reply))
             return history, reply
         except Exception as e:
             print("⚠️ Error:", e)
             switch_token()
+
     return history, "❌ All tokens failed."
 
 # ------------------------------
@@ -70,7 +69,7 @@ init_client(0)
 # Gradio UI
 # ------------------------------
 with gr.Blocks() as demo:
-    chatbot = gr.Chatbot()
+    chatbot = gr.Chatbot(type="messages")  # 👈 updated to messages format
     msg = gr.Textbox(placeholder="Type your message here...")
     clear = gr.Button("Clear")