Update app.py

app.py

@@ -1,13 +1,30 @@
 import gradio as gr
-from transformers import pipeline
+from huggingface_hub import InferenceClient
 
-# මොඩල් එක මෙතනදී Load වෙනවා
-pipe = pipeline("text-generation", model="Qwen/Qwen2.5-1.5B-Instruct")
+# මෙහි ඔබේ Token එක කෙලින්ම ඇතුළත් කරන්න
+client = InferenceClient("Qwen/Qwen2.5-1.5B-Instruct", token="HF_TOKEN")
 
-def predict(message, history):
-    # AI පිළිතුර උත්පාදනය කිරීම
-    response = pipe(message, max_new_tokens=512)[0]['generated_text']
-    return response
+def respond(message, history):
+    messages = [{"role": "system", "content": "You are MINZO AI, a strategic assistant for Commander MINZO-PRIME."}]
+    
+    for val in history:
+        if val[0]: messages.append({"role": "user", "content": val[0]})
+        if val[1]: messages.append({"role": "assistant", "content": val[1]})
 
-# API එකක් ලෙස මෙය විවෘත කිරීම
-gr.ChatInterface(predict).launch()
+    messages.append({"role": "user", "content": message})
+
+    response = ""
+    for message in client.chat_completion(
+        messages,
+        max_tokens=1024,
+        stream=True,
+        temperature=0.7,
+    ):
+        token = message.choices[0].delta.content
+        response += token
+        yield response
+
+demo = gr.ChatInterface(respond)
+
+if __name__ == "__main__":
+    demo.launch()