Update app.py

app.py

@@ -1,10 +1,32 @@
+import os
 import gradio as gr
+from huggingface_hub import InferenceClient
 
-with gr.Blocks(fill_height=True) as demo:
-    with gr.Sidebar():
-        gr.Markdown("# Inference Provider")
-        gr.Markdown("This Space showcases the google/gemma-2-9b-it model, served by the featherless-ai API. Sign in with your Hugging Face account to use this API.")
-        button = gr.LoginButton("Sign in")
-    gr.load("models/google/gemma-2-9b-it", accept_token=button, provider="featherless-ai")
-    
-demo.launch()
+MODEL_NAME = "google/gemma-2-9b-it"
+HF_TOKEN = os.getenv("HF_TOKEN")
+
+client = InferenceClient(
+    model=MODEL_NAME,
+    token=HF_TOKEN
+)
+
+def chat(message, history):
+    messages = [{"role": "system", "content": "أنت مساعد ذكي."}]
+
+    for u, a in history:
+        if u:
+            messages.append({"role": "user", "content": u})
+        if a:
+            messages.append({"role": "assistant", "content": a})
+
+    messages.append({"role": "user", "content": message})
+
+    response = client.chat_completion(
+        messages=messages,
+        max_tokens=300
+    )
+
+    return response.choices[0].message["content"]
+
+demo = gr.ChatInterface(chat)
+demo.launch()