Update app.py

app.py

@@ -1,7 +1,6 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 
-
 def respond(
     message,
     history: list[dict[str, str]],
@@ -11,43 +10,55 @@ def respond(
     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="huihui-ai/Llama-3.3-70B-Instruct-abliterated-finetuned")
+    # التأكد من وجود التوكن
+    if hf_token is None or hf_token.token is None:
+        yield "يرجى تسجيل الدخول عبر Hugging Face لتتمكن من استخدام النموذج."
+        return
 
-    messages = [{"role": "system", "content": system_message}]
+    # تحديد الموديل والتوكن
+    client = InferenceClient(
+        model="huihui-ai/Llama-3.3-70B-Instruct-abliterated-finetuned", 
+        token=hf_token.token
+    )
 
-    messages.extend(history)
+    # بناء قائمة الرسائل
+    messages = [{"role": "system", "content": system_message}]
+    
+    # تحويل التاريخ إلى التنسيق المطلوب إذا لم يكن كذلك
+    for interaction in history:
+        if isinstance(interaction, dict):
+            messages.append(interaction)
+        elif isinstance(interaction, (list, tuple)):
+            messages.append({"role": "user", "content": interaction[0]})
+            messages.append({"role": "assistant", "content": interaction[1]})
 
     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
+    try:
+        # استخدام chat_completion مع معالجة حذرة للـ Generator
+        for chunk in client.chat_completion(
+            messages,
+            max_tokens=max_tokens,
+            stream=True,
+            temperature=temperature,
+            top_p=top_p,
+        ):
+            # الوصول الآمن للمحتوى لتجنب StopIteration أو AttributeError
+            if chunk.choices and chunk.choices[0].delta.content:
+                token = chunk.choices[0].delta.content
+                response += token
+                yield response
+    except Exception as e:
+        # صرخة في وجه الخطأ بدل الصمت المطبق
+        yield f"عذراً يوسف، حدث تمزق في نسيج الكود: {str(e)}"
 
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-chatbot = gr.ChatInterface(
+# إعداد واجهة Gradio (تأكد من وجود هذه الأجزاء في ملفك)
+demo = gr.ChatInterface(
     respond,
-    type="messages",
     additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        gr.Textbox(value="You are a helpful assistant.", 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(
@@ -60,11 +71,5 @@ chatbot = gr.ChatInterface(
     ],
 )
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
-
-
 if __name__ == "__main__":
     demo.launch()