Update app.py

app.py

@@ -1,48 +1,40 @@
-import os
 import gradio as gr
 from huggingface_hub import InferenceClient
 
-# قراءة توكن Hugging Face API من متغير البيئة
-API_TOKEN = os.getenv("HF_API_TOKEN")
-if not API_TOKEN:
-    raise ValueError("Please set the HF_API_TOKEN environment variable with your Hugging Face API token.")
+# لاحظ: يجب تمرير التوكن بطريقة أخرى، مثلاً عبر متغير بيئة أو إعدادات المساحة
+# هنا ننشئ العميل بدون توكن (إذا النموذج يسمح)
+client = InferenceClient("mradermacher/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp-GGUF")
 
-# إنشاء عميل InferenceClient مع نموذج DeepSeek ومفتاح API
-client = InferenceClient("Llama-3.2-3B-Instruct-GGUF", token=API_TOKEN)
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
+def respond(messages, system_message, max_tokens, temperature, top_p):
+    chat_messages = [{"role": "system", "content": system_message}] + messages
 
     response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
+    prompt = ""
+    for msg in chat_messages:
+        role = msg.get("role", "")
+        content = msg.get("content", "")
+        if role == "system":
+            prompt += f"System: {content}\n"
+        elif role == "user":
+            prompt += f"User: {content}\n"
+        elif role == "assistant":
+            prompt += f"Assistant: {content}\n"
+    prompt += "Assistant: "
+
+    generation = client.text_generation(
+        prompt,
+        max_new_tokens=max_tokens,
         temperature=temperature,
         top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-        response += token
+        stream=True,
+    )
+
+    for token in generation:
+        response += token.text
         yield response
 
 demo = gr.ChatInterface(
-    respond,
+    fn=respond,
     additional_inputs=[
         gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
@@ -55,6 +47,7 @@ demo = gr.ChatInterface(
             label="Top-p (nucleus sampling)",
         ),
     ],
+    type="messages",
 )
 
 if __name__ == "__main__":