Update app.py

app.py

@@ -1,70 +1,95 @@
+# app.py
+# GPT Chatbot powered by HuggingFace Inference API
+# Clean, safe, production-ready for Hugging Face Spaces
+
+import os
+import time
 import gradio as gr
 from huggingface_hub import InferenceClient
 
+# -----------------------
+# Configuration
+# -----------------------
+HF_TOKEN = os.getenv("HF_API_TOKEN")
+GPT_MODEL_ID = os.getenv("GPT_MODEL_ID", "HuggingFaceH4/zephyr-7b-beta")
+
+if HF_TOKEN is None:
+    raise ValueError("❌ Please define HF_API_TOKEN in Hugging Face Secrets.")
+
+# Create inference client
+client = InferenceClient(
+    model=GPT_MODEL_ID,
+    token=HF_TOKEN,
+)
 
-def respond(
-    message,
-    history: list[dict[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-    hf_token: gr.OAuthToken,
-):
+# -----------------------
+# Chatbot Core
+# -----------------------
+def gpt_chat(prompt: str, history, thinking_mode=False, thinking_time=2.0):
     """
-    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
+    Generate a chat response using GPT model on HuggingFace Inference API.
+    Clean, without chain-of-thought exposure.
     """
-    client = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b")
-
-    messages = [{"role": "system", "content": system_message}]
-
-    messages.extend(history)
-
-    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
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-chatbot = gr.ChatInterface(
-    respond,
-    type="messages",
-    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"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
+    if not prompt.strip():
+        return history, "لطفاً پیام بنویسید."
+
+    # Optional "thinking" simulation
+    if thinking_mode:
+        time.sleep(thinking_time)
+
+    try:
+        # Build clean conversation prompt
+        conversation_text = ""
+        for user_msg, bot_msg in history:
+            conversation_text += f"User: {user_msg}\nAssistant: {bot_msg}\n"
+        conversation_text += f"User: {prompt}\nAssistant:"
+
+        # Query HuggingFace API
+        response = client.text_generation(
+            prompt=conversation_text,
+            max_new_tokens=200,
+            temperature=0.7,
+            do_sample=True,
+        )
+
+        # Clean output
+        answer = response.replace(conversation_text, "").strip()
+        answer = answer.split("Assistant:")[-1].strip()
+
+        # Update history
+        history.append((prompt, answer))
+        return history, "OK"
+
+    except Exception as e:
+        print("Error:", e)
+        history.append((prompt, "⚠ خطا در ارتباط با مدل."))
+        return history, str(e)
+
+# -----------------------
+# Gradio UI
+# -----------------------
+with gr.Blocks(title="GPT Chatbot") as demo:
+    gr.Markdown("""
+    # 🤖 GPT Chatbot (HuggingFace Inference API)
+    مدل: **{GPT_MODEL_ID}**
+    
+    این چت‌بات از API رسمی هاگینگ‌فیس استفاده می‌کند.
+    """)
+
+    chatbot = gr.Chatbot(label="Chat")
+    user_input = gr.Textbox(placeholder="پیام خود را بنویسید...", show_label=False)
+    thinking_mode = gr.Checkbox(label="حالت فکر کردن", value=True)
+    thinking_time = gr.Slider(0, 5, value=2, step=0.5, label="مدت فکر کردن (ثانیه)")
+    status_box = gr.Textbox(label="وضعیت")
+
+    def respond(history, msg, thinking, thinking_t):
+        return gpt_chat(msg, history, thinking, thinking_t)
 
+    user_input.submit(
+        respond,
+        inputs=[chatbot, user_input, thinking_mode, thinking_time],
+        outputs=[chatbot, status_box]
+    )
 
-if __name__ == "__main__":
-    demo.launch()
+demo.launch()