Update app.py

app.py

@@ -3,7 +3,10 @@ import gradio as gr
 from huggingface_hub import InferenceClient
 
 MODEL_ID = "MiniMaxAI/MiniMax-M2.5"
-SYSTEM_PROMPT = "You are a helpful assistant. Your name is MiniMax-M2.5 and is built by MiniMax."
+SYSTEM_PROMPT = (
+    "You are a helpful assistant. "
+    "Your name is MiniMax-M2.5 and is built by MiniMax."
+)
 
 client = InferenceClient(
     provider="novita",
@@ -14,11 +17,14 @@ client = InferenceClient(
 def respond(message, history, system_message, max_tokens, temperature, top_p):
     messages = [{"role": "system", "content": system_message}]
 
-    for user_msg, assistant_msg in history:
-        if user_msg:
-            messages.append({"role": "user", "content": user_msg})
-        if assistant_msg:
-            messages.append({"role": "assistant", "content": assistant_msg})
+    # history در نسخه‌های جدید Gradio به صورت لیست دیکشنری است
+    for msg in history:
+        messages.append(
+            {
+                "role": msg["role"],
+                "content": msg["content"],
+            }
+        )
 
     messages.append({"role": "user", "content": message})
 
@@ -26,28 +32,53 @@ def respond(message, history, system_message, max_tokens, temperature, top_p):
     for chunk in client.chat_completion(
         model=MODEL_ID,
         messages=messages,
-        max_tokens=max_tokens,
+        max_tokens=int(max_tokens),
+        temperature=float(temperature),
+        top_p=float(top_p),
         stream=True,
-        temperature=temperature,
-        top_p=top_p,
     ):
-        if chunk.choices and chunk.choices[0].delta.content:
-            response += chunk.choices[0].delta.content
-            yield response
+        if chunk.choices:
+            delta = chunk.choices[0].delta
+            if delta and delta.content:
+                response += delta.content
+                yield response
 
 
 demo = gr.ChatInterface(
-    respond,
+    fn=respond,
+    type="messages",  # مهم
     title="MiniMax M2.5 Chat",
     description=(
-        "Chat with [MiniMax M2.5](https://huggingface.co/MiniMaxAI/MiniMax-M2.5) — "
-        "a 230B MoE model (10B active) that is SOTA in coding, agentic tool use, and more."
+        "Chat with MiniMax M2.5 — "
+        "a 230B MoE model (10B active) that is SOTA in coding, "
+        "agentic tool use, and more."
     ),
     additional_inputs=[
-        gr.Textbox(value=SYSTEM_PROMPT, label="System message"),
-        gr.Slider(minimum=1, maximum=4096, value=2048, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=2.0, value=1.0, step=0.05, label="Temperature"),
-        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p"),
+        gr.Textbox(
+            value=SYSTEM_PROMPT,
+            label="System message",
+        ),
+        gr.Slider(
+            minimum=1,
+            maximum=4096,
+            value=2048,
+            step=1,
+            label="Max new tokens",
+        ),
+        gr.Slider(
+            minimum=0.1,
+            maximum=2.0,
+            value=1.0,
+            step=0.05,
+            label="Temperature",
+        ),
+        gr.Slider(
+            minimum=0.1,
+            maximum=1.0,
+            value=0.95,
+            step=0.05,
+            label="Top-p",
+        ),
     ],
     examples=[
         ["Write a Python function to check if a number is prime."],
@@ -57,5 +88,6 @@ demo = gr.ChatInterface(
     cache_examples=False,
 )
 
+
 if __name__ == "__main__":
     demo.launch()