Update app.py

app.py

@@ -2,67 +2,53 @@ import gradio as gr
 from huggingface_hub import InferenceClient
 import os
 
-"""
-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(
     model="HuggingFaceH4/zephyr-7b-beta",
     token=os.getenv('HF_TOKEN')
 )
 
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
+def chat_fn(message, system_message, history_str, max_tokens, temperature, top_p):
+    # Convert history string (optional) to message list
     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]})
-
+    
+    if history_str:
+        # Format: user1||assistant1\nuser2||assistant2
+        for pair in history_str.split("\n"):
+            if "||" in pair:
+                user_msg, assistant_msg = pair.split("||", 1)
+                messages.append({"role": "user", "content": user_msg})
+                messages.append({"role": "assistant", "content": assistant_msg})
+    
     messages.append({"role": "user", "content": message})
 
+    # Get response from HF
     response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
+    for chunk in client.chat_completion(
+        messages=messages,
         stream=True,
+        max_tokens=max_tokens,
         temperature=temperature,
         top_p=top_p,
     ):
-        token = message.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
-"""
-demo = gr.ChatInterface(
-    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"),
+        response += chunk.choices[0].delta.content or ""
+    
+    return response
+
+demo = gr.Interface(
+    fn=chat_fn,
+    inputs=[
+        gr.Textbox(lines=2, label="User Message"),
+        gr.Textbox(value="You are a friendly Chatbot.", label="System Prompt"),
+        gr.Textbox(lines=4, placeholder="user||bot\nuser2||bot2", label="Conversation History (optional)"),
+        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max 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)",
-        ),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p"),
     ],
+    outputs="text",
+    allow_flagging="never",
+    title="LLM Budaya",
+    description="Chatbot menggunakan model HuggingFace Zephyr-7B"
 )
 
-
 if __name__ == "__main__":
     demo.launch()