updated app.py to reflect fields

app.py

@@ -3,10 +3,6 @@ import torch
 import gradio as gr
 from transformers import pipeline
 
-"""
-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("HuggingFaceH4/zephyr-7b-beta")
 pipe = pipeline(
     model="gyulukeyi/llama3-nallm-qa-8B_240708",
     token=os.environ.get("hf_token"),
@@ -16,16 +12,16 @@ pipe = pipeline(
 
 
 def respond(
-    message,
-    history,
-    municipality,
+    지자체,
+    제목,
+    질문,
     max_tokens,
     temperature,
     top_p,
 ):
-    messages = [{"role": "municipality", "content": municipality}]
-    messages.append({"role": "title", "content": "민원"})
-    messages.append({"role": "question", "content": message})
+    messages = [{"role": "municipality", "content": 지자체}]
+    messages.append({"role": "title", "content": 제목})
+    messages.append({"role": "question", "content": 질문})
 
     output = pipe(
         messages,
@@ -34,22 +30,21 @@ def respond(
         return_full_text=False,
         top_p=top_p,
     )
+
     return output[0]["generated_text"]
 
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
+demo = gr.Interface(
     respond,
+    inputs=["textbox", "textbox", "textbox"],
+    outputs=["textbox"],
     additional_inputs=[
-        gr.Textbox(value="서울특별시", label="municipality"),
         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=1.0, value=0.5, step=0.05, label="Temperature"),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.4, step=0.05, label="Temperature"),
         gr.Slider(
             minimum=0.1,
             maximum=1.0,
-            value=0.95,
+            value=0.90,
             step=0.05,
             label="Top-p (nucleus sampling)",
         ),