update UI/UX

app.py

@@ -1,10 +1,12 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+import requests
+import json
+
+MODAL_ENDPOINT = "https://kim-ju-won--llama3-70b-chat.modal.run/llama3_chat_endpoint"
 
 """
 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")
 
 def create_system_prompt(agent_type, personality, expertise_level, language):
     base_prompt = f"""You are a {agent_type} movie recommendation agent with the following characteristics:
@@ -37,30 +39,44 @@ def respond(
 ):
     # Create system prompt
     system_message = create_system_prompt(agent_type, personality, expertise_level, language)
+    
+    # Prepare messages for the API
     messages = [{"role": "system", "content": system_message}]
-
-    # Add genre and mood information to user input
-    enhanced_message = f"Genre: {genre}\nMood: {mood}\nUser request: {message}"
     
+    # Add conversation history
     for val in history:
         if val[0]:
             messages.append({"role": "user", "content": val[0]})
         if val[1]:
             messages.append({"role": "assistant", "content": val[1]})
-
+    
+    # Add current message with genre and mood
+    enhanced_message = f"Genre: {genre}\nMood: {mood}\nUser request: {message}"
     messages.append({"role": "user", "content": enhanced_message})
-
-    response = ""
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-        response += token
-        yield response
+    
+    # Prepare request payload
+    payload = {
+        "messages": messages,
+        "max_tokens": max_tokens,
+        "temperature": temperature,
+        "top_p": top_p
+    }
+    
+    try:
+        # Send request to Modal endpoint
+        response = requests.post(
+            MODAL_ENDPOINT,
+            json=payload,
+            headers={"Content-Type": "application/json"}
+        )
+        response.raise_for_status()
+        
+        # Get response from Modal
+        result = response.json()
+        return result.get("response", "Sorry, I couldn't process your request.")
+        
+    except Exception as e:
+        return f"Error: {str(e)}"
 
 def reset_chat():
     return None
@@ -103,7 +119,7 @@ with gr.Blocks() as demo:
                     container=False
                 )
                 with gr.Row():
-                    submit = gr.Button("Get Recommendations", variant="primary", size="sm")
+                    submit = gr.Button("Send Chat", variant="primary", size="sm")
                     clear = gr.Button("Clear Chat", size="sm")
         
         with gr.Column(scale=1):