Update app.py

app.py

@@ -1,7 +1,8 @@
+#refer llama recipes for more info https://github.com/huggingface/huggingface-llama-recipes/blob/main/inference-api.ipynb
+#huggingface-llama-recipes : https://github.com/huggingface/huggingface-llama-recipes/tree/main
 import gradio as gr
 from openai import OpenAI
 import os
-import json
 
 css = '''
 .gradio-container{max-width: 1000px !important}
@@ -11,31 +12,13 @@ footer {
 }
 '''
 
-# Access token for Hugging Face
 ACCESS_TOKEN = os.getenv("HF_TOKEN")
 
-# Initialize the client for the OpenAI model
 client = OpenAI(
     base_url="https://api-inference.huggingface.co/v1/",
     api_key=ACCESS_TOKEN,
 )
 
-# File path for storing user preferences
-USER_DATA_PATH = "user_data.json"
-
-# Load user preferences if they exist
-def load_user_preferences():
-    if os.path.exists(USER_DATA_PATH):
-        with open(USER_DATA_PATH, "r") as file:
-            return json.load(file)
-    return {}
-
-# Save user preferences
-def save_user_preferences(data):
-    with open(USER_DATA_PATH, "w") as file:
-        json.dump(data, file)
-
-# Respond function that generates the assistant's reply
 def respond(
     message,
     history: list[tuple[str, str]],
@@ -44,36 +27,6 @@ def respond(
     temperature,
     top_p,
 ):
-    # Load user preferences
-    user_data = load_user_preferences()
-
-    # Custom welcome message or save user input
-    if message.lower().startswith("my name is"):
-        user_data["name"] = message.split("is")[-1].strip()
-        save_user_preferences(user_data)
-        response = f"Nice to meet you, {user_data['name']}! How can I assist you with your travel plans today?"
-        yield response
-        return
-
-    if message.lower().startswith("i like to travel to"):
-        user_data["favorite_destination"] = message.split("to")[-1].strip()
-        save_user_preferences(user_data)
-        response = f"Got it! I noted that you enjoy traveling to {user_data['favorite_destination']}."
-        yield response
-        return
-
-    if message.lower().startswith("my budget is"):
-        user_data["budget"] = message.split("is")[-1].strip()
-        save_user_preferences(user_data)
-        response = f"Understood! I'll keep your budget of {user_data['budget']} in mind when suggesting travel options."
-        yield response
-        return
-
-    # Use user's name and preferences in responses if available
-    name = user_data.get("name", "Traveler")
-    favorite_destination = user_data.get("favorite_destination", "various places")
-    budget = user_data.get("budget", "not specified")
-
     messages = [{"role": "system", "content": system_message}]
 
     for val in history:
@@ -82,13 +35,11 @@ def respond(
         if val[1]:
             messages.append({"role": "assistant", "content": val[1]})
 
-    # Add the current user message
     messages.append({"role": "user", "content": message})
 
-    response = f"Hello {name}! You mentioned you like traveling to {favorite_destination}. Let's plan something exciting within your budget of {budget}.\n"
-
-    # Generate a response using the OpenAI client
-    for message in client.chat.completions.create(
+    response = ""
+    
+    for message in  client.chat.completions.create(
         model="meta-llama/Meta-Llama-3.1-8B-Instruct",
         max_tokens=max_tokens,
         stream=True,
@@ -97,17 +48,14 @@ def respond(
         messages=messages,
     ):
         token = message.choices[0].delta.content
+        
         response += token
         yield response
 
-# Gradio interface
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
-        gr.Textbox(
-            value="You are a friendly travel assistant. Offer personalized travel tips and remember user preferences.",
-            label="System message"
-        ),
+        gr.Textbox(value="", 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(
@@ -117,10 +65,10 @@ demo = gr.ChatInterface(
             step=0.05,
             label="Top-P",
         ),
+        
     ],
     css=css,
     theme="allenai/gradio-theme",
 )
-
 if __name__ == "__main__":
     demo.launch()