Update app.py

app.py

@@ -4,64 +4,85 @@ from datasets import load_dataset
 import threading
 import time
 
-# Initialize the InferenceClient for Zephyr model
+"""
+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")
 
-# Function to load the latest dataset from Hugging Face
+
 def load_data():
     dataset = load_dataset("accesscreate012/abhinav-academy-chatbot", split="train")
     return {entry["instruction"]: entry["response"] for entry in dataset}
 
+
 # Global variable to store the dataset
 data = load_data()
 
-# Function to update dataset every 24 hours
+
 def auto_update():
     global data
     while True:
-        time.sleep(86400)  # Wait for 24 hours before refreshing dataset
+        time.sleep(86400)  # Wait for 24 hours before refreshing the dataset
         data = load_data()  # Reload the dataset
         print("Dataset updated.")
 
+
 # Start the auto-update thread (runs in the background)
 threading.Thread(target=auto_update, daemon=True).start()
 
-# Chatbot response function using the InferenceClient
-def respond(message, system_message, max_tokens, temperature, top_p):
-    # Prepare the message history for the model
+
+def respond(
+    message,
+    history: list[tuple[str, str]],
+    system_message,
+    max_tokens,
+    temperature,
+    top_p,
+):
     messages = [{"role": "system", "content": system_message}]
-    
-    # Add the new user 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]})
+
     messages.append({"role": "user", "content": message})
 
     response = ""
 
-    # Generate the response using the model
-    for msg in client.chat_completion(
+    for message in client.chat_completion(
         messages,
         max_tokens=max_tokens,
         stream=True,
         temperature=temperature,
         top_p=top_p,
     ):
-        token = msg.choices[0].delta.content
+        token = message.choices[0].delta.content
+
         response += token
-        yield response  # Streaming response
-
-# Gradio interface (using gr.Interface instead of gr.ChatInterface)
-demo = gr.Interface(
-    fn=respond,
-    inputs=[
-        gr.Textbox(label="User Message"),
-        gr.Textbox(value="You are a helpful chatbot.", label="System Message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max Tokens"),
+        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"),
         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 (nucleus sampling)",
+        ),
     ],
-    outputs=gr.Textbox(label="Chatbot Response"),  # Changed to Textbox to capture the response
-    live=True  # Enable live responses
 )
 
-# Launch the interface
+
 if __name__ == "__main__":
     demo.launch()