Update app.py

app.py

@@ -1,9 +1,29 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+import logging
+from datetime import datetime
 
 # Initialize the InferenceClient with the model ID from Hugging Face
 client = InferenceClient(model="HuggingFaceH4/zephyr-7b-beta")
 
+# Set up logging
+logging.basicConfig(
+    filename='chatbot_log.log',
+    level=logging.INFO,
+    format='%(asctime)s - %(levelname)s - %(message)s',
+)
+
+def log_conversation(user_message, bot_response):
+    """
+    Logs the conversation between the user and the AI.
+    
+    Args:
+        user_message (str): The user's input message.
+        bot_response (str): The AI's response.
+    """
+    logging.info(f"User: {user_message}")
+    logging.info(f"Bot: {bot_response}")
+
 def respond(
     message: str,
     history: list[tuple[str, str]],
@@ -11,6 +31,8 @@ def respond(
     max_tokens: int,
     temperature: float,
     top_p: float,
+    stop_sequence: str,
+    stream_response: bool,
 ):
     """
     Generates a response from the AI model based on the user's message and chat history.
@@ -22,6 +44,8 @@ def respond(
         max_tokens (int): The maximum number of tokens for the output.
         temperature (float): Sampling temperature for controlling the randomness.
         top_p (float): Top-p (nucleus sampling) for controlling diversity.
+        stop_sequence (str): A custom stop sequence to end the response generation.
+        stream_response (bool): Whether to stream the response or return it as a whole.
 
     Yields:
         str: The AI's response as it is generated.
@@ -43,20 +67,37 @@ def respond(
     response = ""
 
     try:
-        # Generate a response from the model with streaming
-        for message in client.chat_completion(
-            messages=messages,
-            max_tokens=max_tokens,
-            stream=True,
-            temperature=temperature,
-            top_p=top_p,
-        ):
-            token = message.choices[0].delta.get("content", "")
-            response += token
+        if stream_response:
+            # Generate a response from the model with streaming
+            for message in client.chat_completion(
+                messages=messages,
+                max_tokens=max_tokens,
+                stream=True,
+                temperature=temperature,
+                top_p=top_p,
+                stop=stop_sequence,
+            ):
+                token = message.choices[0].delta.get("content", "")
+                response += token
+                yield response
+        else:
+            # Generate a complete response without streaming
+            result = client.chat_completion(
+                messages=messages,
+                max_tokens=max_tokens,
+                stream=False,
+                temperature=temperature,
+                top_p=top_p,
+                stop=stop_sequence,
+            )
+            response = result.choices[0].message.get("content", "")
+            log_conversation(message, response)
             yield response
 
     except Exception as e:
-        yield f"An error occurred: {str(e)}"
+        error_message = f"An error occurred: {str(e)}"
+        logging.error(error_message)
+        yield error_message
 
 # Define the ChatInterface with additional input components for user customization
 demo = gr.ChatInterface(
@@ -66,11 +107,17 @@ demo = gr.ChatInterface(
         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max New Tokens"),
         gr.Slider(minimum=0.1, maximum=2.0, 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.Textbox(value="", label="Stop Sequence (optional)", lines=1),
+        gr.Checkbox(label="Stream Response", value=True),
     ],
     title="AI Chatbot Interface",
     description="Interact with an AI chatbot powered by Hugging Face's Zephyr-7B model. Customize the chatbot's behavior and response generation settings.",
+    theme="default",
+    allow_flagging="never",
 )
 
 # Launch the Gradio interface
 if __name__ == "__main__":
+    logging.info("Launching the Gradio interface...")
     demo.launch()
+    logging.info("Gradio interface launched successfully.")