Update app.py

app.py

@@ -1,25 +1,31 @@
 from huggingface_hub import InferenceClient
 import gradio as gr
+
+
+# Import required libraries
 from pathlib import Path
 
 # Initialize the InferenceClient
-client = InferenceClient(
-    "mistralai/Mixtral-8x7B-Instruct-v0.1"
-)
+client = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.1")
 
-def format_prompt(message, history, system_prompt):
+def format_prompt(message, history):
+    """
+    Format the prompt by appending the user's message and the system prompt to the conversation history.
+    """
     prompt = "<s>"
     for user_prompt, bot_response in history:
         prompt += f"[INST] {user_prompt} [/INST]"
         prompt += f" {bot_response}</s> "
     prompt += f"[INST] {message} [/INST]"
-    # Add the system prompt only once at the beginning
     prompt = system_prompt + prompt
     return prompt
 
 def generate(
     prompt, history, user_system_prompt, temperature=0.9, max_new_tokens=9048, top_p=0.95, repetition_penalty=1.0
 ):
+    """
+    Generate a response using the InferenceClient.
+    """
     system_prompt = "Instructions: Everything else is from the user. You are Milo, an AI assistant created by ConvoLite in 2024 (he/him). Be friendly and empathetic, matching the user's tone and vibe. Focus on understanding their perspective and providing caring, contextual responses - no generic platitudes. Keep it conversational, not overly formal. Be friendly and funny, use ASCII emojis or normal ones. Be lovely, kind, and have a great sense of humour. Have Bible based values. Do not talk about yourself unless asked. Never respond to a message with 'as an AI' or something similar. Don't talk a lot!" + str(user_system_prompt)
 
     temperature = float(temperature)
@@ -27,6 +33,8 @@ def generate(
         temperature = 1e-2
 
     top_p = float(top_p)
+
+    # Set generate_kwargs for text generation
     generate_kwargs = dict(
         temperature=temperature,
         max_new_tokens=max_new_tokens,
@@ -38,14 +46,15 @@ def generate(
 
     formatted_prompt = format_prompt(f"{prompt}", history, system_prompt)
 
+    # Generate text stream
     stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
 
-    output_text = ""
+    output = ""
     for response in stream:
-        output_text += response.token.text
-        yield output_text, history  # Yield the updated output_text and the updated history
-    yield output
+        output += response.token.text
+        yield output
 
+# Define additional input components
 additional_inputs = [
     gr.Textbox(label="System Prompt", max_lines=1, interactive=True),
     gr.Slider(label="Temperature", value=0.9, minimum=0.0, maximum=1.0, step=0.05, interactive=True, info="Higher values produce more diverse outputs"),
@@ -54,8 +63,10 @@ additional_inputs = [
     gr.Slider(label="Repetition penalty", value=1.2, minimum=1.0, maximum=2.0, step=0.05, interactive=True, info="Penalize repeated tokens")
 ]
 
+# Define avatar images
 avatar_images = ("https://i.postimg.cc/pXjKKVXG/user-circle.png", "https://i.postimg.cc/qq04Yz93/CL3.png")
 
+# Create Gradio interface
 gr.ChatInterface(
     fn=generate,
     chatbot=gr.Chatbot(show_label=True, show_share_button=False, show_copy_button=True, likeable=True, layout="panel", height="auto", avatar_images=avatar_images),