Update app.py

app.py

@@ -1,19 +1,9 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 
-# Alpaca-style prompt format
-ALPACA_PROMPT = """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
-
-### Instruction:
-{instruction}
-
-### Input:
-{input}
-
-### Response:
 """
-
-# Initialize Hugging Face Inference Client
+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("Futuresony/future_ai_12_10_2024.gguf")
 
 
@@ -25,22 +15,18 @@ def respond(
     temperature,
     top_p,
 ):
-    """Formats messages into Alpaca-style prompts and sends them to the model."""
     messages = [{"role": "system", "content": system_message}]
 
-    for user_msg, bot_msg in history:
-        if user_msg:
-            messages.append({"role": "user", "content": user_msg})
-        if bot_msg:
-            messages.append({"role": "assistant", "content": bot_msg})
+    for val in history:
+        if val[0]:
+            messages.append({"role": "user", "content": val[0]})
+        if val[1]:
+            messages.append({"role": "assistant", "content": val[1]})
 
-    # Apply Alpaca-style formatting
-    formatted_message = ALPACA_PROMPT.format(instruction=system_message, input=message)
-    messages.append({"role": "user", "content": formatted_message})
+    messages.append({"role": "user", "content": message})
 
     response = ""
-    
-    # Send request to the inference API
+
     for message in client.chat_completion(
         messages,
         max_tokens=max_tokens,
@@ -49,22 +35,30 @@ def respond(
         top_p=top_p,
     ):
         token = message.choices[0].delta.content
+
         response += token
         yield response
 
 
-# Gradio ChatInterface
+"""
+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 helpful AI assistant.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max tokens"),
+        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)"
+            minimum=0.1,
+            maximum=1.0,
+            value=0.95,
+            step=0.05,
+            label="Top-p (nucleus sampling)",
         ),
     ],
 )
 
+
 if __name__ == "__main__":
     demo.launch()