g

app.py

@@ -1,33 +1,51 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 
-"""
-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")
+
+SYSTEM_MESSAGE_DEFAULT = "You are a friendly Chatbot."
+MAX_TOKENS_DEFAULT = 512
+TEMPERATURE_DEFAULT = 0.7
+TOP_P_DEFAULT = 0.95
+
+
+inference_client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
 
 def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
+    user_message: str,
+    conversation_history: list[tuple[str, str]],
+    system_message: str,
+    max_tokens: int,
+    temperature: float,
+    top_p: float,
+) -> str:
+    """
+    Respond to a user message given the conversation history and other parameters.
+
+    Args:
+        user_message (str): The user's message.
+        conversation_history (list[tuple[str, str]]): The conversation history.
+        system_message (str): The system message to display at the top of the chat interface.
+        max_tokens (int): The maximum number of tokens to generate in the response.
+        temperature (float): The temperature to use when generating text.
+        top_p (float): The top-p value to use when generating text.
+
+    Returns:
+        str: The response to the user's message.
+    """
     messages = [{"role": "system", "content": system_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]})
+    for user_input, assistant_response in conversation_history:
+        if user_input:
+            messages.append({"role": "user", "content": user_input})
+        if assistant_response:
+            messages.append({"role": "assistant", "content": assistant_response})
 
-    messages.append({"role": "user", "content": message})
+    messages.append({"role": "user", "content": user_message})
 
     response = ""
 
-    for message in client.chat_completion(
+    for message in inference_client.chat_completion(
         messages,
         max_tokens=max_tokens,
         stream=True,
@@ -39,20 +57,33 @@ def respond(
         response += token
         yield response
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
+
+chatbot_interface = gr.ChatInterface(
+    fn=respond,
     chatbot=gr.Chatbot(height=600),
     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.Textbox(
+            value=SYSTEM_MESSAGE_DEFAULT,
+            label="System message",
+        ),
+        gr.Slider(
+            minimum=1,
+            maximum=2048,
+            value=MAX_TOKENS_DEFAULT,
+            step=1,
+            label="Max new tokens",
+        ),
+        gr.Slider(
+            minimum=0.1,
+            maximum=4.0,
+            value=TEMPERATURE_DEFAULT,
+            step=0.1,
+            label="Temperature",
+        ),
         gr.Slider(
             minimum=0.1,
             maximum=1.0,
-            value=0.95,
+            value=TOP_P_DEFAULT,
             step=0.05,
             label="Top-p (nucleus sampling)",
         ),
@@ -61,4 +92,4 @@ demo = gr.ChatInterface(
 
 
 if __name__ == "__main__":
-    demo.launch()
+    chatbot_interface.launch()