Update app.py

app.py

@@ -2,9 +2,7 @@ import gradio as gr
 from huggingface_hub import InferenceClient
 from transformers import pipeline
 
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
+# Define the respond function
 def respond(
     message,
     history: list[tuple[str, str]],
@@ -13,30 +11,30 @@ def respond(
     temperature,
     top_p,
 ):
+    # Define the initial message for the chat
     messages = [
-    {"role": "user", "content": "Who are you?"},
-]
-pipe = pipeline("text-generation", model="codefuse-ai/CodeFuse-DeepSeek-33B")
-pipe(messages)
-
-response = ""
-
+        {"role": "user", "content": message},
+    ]
+    
+    # Create a pipeline for text generation
+    pipe = pipeline("text-generation", model="codefuse-ai/CodeFuse-DeepSeek-33B")
+    pipe(messages)
+
+    response = ""
+    
+    # Use the InferenceClient to get responses
     for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
+            messages,
+            max_tokens=max_tokens,
+            stream=True,
+            temperature=temperature,
+            top_p=top_p,
+        ):
         token = message.choices[0].delta.content
-
         response += token
         yield response
 
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# Setup Gradio interface
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
@@ -53,6 +51,6 @@ demo = gr.ChatInterface(
     ],
 )
 
-
+# Launch the Gradio app
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()