Update app.py

app.py

@@ -1,32 +1,27 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 
+# Initialize the InferenceClient
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
-
 def respond(
     message,
-    history: list[tuple[str, str]],
+    history: list[dict],  # Use a list of dictionaries instead of tuples
     system_message,
     max_tokens,
     temperature,
     top_p,
 ):
-    # Prepare messages for the API
     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]})
+        messages.append({"role": val['role'], "content": val['content']})
 
     messages.append({"role": "user", "content": message})
 
-    # Initialize response variable
     response = ""
-
-    # Call the InferenceClient with chat_completion
+    
+    # Use chat_completion to get responses
     for message in client.chat_completion(
         messages,
         max_tokens=max_tokens,
@@ -38,11 +33,12 @@ def respond(
         response += token
         yield response
 
-
-# Create the Gradio ChatInterface
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
+# Create the Gradio Interface for API
+api_interface = gr.Interface(
+    fn=respond,
+    inputs=[
+        gr.Textbox(label="Message"),
+        gr.JSON(label="History"),
         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"),
@@ -54,8 +50,9 @@ demo = gr.ChatInterface(
             label="Top-p (nucleus sampling)",
         ),
     ],
+    outputs=gr.Textbox(label="Response"),
 )
 
-# Launch the Gradio app and enable API
+# Launch the API
 if __name__ == "__main__":
-    demo.launch(share=True, enable_queue=True)  # Set to True to share on Hugging Face Spaces
+    api_interface.launch(server_name="0.0.0.0", server_port=7860, share=False)  # Set share=False to avoid Hugging Face Spaces