Update app.py

app.py

@@ -1,59 +1,72 @@
 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
+""" 
+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")
 
 
 def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
+	message, 
+    history: list[tuple[str, str]], 
+    system_message, 
+    max_tokens, 
+    temperature, 
+    top_p
 ):
-    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]})
+    try:
+        import json # Import json inside the function to avoid global import errors on spaces
+        data_received = {
+            "message": message,
+            "history": history,
+            "system_message": system_message,
+            "max_tokens": max_tokens,
+            "temperature": temperature,
+            "top_p": top_p,
+        }
+        print(json.dumps(data_received, indent=4))  # Pretty print it to the logs
 
-    messages.append({"role": "user", "content": 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]})
 
-    response = ""
+        messages.append({"role": "user", "content": message})
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+        response = ""
+        for message in client.chat_completion(
+            messages,
+            max_tokens=max_tokens,
+            stream=True,
+            temperature=temperature,
+            top_p=top_p,
+        ):
+            token = message.choices[0].delta.content
+            response += token
+            yield response
 
-        response += token
-        yield response
+    except Exception as e:
+        print(f"An error occurred: {e}")  # Log any errors
+        return "An error occurred during processing." # Return an error message to Gradio
 
 
+""" 
+For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface 
 """
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+import gradio as gr # Import gradio here
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
         gr.Textbox(value="You are an AI assistant for missed calls. Keep responses short and specific.", label="System message"),
         gr.Slider(minimum=1, maximum=2048, value=100, step=1, label="Max new tokens"),
         gr.Slider(minimum=0.1, maximum=4.0, value=0.2, step=0.1, label="Temperature"),
-        gr.Slider(minimum=0.1, maximum=1.0, value=0.50, step=0.05, label="Top-p (nucleus sampling)",
-        ),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.50, step=0.05, label="Top-p (nucleus sampling)"),
     ],
 )
 
-
 if __name__ == "__main__":
     demo.launch()
+