Update app.py

app.py

@@ -1,73 +1,12 @@
-# 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")
-
-
-# def respond(
-#     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]})
-
-#     messages.append({"role": "user", "content": message})
-
-#     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
-
-# """
-# 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 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)",
-#         ),
-#     ],
-# )
-
-
-# if __name__ == "__main__":
-#     demo.launch()
-
 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")
 
-# Function to respond to user input while maintaining chat history
+
 def respond(
     message,
     history: list[tuple[str, str]],
@@ -76,43 +15,37 @@ def respond(
     temperature,
     top_p,
 ):
-    try:
-        # Append system message at the start
-        messages = [{"role": "system", "content": system_message}]
-
-        # Append the chat history
-        for user_msg, bot_reply in history:
-            if user_msg:
-                messages.append({"role": "user", "content": user_msg})
-            if bot_reply:
-                messages.append({"role": "assistant", "content": bot_reply})
-
-        # Add the latest user message
-        messages.append({"role": "user", "content": message})
-
-        response = ""
-
-        # Stream the response token by token to avoid loading delays
-        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
-
-    except Exception:
-        # Handle any error silently (without showing the error icon or message)
-        yield "An internal error occurred. But let's continue."  # Custom message or silent
-
-# Gradio interface for customizable chatbot behavior
+    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": "user", "content": message})
+
+    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
+
+"""
+For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
+"""
 demo = gr.ChatInterface(
-    fn=respond,
+    respond,
     additional_inputs=[
-        gr.Textbox(value="You are an AI dermatologist Chatbot.", label="System message"),
+        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(
@@ -125,7 +58,74 @@ demo = gr.ChatInterface(
     ],
 )
 
+
 if __name__ == "__main__":
     demo.launch()
 
+# import gradio as gr
+# from huggingface_hub import InferenceClient
+
+# client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+
+# # Function to respond to user input while maintaining chat history
+# def respond(
+#     message,
+#     history: list[tuple[str, str]],
+#     system_message,
+#     max_tokens,
+#     temperature,
+#     top_p,
+# ):
+#     try:
+#         # Append system message at the start
+#         messages = [{"role": "system", "content": system_message}]
+
+#         # Append the chat history
+#         for user_msg, bot_reply in history:
+#             if user_msg:
+#                 messages.append({"role": "user", "content": user_msg})
+#             if bot_reply:
+#                 messages.append({"role": "assistant", "content": bot_reply})
+
+#         # Add the latest user message
+#         messages.append({"role": "user", "content": message})
+
+#         response = ""
+
+#         # Stream the response token by token to avoid loading delays
+#         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
+
+#     except Exception:
+#         # Handle any error silently (without showing the error icon or message)
+#         yield "An internal error occurred. But let's continue."  # Custom message or silent
+
+# # Gradio interface for customizable chatbot behavior
+# demo = gr.ChatInterface(
+#     fn=respond,
+#     additional_inputs=[
+#         gr.Textbox(value="You are an AI dermatologist 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)",
+#         ),
+#     ],
+# )
+
+# if __name__ == "__main__":
+#     demo.launch()
+