Update app.py

app.py

@@ -1,105 +1,64 @@
-# 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")
-# # client = InferenceClient("meta-llama/Llama-2-7b-hf")
-
-
-# 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 chatbot import generate_response
-
-def respond(message, history, system_message, max_tokens, temperature, top_p):
-    response, updated_history = generate_response(message, history)
-    return response, updated_history
-
-# Create Gradio Interface
-demo = gr.Blocks()
-
-with demo:
-    gr.Markdown("# Chatbot with BlenderBot")
-
-    with gr.Row():
-        system_message = gr.Textbox(value="You are a friendly Chatbot.", label="System message")
-        max_tokens = gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens")
-        temperature = gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature")
-        top_p = gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)")
-
-    chatbot = gr.Chatbot(label="Chatbot Interface")
-    state = gr.State([])
-
-    with gr.Row():
-        user_input = gr.Textbox(placeholder="Type a message...", show_label=False)
-        submit_btn = gr.Button("Submit")
-
-    def submit_message(user_input, history, system_message, max_tokens, temperature, top_p):
-        response, history = respond(user_input, history, system_message, max_tokens, temperature, top_p)
-        return gr.update(chatbot=history), history
+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")
+# client = InferenceClient("meta-llama/Llama-2-7b-hf")
+
+
+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)",
+        ),
+    ],
+)
 
-    submit_btn.click(
-        submit_message,
-        inputs=[user_input, state, system_message, max_tokens, temperature, top_p],
-        outputs=[chatbot, state]
-    )
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()