Spaces:
Sleeping
Sleeping
| 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("unsloth/Llama-3.2-1B-Instruct") | |
| def respond( | |
| message, | |
| history: list[tuple[str, str]], | |
| # system_message, | |
| # max_tokens, | |
| # temperature, | |
| # top_p, | |
| ): | |
| system_message = "You are a Dietician Assistant specializing in providing general guidance on diet, " | |
| "nutrition, and healthy eating habits. Answer questions thoroughly with scientifically " | |
| "backed advice, practical tips, and easy-to-understand explanations. Keep in mind that " | |
| "your role is to assist, not replace a registered dietitian, so kindly remind users to " | |
| "consult a professional for personalized advice when necessary." | |
| max_tokens = 512 | |
| temperature = 0.7 | |
| top_p = 0.95 | |
| 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)", | |
| # # ), | |
| # # ], | |
| # ) | |
| def default_message(): | |
| """Function to return initial default message.""" | |
| return [("Hi there! I'm your Dietician Assistant, here to help with general advice " | |
| "on diet, nutrition, and healthy eating habits. Let's explore your questions.", "")] | |
| # Set up the Gradio ChatInterface with an initial default message | |
| with gr.Blocks() as demo: | |
| chatbot = 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)", | |
| # ), | |
| # ], | |
| ) | |
| # Display the default message on load | |
| gr.State(default_message()) # Store initial chat history | |
| chatbot.history = default_message() # Set the chat history to show the greeting | |
| if __name__ == "__main__": | |
| demo.launch() |