| # 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 | |
| client = InferenceClient("HuggingFaceH4/zephyr-7b-beta") | |
| def chat_api(message, system_message, max_tokens, temperature, top_p, history=None): | |
| if history is None: | |
| history = [] | |
| messages = [{"role": "system", "content": system_message}] | |
| for user_msg, bot_msg in history: | |
| messages.append({"role": "user", "content": user_msg}) | |
| messages.append({"role": "assistant", "content": bot_msg}) | |
| messages.append({"role": "user", "content": message}) | |
| response = "" | |
| for msg in client.chat_completion( | |
| messages, | |
| max_tokens=max_tokens, | |
| stream=True, | |
| temperature=temperature, | |
| top_p=top_p, | |
| ): | |
| token = msg.choices[0].delta.content | |
| response += token | |
| # Return new response and updated history | |
| history.append((message, response)) | |
| return response, history | |
| # Gradio Interface compatible with JS client | |
| demo = gr.Interface( | |
| fn=chat_api, | |
| inputs=[ | |
| gr.Textbox(label="User Message"), | |
| gr.Textbox(value="You are a friendly Chatbot.", label="System Message"), | |
| gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max 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"), | |
| gr.State([]), # history (user-message, bot-response) | |
| ], | |
| outputs=[ | |
| gr.Textbox(label="Bot Reply"), | |
| gr.State() | |
| ], | |
| allow_flagging="never", | |
| live=False | |
| ) | |
| if __name__ == "__main__": | |
| demo.launch() | |