# import gradio as gr # type: ignore # from huggingface_hub import InferenceClient # type: ignore # """ # 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() # ########################### # # app.py # import gradio as gr # type: ignore # import os # # import openai # type: ignore # # # openai.api_key = os.getenv("OPENAI_API_KEY") # # client = openai.OpenAI() # # def respond( # # message, # # history: list[tuple[str, str]], # # system_message, # # max_tokens, # # temperature, # # top_p, # # image_uploaded, # # file_uploaded # # ): # # #read system message # # messages = [{"role": "system", "content": system_message}] # # #read history # # for val in history: # # if val[0]: # # messages.append({"role": "user", "content": val[0]}) # # if val[1]: # # messages.append({"role": "assistant", "content": val[1]}) # # #read output # # messages.append({"role": "user", "content": message}) # # print("## Messages: \n", messages) #debug output # # #create output # # response = client.responses.create( # # model="gpt-4.1-nano", # # input=messages, # # temperature=temperature, # # top_p=top_p, # # max_output_tokens=max_tokens # # ) # # #read output # # response = response.output_text # # print("## Response: ", response) #debug output # # print("\n") # # yield response #chat reply # # import torch # # from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig # # model_name = "deepseek-ai/deepseek-math-7b-base" # # tokenizer = AutoTokenizer.from_pretrained(model_name) # # model = AutoModelForCausalLM.from_pretrained(model_name) # # # model.generation_config = GenerationConfig.from_pretrained(model_name) # # # model.generation_config.pad_token_id = model.generation_config.eos_token_id # # def deepseek( # # message, # # history: list[tuple[str, str]], # # system_message, # # max_tokens, # # temperature, # # top_p): # # # messages = [ # # # {"role": "user", "content": "what is the integral of x^2 from 0 to 2?\nPlease reason step by step, and put your final answer within \\boxed{}."} # # # ] # # messages = [ # # {"role": "user", "content": message} # # ] # # input_tensor = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt") # # outputs = model.generate(input_tensor.to(model.device), max_new_tokens=100) # # print(outputs) # # print("\n") # # result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=True) # # print(result) # # return result # # import replicate # # def deepseek_api_replicate( # # user_message, # # history: list[tuple[str, str]], # # system_message, # # max_new_tokens, # # temperature, # # top_p): # # """ # # Gọi DeepSeek Math trên Replicate và trả ngay kết quả. # # Trả về: # # str hoặc [bytes]: output model sinh ra # # """ # # # 1. Khởi tạo client và xác thực # # # token = os.getenv("REPLICATE_API_TOKEN") # # # if not token: # # # raise RuntimeError("Missing REPLICATE_API_TOKEN") # bảo mật bằng biến môi trường # # client = replicate.Client(api_token="REPLICATE_API_TOKEN") # # # 2. Gọi model # # output = client.run( # # "deepseek-ai/deepseek-math-7b-base:61f572dae0985541cdaeb4a114fd5d2d16cb40dac3894da10558992fc60547c7", # # input={ # # "system_prompt": system_message, # # "user_prompt": user_message, # # "max_new_tokens": max_new_tokens, # # "temperature": temperature, # # "top_p": top_p # # } # # ) # # # 3. Trả kết quả # # return output # import call_api # chat = gr.ChatInterface( # call_api.respond, #chat # title="Trợ lý Học Tập AI", # description="Nhập câu hỏi của bạn về Toán, Lý, Hóa, Văn… và nhận giải đáp chi tiết ngay lập tức!", # additional_inputs=[ # gr.Textbox("Bạn là một chatbot tiếng Việt thân thiện.", label="System message"), # gr.Slider(1, 2048, value=200, step=1, label="Max new tokens"), # gr.Slider(0.1, 4.0, value=0.7, step=0.1, label="Temperature"), # gr.Slider(0.1, 1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"), # # gr.Image(type="pil", label="Attach an image (optional)"), # # gr.File(label="Upload a file (optional)"), # ], # examples=[ # # Mỗi item: [message, system_message, max_tokens, temperature, top_p] # ["tích phân của x^2 từ 0 đến 2 là gì? vui lòng lập luận từng bước, và đặt kết quả cuối cùng trong \boxed{}", "bạn là nhà toán học", 100, 0.7, 0.95], # ], # ) # if __name__ == "__main__": # chat.launch()