pythainlp.chat

class pythainlp.chat.ChatBotModel

model: WangChanGLM

__init__() → None

Chat using AI generation

history: list[tuple[str, str]]

reset_chat() → None

Reset chat by cleaning history

load_model(model_name: str = 'wangchanglm', return_dict: bool = True, load_in_8bit: bool = False, device: str = 'cuda', torch_dtype: 'torch.dtype' | None = None, offload_folder: str = './', low_cpu_mem_usage: bool = True) → None

Load model

Parameters:

• model_name (str) – Model name (Now, we support wangchanglm only)

• return_dict (bool) – return_dict

• load_in_8bit (bool) – load model in 8bit

• device (str) – device (cpu, cuda or other)

• torch_dtype (Optional[torch.dtype]) – torch_dtype

• offload_folder (str) – offload folder

• low_cpu_mem_usage (bool) – low cpu mem usage

chat(text: str) → str

Chatbot

Parameters:

text (str) – text for asking chatbot with.

Returns:

answer from chatbot.

Return type:

str

Example:

>>>     from pythainlp.chat import ChatBotModel
>>>     import torch

>>>     chatbot = ChatBotModel()
>>>     chatbot.load_model(device="cpu", torch_dtype=torch.bfloat16)

>>>     print(chatbot.chat("สวัสดี"))
    ยินดีที่ได้รู้จัก

>>>     print(chatbot.history)
    [('สวัสดี', 'ยินดีที่ได้รู้จัก')]