Spaces:
Configuration error
Configuration error
File size: 2,200 Bytes
88435ed |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 |
from typing import TypedDict
from neollm import MyLLM
from neollm.types import Messages, OpenAIResponse
from neollm.utils.postprocess import strip_string
from neollm.utils.preprocess import optimize_token
class TranslatorInputType(TypedDict):
text: str
class TranslatorOuputType(TypedDict):
text_translated: str
class Translator(MyLLM):
"""情報を抽出するMyLLM
Notes:
inputs:
>>> {"text": str}
outpus:
>>> {"text_translated": str | None(うまくいかなかった場合)}
"""
def _preprocess(self, inputs: TranslatorInputType) -> Messages:
system_prompt = (
"You are a good translator. Translate Japanese into English or English into Japanese.\n"
"# output_format:\n<output>\n{translated text in English or Japanese}"
)
user_prompt = "<input>\n" f"'''{inputs['text'].strip()}'''"
messages: Messages = [
{"role": "system", "content": optimize_token(system_prompt)},
{"role": "user", "content": optimize_token(user_prompt)},
]
return messages
def _ruleprocess(self, inputs: TranslatorInputType) -> None | TranslatorOuputType:
# 入力がない場合の処理
if inputs["text"].strip() == "":
return {"text_translated": ""}
return None
def _update_settings(self) -> None:
# 入力が多い時に16kを使う
if self.messages is not None:
if self.llm.count_tokens(self.messages) >= 1600:
self.model = "gpt-3.5-turbo-16k"
else:
self.model = "gpt-3.5-turbo"
def _postprocess(self, response: OpenAIResponse) -> TranslatorOuputType:
text_translated: str = str(response.choices[0].message["content"])
text_translated = strip_string(text=text_translated, first_character=["<output>", "<outputs>"])
outputs: TranslatorOuputType = {"text_translated": text_translated}
return outputs
# 型定義のために必要
def __call__(self, inputs: TranslatorInputType) -> TranslatorOuputType:
outputs: TranslatorOuputType = super().__call__(inputs)
return outputs
|