72 lines
2.8 KiB
Python
72 lines
2.8 KiB
Python
from langchain_openai import ChatOpenAI
|
|
from pydantic import BaseModel, Field, SecretStr
|
|
from langchain_core.output_parsers import PydanticOutputParser
|
|
from langchain_core.prompts import PromptTemplate
|
|
|
|
# LLM placeholder
|
|
llm = ChatOpenAI(
|
|
model="openai/gpt-oss-20b",
|
|
base_url='https://platform.brojs.ru/jrnl-bh/api/inference/v1',
|
|
api_key=SecretStr("jrnl_30283ab953615cbb6846ff9940a1eedce0b76d7b2f59a2394f29e74643e6a90d"),
|
|
temperature=0.7,
|
|
)
|
|
|
|
class PersonInfo(BaseModel):
|
|
name: str = Field(description="Имя человека")
|
|
age: int | None = Field(default=None, description="Возраст (необязательно)")
|
|
profession: str = Field(description="Профессия")
|
|
skills: list[str] = Field(description="Список навыков")
|
|
|
|
class MeetingNotes(BaseModel):
|
|
date: str = Field(description="Дата встречи в формате YYYY-MM-DD")
|
|
participants: list[str] = Field(description="Участники встречи")
|
|
topics: list[str] = Field(description="Обсуждаемые темы")
|
|
decisions: list[str] = Field(description="Принятые решения")
|
|
next_steps: list[str] = Field(description="Следующие шаги")
|
|
|
|
person_parser = PydanticOutputParser(pydantic_object=PersonInfo)
|
|
meeting_parser = PydanticOutputParser(pydantic_object=MeetingNotes)
|
|
|
|
prompt_template = PromptTemplate(
|
|
input_variables=["text", "format_instructions"],
|
|
template="""Найди в тексте следующую информацию и верни её как JSON:
|
|
{format_instructions}
|
|
Текст: {text}"""
|
|
)
|
|
|
|
def choose_parser(text: str):
|
|
if any(word in text.lower() for word in ["meeting", "встреча", "собрание"]):
|
|
return meeting_parser
|
|
return person_parser
|
|
|
|
def extract(text: str):
|
|
parser = choose_parser(text)
|
|
chain = prompt_template | llm | parser
|
|
result = chain.invoke({"text": text, "format_instructions": parser.get_format_instructions()})
|
|
return result
|
|
|
|
if __name__ == "__main__":
|
|
examples = [
|
|
"Анна, 28 лет, Python-разработчик. Навыки: FastAPI, Docker.",
|
|
"""Meeting on 2024-05-27
|
|
Participants: Alice, Bob, Charlie
|
|
Topics: Project roadmap, Budget allocation
|
|
Decisions: Approve Q3 budget, Hire new devs
|
|
Next steps: Send email to stakeholders, Update project plan""",
|
|
]
|
|
for i, txt in enumerate(examples, 1):
|
|
print(f"Example {i} input:")
|
|
print(txt)
|
|
obj = extract(txt)
|
|
print("\nParsed object:")
|
|
print(obj.model_dump())
|
|
print("-" * 40)
|
|
|
|
# Interactive mode
|
|
while True:
|
|
user_input = input("Введите текст (или 'exit' для выхода): ").strip()
|
|
if not user_input or user_input.lower() == "exit":
|
|
break
|
|
obj = extract(user_input)
|
|
print("\nParsed object:")
|
|
print(obj.model_dump()) |