36 lines
1.4 KiB
Python
36 lines
1.4 KiB
Python
import os
|
|
from langchain_openai import ChatOpenAI
|
|
from langchain_core.prompts import PromptTemplate
|
|
from langchain.output_parsers import PydanticOutputParser
|
|
from models import TaskCard
|
|
from typing import List
|
|
|
|
class TaskParser:
|
|
"""Converts raw task text into a TaskCard using LangChain."""
|
|
|
|
def __init__(self) -> None:
|
|
self.llm = ChatOpenAI(
|
|
model="openai/gpt-oss-20b:free",
|
|
base_url="https://platform.brojs.ru/jrnl-bh/api/inference/v1",
|
|
api_key=os.getenv("JOURNAL_MCP_PAT"),
|
|
temperature=0.0,
|
|
)
|
|
self.output_parser = PydanticOutputParser(pydantic_object=TaskCard)
|
|
self.prompt = PromptTemplate(
|
|
template=(
|
|
"Parse the following raw task description into a structured card.\n"
|
|
"{format_instructions}\n\nRaw text:\n{raw_text}\n\nJSON:"
|
|
),
|
|
input_variables=["raw_text"],
|
|
partial_variables={"format_instructions": self.output_parser.get_format_instructions()},
|
|
)
|
|
self.chain = self.prompt | self.llm | self.output_parser
|
|
|
|
def parse(self, raw_text: str) -> TaskCard:
|
|
"""Parse a single raw task description."""
|
|
return self.chain.invoke({"raw_text": raw_text})
|
|
|
|
def batch_parse(self, texts: List[str]) -> List[TaskCard]:
|
|
"""Parse multiple raw task descriptions."""
|
|
return [self.parse(t) for t in texts]
|