add parser.py
This commit is contained in:
@@ -1,108 +1,111 @@
|
|||||||
|
#!/usr/bin/env python3
|
||||||
|
# -*- coding: utf-8 -*-
|
||||||
|
|
||||||
"""
|
"""
|
||||||
Raw text → flat card parser.
|
Пример преобразования неформального описания задания в структурированный объект.
|
||||||
|
|
||||||
This module demonstrates how to convert a free‑form assignment description into a structured
|
Используем:
|
||||||
Pydantic model using LangChain’s PromptTemplate, LLM and PydanticOutputParser.
|
* LangChain (core + OpenAI)
|
||||||
|
* Pydantic для типизации и проверки результата
|
||||||
The public function ``parse_assignment(text: str) -> AssignmentCard`` returns an instance of
|
|
||||||
the :class:`AssignmentCard` dataclass. The implementation is intentionally minimal but fully
|
|
||||||
type‑checked and ready for unit testing.
|
|
||||||
"""
|
"""
|
||||||
|
|
||||||
from __future__ import annotations
|
import os
|
||||||
|
from pathlib import Path
|
||||||
|
|
||||||
from dataclasses import dataclass
|
|
||||||
from typing import List, Dict
|
|
||||||
|
|
||||||
# LangChain imports – the core library provides PromptTemplate and LLM wrappers
|
|
||||||
from langchain_core.prompts import PromptTemplate
|
from langchain_core.prompts import PromptTemplate
|
||||||
from langchain_openai import ChatOpenAI
|
from langchain_openai import ChatOpenAI
|
||||||
from langchain.output_parsers import PydanticOutputParser
|
from langchain_core.output_parsers import PydanticOutputParser
|
||||||
from pydantic import BaseModel, Field
|
from pydantic import BaseModel, Field
|
||||||
|
|
||||||
# ---------------------------------------------------------------------------
|
|
||||||
# 1. Define the output schema with Pydantic
|
# ------------------------------------------------------------------
|
||||||
# ---------------------------------------------------------------------------
|
# 1. Модель карточки задания (Pydantic)
|
||||||
|
# ------------------------------------------------------------------
|
||||||
class AssignmentCard(BaseModel):
|
class AssignmentCard(BaseModel):
|
||||||
"""Structured representation of an assignment description.
|
title: str = Field(..., description="Краткое название задачи")
|
||||||
|
subject: str = Field(
|
||||||
|
..., description="Предмет/тема, к которой относится задание"
|
||||||
|
)
|
||||||
|
deadline_hint: str | None = Field(
|
||||||
|
None,
|
||||||
|
description="Указание дедлайна в свободной форме (например, «к пятнице»)",
|
||||||
|
)
|
||||||
|
deliverable_type: str = Field(
|
||||||
|
...,
|
||||||
|
description=(
|
||||||
|
"Тип сдачи: отчёт, код, презентация и т.п. "
|
||||||
|
"(если однотипное – перечислите без пунктов)"
|
||||||
|
),
|
||||||
|
)
|
||||||
|
grading_hints: list[str] | None = Field(
|
||||||
|
None,
|
||||||
|
description="Ключевые критерии оценки (список строк)",
|
||||||
|
)
|
||||||
|
|
||||||
Attributes
|
|
||||||
----------
|
|
||||||
title : str
|
|
||||||
Short title of the task.
|
|
||||||
subject : str
|
|
||||||
Subject or topic covered by the assignment.
|
|
||||||
deadline_hint : str | None
|
|
||||||
Human‑readable hint about the due date (e.g. "by Friday").
|
|
||||||
deliverable_type : str
|
|
||||||
What should be submitted – e.g. "report", "code".
|
|
||||||
grading_hints : List[str]
|
|
||||||
Optional list of hints that influence grading.
|
|
||||||
"""
|
|
||||||
|
|
||||||
title: str = Field(..., description="Short title of the task")
|
# ------------------------------------------------------------------
|
||||||
subject: str = Field(..., description="Subject or topic covered by the assignment")
|
# 2. Парсер и промпт
|
||||||
deadline_hint: str | None = Field(None, description="Human‑readable hint about due date")
|
# ------------------------------------------------------------------
|
||||||
deliverable_type: str = Field(..., description="What should be submitted – e.g. report, code")
|
|
||||||
grading_hints: List[str] = Field(default_factory=list, description="Hints that influence grading")
|
|
||||||
|
|
||||||
# ---------------------------------------------------------------------------
|
|
||||||
# 2. Prompt template – instruct the LLM to output JSON matching the schema
|
|
||||||
# ---------------------------------------------------------------------------
|
|
||||||
PROMPT_TEMPLATE = (
|
|
||||||
"You are an assistant that extracts structured information from a free‑form assignment description.
|
|
||||||
Return a JSON object with the following fields exactly as defined in the AssignmentCard model:
|
|
||||||
{{schema}}
|
|
||||||
The input text is: "{{text}}"
|
|
||||||
""")
|
|
||||||
|
|
||||||
# ---------------------------------------------------------------------------
|
|
||||||
# 3. Parser that validates the LLM output against the Pydantic schema
|
|
||||||
# ---------------------------------------------------------------------------
|
|
||||||
parser = PydanticOutputParser(pydantic_object=AssignmentCard)
|
parser = PydanticOutputParser(pydantic_object=AssignmentCard)
|
||||||
|
|
||||||
# ---------------------------------------------------------------------------
|
prompt_template = """
|
||||||
# 4. The main function – orchestrates prompt → LLM → parser
|
Пожалуйста, преобразуйте следующее описание задания в JSON‑объект,
|
||||||
# ---------------------------------------------------------------------------
|
соответствующий схеме:
|
||||||
def parse_assignment(text: str, *, llm_model: str = "gpt-3.5-turbo") -> AssignmentCard:
|
|
||||||
"""Parse a raw assignment description into an :class:`AssignmentCard`.
|
|
||||||
|
|
||||||
Parameters
|
{format_instructions}
|
||||||
----------
|
|
||||||
text : str
|
|
||||||
Free‑form assignment description.
|
|
||||||
llm_model : str, optional
|
|
||||||
Name of the OpenAI model to use. Defaults to ``gpt-3.5-turbo``.
|
|
||||||
|
|
||||||
Returns
|
Текст задания:
|
||||||
-------
|
"{input_text}"
|
||||||
AssignmentCard
|
"""
|
||||||
Validated dataclass instance.
|
|
||||||
"""
|
|
||||||
# Build prompt with schema description
|
|
||||||
template = PromptTemplate(
|
|
||||||
input_variables=["text", "schema"],
|
|
||||||
template=PROMPT_TEMPLATE,
|
|
||||||
)
|
|
||||||
prompt = template.format(text=text, schema=parser.get_format_instructions())
|
|
||||||
|
|
||||||
# Call the LLM – we use ChatOpenAI from langchain_openai for simplicity
|
prompt = PromptTemplate(
|
||||||
llm = ChatOpenAI(model_name=llm_model, temperature=0)
|
template=prompt_template,
|
||||||
raw_output = llm.invoke(prompt).content
|
input_variables=["input_text"],
|
||||||
|
partial_variables={"format_instructions": parser.get_format_instructions()},
|
||||||
|
)
|
||||||
|
|
||||||
# Parse and validate
|
# ------------------------------------------------------------------
|
||||||
return parser.parse(raw_output)
|
# 3. Модель LLM
|
||||||
|
# ------------------------------------------------------------------
|
||||||
|
llm = ChatOpenAI(temperature=0, model="gpt-4o-mini") # можно поменять модель
|
||||||
|
|
||||||
# ---------------------------------------------------------------------------
|
# Создаём цепочку: Prompt → LLM → Parser
|
||||||
# 5. Demo – run when executed as a script
|
chain = prompt | llm | parser
|
||||||
# ---------------------------------------------------------------------------
|
|
||||||
|
|
||||||
|
# ------------------------------------------------------------------
|
||||||
|
# 4. Функция «обработки» одной строки
|
||||||
|
# ------------------------------------------------------------------
|
||||||
|
def parse_assignment(text: str) -> AssignmentCard:
|
||||||
|
"""Возвращает валидированную модель из текста."""
|
||||||
|
return chain.invoke({"input_text": text})
|
||||||
|
|
||||||
|
|
||||||
|
# ------------------------------------------------------------------
|
||||||
|
# 5. Тестовый пример (можно заменить на любой другой)
|
||||||
|
# ------------------------------------------------------------------
|
||||||
if __name__ == "__main__":
|
if __name__ == "__main__":
|
||||||
import os
|
example = (
|
||||||
if not os.getenv("OPENAI_API_KEY"):
|
"Сдайте к пятнице мини‑отчёт по LangChain: "
|
||||||
raise RuntimeError("Set OPENAI_API_KEY environment variable.")
|
"2 страницы, упор на агентов. Оценка: за полноту и за пример кода."
|
||||||
|
|
||||||
sample = (
|
|
||||||
"Сдайте к пятнице мини‑отчёт по LangChain. В отчёте должно быть описание модели, пример кода и выводы."
|
|
||||||
)
|
)
|
||||||
card = parse_assignment(sample)
|
card = parse_assignment(example)
|
||||||
print("Parsed assignment:", card.json(indent=2))
|
|
||||||
|
# Выводим модель в виде JSON
|
||||||
|
print("\n=== Валидация ===")
|
||||||
|
print(card.model_dump(indent=4))
|
||||||
|
|
||||||
|
# Краткая человекочитаемая сводка
|
||||||
|
print("\n=== Сводка ===")
|
||||||
|
print(f"Тема: {card.subject}")
|
||||||
|
print(f"Название: {card.title}")
|
||||||
|
if card.deadline_hint:
|
||||||
|
print(f"Дедлайн: {card.deadline_hint}")
|
||||||
|
print(f"Сдача: {card.deliverable_type}")
|
||||||
|
if card.grading_hints:
|
||||||
|
print("Критерии оценки:")
|
||||||
|
for h in card.grading_hints:
|
||||||
|
print(f" • {h}")
|
||||||
|
|
||||||
|
|
||||||
|
# ────────────────────── End of file ─────────────────────
|
||||||
|
|||||||
Reference in New Issue
Block a user