feat: solution for unknown
This commit is contained in:
@@ -1,9 +1,9 @@
|
||||
from langchain_openai import ChatOpenAI
|
||||
from pydantic import BaseModel, Field, SecretStr
|
||||
from langchain.agents import create_agent
|
||||
import sys
|
||||
from langchain_core.output_parsers import PydanticOutputParser
|
||||
from langchain_core.prompts import PromptTemplate
|
||||
|
||||
# LLM placeholder configuration
|
||||
# LLM placeholder
|
||||
llm = ChatOpenAI(
|
||||
model="openai/gpt-oss-20b",
|
||||
base_url='https://platform.brojs.ru/jrnl-bh/api/inference/v1',
|
||||
@@ -11,72 +11,62 @@ llm = ChatOpenAI(
|
||||
temperature=0.7,
|
||||
)
|
||||
|
||||
# ---------- Pydantic models ----------
|
||||
class PersonInfo(BaseModel):
|
||||
"""Information about a person."""
|
||||
name: str = Field(description="Full name of the person")
|
||||
age: int | None = Field(default=None, description="Age in years, optional")
|
||||
profession: str = Field(description="Current occupation or job title")
|
||||
skills: list[str] = Field(description="List of professional skills")
|
||||
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):
|
||||
"""Summary of a meeting."""
|
||||
date: str = Field(description="Date of the meeting (ISO format)")
|
||||
participants: list[str] = Field(description="Names of attendees")
|
||||
topics: list[str] = Field(description="Main discussion topics")
|
||||
decisions: list[str] = Field(description="Decisions made during the meeting")
|
||||
next_steps: list[str] = Field(description="Action items for follow‑up")
|
||||
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")
|
||||
|
||||
# ---------- Agent creation ----------
|
||||
agent_person = create_agent(
|
||||
model=llm,
|
||||
response_format=PersonInfo,
|
||||
system_prompt="You are an assistant that extracts structured person information from a single sentence.",
|
||||
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}"""
|
||||
)
|
||||
|
||||
agent_meeting = create_agent(
|
||||
model=llm,
|
||||
response_format=MeetingNotes,
|
||||
system_prompt="You are an assistant that extracts structured meeting notes from a paragraph of text.",
|
||||
)
|
||||
def choose_parser(text: str):
|
||||
if any(word in text.lower() for word in ["meeting", "встреча", "собрание"]):
|
||||
return meeting_parser
|
||||
return person_parser
|
||||
|
||||
# ---------- Simple heuristic to choose schema ----------
|
||||
def detect_schema(text: str) -> str:
|
||||
"""Return 'person' or 'meeting' based on simple keyword heuristics."""
|
||||
lower = text.lower()
|
||||
if any(word in lower for word in ("profession", "skills", "age")):
|
||||
return "person"
|
||||
if any(word in lower for word in ("meeting", "participants", "decisions", "next steps")):
|
||||
return "meeting"
|
||||
# Default to person if ambiguous
|
||||
return "person"
|
||||
|
||||
# ---------- CLI ----------
|
||||
def main():
|
||||
examples = [
|
||||
"Анна, 28 лет, Python-разработчик. Навыки: FastAPI, Docker.",
|
||||
("Встреча с командой по проекту X прошла 2024-05-20.\n"
|
||||
"Участники: Иван, Мария, Алексей.\n"
|
||||
"Темы: планирование спринта, распределение задач.\n"
|
||||
"Решения: назначить ответственных за каждый модуль.\n"
|
||||
"Next steps: подготовить спецификации к 2024-05-27."),
|
||||
]
|
||||
|
||||
if len(sys.argv) > 1:
|
||||
texts = [" ".join(sys.argv[1:])]
|
||||
else:
|
||||
texts = examples
|
||||
|
||||
for txt in texts:
|
||||
print("\n=== Input ===")
|
||||
print(txt)
|
||||
schema_type = detect_schema(txt)
|
||||
agent = agent_person if schema_type == "person" else agent_meeting
|
||||
result = agent.invoke({"messages": [{"role": "user", "content": txt}]})
|
||||
structured = result["structured_response"]
|
||||
print("\n=== Output ===")
|
||||
print(structured.model_dump(indent=2))
|
||||
print("\n---")
|
||||
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__":
|
||||
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())
|
||||
Reference in New Issue
Block a user