136 lines
4.7 KiB
Python
136 lines
4.7 KiB
Python
import os
|
|
import sys
|
|
import asyncio
|
|
from dotenv import load_dotenv
|
|
from langchain_openai import ChatOpenAI
|
|
from langchain_core.messages import HumanMessage
|
|
from langchain.tools import tool
|
|
from deepagents import create_deep_agent
|
|
from deepagents.backends import FilesystemBackend, LocalShellBackend, CompositeBackend
|
|
from pydantic import BaseModel, Field
|
|
from langchain_core.output_parsers import PydanticOutputParser
|
|
from langchain_core.prompts import PromptTemplate
|
|
|
|
load_dotenv()
|
|
|
|
# Pydantic models
|
|
class PersonInfo(BaseModel):
|
|
name: str = Field(description="Full name of the person")
|
|
age: int | None = Field(description="Age in years, optional", default=None)
|
|
profession: str = Field(description="Current profession")
|
|
skills: list[str] = Field(description="List of skills")
|
|
|
|
class MeetingNotes(BaseModel):
|
|
date: str = Field(description="Date of the meeting")
|
|
participants: list[str] = Field(description="List of participants")
|
|
topics: list[str] = Field(description="Discussion topics")
|
|
decisions: list[str] = Field(description="Decisions made")
|
|
next_steps: list[str] = Field(description="Next steps to be taken")
|
|
|
|
# LLM configuration
|
|
llm = ChatOpenAI(
|
|
model="openai/gpt-oss-20b:free",
|
|
base_url="https://openrouter.ai/api/v1",
|
|
api_key=os.getenv("OPENAI_API_KEY"),
|
|
temperature=0.0,
|
|
)
|
|
|
|
# Backend for deepagents
|
|
backend = CompositeBackend([
|
|
LocalShellBackend(workspace_dir="./workspace"),
|
|
FilesystemBackend(),
|
|
])
|
|
|
|
# Parsers
|
|
person_parser = PydanticOutputParser(pydantic_object=PersonInfo)
|
|
meeting_parser = PydanticOutputParser(pydantic_object=MeetingNotes)
|
|
|
|
# Prompt template
|
|
prompt_template = PromptTemplate(
|
|
input_variables=["format_instructions", "text"],
|
|
template=(
|
|
"Extract structured data from the following text. "
|
|
"Follow the format:\n{format_instructions}\n\nText:\n{text}\n\nOutput:"
|
|
),
|
|
)
|
|
|
|
# Helper to decide which parser to use
|
|
def choose_parser(text: str):
|
|
lower = text.lower()
|
|
if any(word in lower for word in ["age", "years", "profession", "skills", "skill"]):
|
|
return person_parser
|
|
if any(word in lower for word in ["meeting", "participants", "topics", "decisions", "next steps", "next_step"]):
|
|
return meeting_parser
|
|
# Default to person_parser
|
|
return person_parser
|
|
|
|
# Tool for extraction
|
|
@tool
|
|
def extract_structured(text: str) -> str:
|
|
"""
|
|
Extract structured data from the given text and return a JSON string.
|
|
"""
|
|
parser = choose_parser(text)
|
|
format_instructions = parser.get_format_instructions()
|
|
prompt = prompt_template.format(format_instructions=format_instructions, text=text)
|
|
raw_output = llm.invoke(prompt).content
|
|
try:
|
|
parsed_obj = parser.parse(raw_output)
|
|
return parsed_obj.model_dump_json()
|
|
except Exception as e:
|
|
return f"Error parsing output: {e}"
|
|
|
|
# Create the agent
|
|
agent = create_deep_agent(
|
|
model=llm,
|
|
tools=[extract_structured],
|
|
backend=backend,
|
|
system_prompt="You are a helpful agent that extracts structured data from text.",
|
|
)
|
|
|
|
# CLI logic
|
|
async def run_agent(text: str):
|
|
result = await agent.ainvoke(
|
|
{"messages": [HumanMessage(content=text)]},
|
|
{"configurable": {"thread_id": "session-1"}},
|
|
)
|
|
output = result["messages"][-1].content
|
|
try:
|
|
data = PersonInfo.model_validate_json(output)
|
|
obj_type = "PersonInfo"
|
|
except Exception:
|
|
try:
|
|
data = MeetingNotes.model_validate_json(output)
|
|
obj_type = "MeetingNotes"
|
|
except Exception:
|
|
print("Failed to parse JSON output.")
|
|
return
|
|
print("\nParsed object:")
|
|
print(data.model_dump())
|
|
print("\nSummary:")
|
|
if obj_type == "PersonInfo":
|
|
print(f"{obj_type}: {data.name}, age={data.age}, profession={data.profession}, skills={data.skills}")
|
|
else:
|
|
print(f"{obj_type}: date={data.date}, participants={data.participants}, topics={data.topics}, decisions={data.decisions}, next_steps={data.next_steps}")
|
|
|
|
def main():
|
|
if len(sys.argv) > 1:
|
|
input_text = " ".join(sys.argv[1:])
|
|
asyncio.run(run_agent(input_text))
|
|
else:
|
|
examples = [
|
|
(
|
|
"Анна, 28 лет, Python-разработчик. Навыки: FastAPI, Docker.",
|
|
"PersonInfo example",
|
|
),
|
|
(
|
|
"Встреча 12.09.2026. Участники: Иван, Мария. Темы: проект X, бюджет. Решения: увеличить бюджет. Следующие шаги: подготовить отчёт.",
|
|
"MeetingNotes example",
|
|
),
|
|
]
|
|
for text, title in examples:
|
|
print(f"\n=== {title} ===")
|
|
asyncio.run(run_agent(text))
|
|
|
|
if __name__ == "__main__":
|
|
main() |