feat: solution for unknown

solutions/unknown/solution.py

@@ -1,9 +1,9 @@
 from langchain_openai import ChatOpenAI
 from pydantic import BaseModel, Field, SecretStr
-from langchain.agents import create_agent
+from langchain_core.output_parsers import PydanticOutputParser
-import sys
+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="Имя человека")
-    name: str = Field(description="Full name of the person")
+    age: int | None = Field(default=None, description="Возраст (необязательно)")
-    age: int | None = Field(default=None, description="Age in years, optional")
+    profession: str = Field(description="Профессия")
-    profession: str = Field(description="Current occupation or job title")
+    skills: list[str] = Field(description="Список навыков")
-    skills: list[str] = Field(description="List of professional skills")
 
 class MeetingNotes(BaseModel):
-    """Summary of a meeting."""
+    date: str = Field(description="Дата встречи в формате YYYY-MM-DD")
-    date: str = Field(description="Date of the meeting (ISO format)")
+    participants: list[str] = Field(description="Участники встречи")
-    participants: list[str] = Field(description="Names of attendees")
+    topics: list[str] = Field(description="Обсуждаемые темы")
-    topics: list[str] = Field(description="Main discussion topics")
+    decisions: list[str] = Field(description="Принятые решения")
-    decisions: list[str] = Field(description="Decisions made during the meeting")
+    next_steps: list[str] = Field(description="Следующие шаги")
-    next_steps: list[str] = Field(description="Action items for follow‑up")
 
-# ---------- Agent creation ----------
+person_parser = PydanticOutputParser(pydantic_object=PersonInfo)
-agent_person = create_agent(
+meeting_parser = PydanticOutputParser(pydantic_object=MeetingNotes)
-    model=llm,
+
-    response_format=PersonInfo,
+prompt_template = PromptTemplate(
-    system_prompt="You are an assistant that extracts structured person information from a single sentence.",
+    input_variables=["text", "format_instructions"],
+    template="""Найди в тексте следующую информацию и верни её как JSON:
+{format_instructions}
+Текст: {text}"""
 )
 
-agent_meeting = create_agent(
+def choose_parser(text: str):
-    model=llm,
+    if any(word in text.lower() for word in ["meeting", "встреча", "собрание"]):
-    response_format=MeetingNotes,
+        return meeting_parser
-    system_prompt="You are an assistant that extracts structured meeting notes from a paragraph of text.",
+    return person_parser
-)
 
-# ---------- Simple heuristic to choose schema ----------
+def extract(text: str):
-def detect_schema(text: str) -> str:
+    parser = choose_parser(text)
-    """Return 'person' or 'meeting' based on simple keyword heuristics."""
+    chain = prompt_template | llm | parser
-    lower = text.lower()
+    result = chain.invoke({"text": text, "format_instructions": parser.get_format_instructions()})
-    if any(word in lower for word in ("profession", "skills", "age")):
+    return result
-        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---")
 
 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())