add main.py

main.py

@@ -1,15 +1,24 @@
 import os
-from langchain_openai import ChatOpenAI
-from langchain_core.messages import HumanMessage
-from langchain_output_parsers import PydanticOutputParser
 from pydantic import BaseModel, Field
+from langchain_core.prompts import PromptTemplate
+from langchain_openai import ChatOpenAI
+from langchain_core.output_parsers import PydanticOutputParser
 
 class TaskCard(BaseModel):
     title: str = Field(..., description="Title of the task")
-    subject: str = Field(..., description="Subject area")
-    deadline_hint: str | None = Field(None, description="Hint about deadline")
-    deliverable_type: str = Field(..., description="What to submit (report, code, etc.)")
-    grading_hints: list[str] = Field(default_factory=list, description="Hints for grading")
+    subject: str = Field(..., description="Subject or domain of the task")
+    deadline_hint: str | None = Field(None, description="Short hint about deadline")
+    deliverable_type: str = Field(..., description="What to submit: report, code, presentation etc.")
+    grading_hints: list[str] = Field(default_factory=list, description="Hints for grading such as completeness, code example")
+
+parser = PydanticOutputParser(pydantic_object=TaskCard)
+prompt_template = PromptTemplate(
+    template="""
+Given the following informal task description:\n{task_description}\n\nReturn a JSON object with fields: title, subject, deadline_hint, deliverable_type, grading_hints.\n{format_instructions}
+""",
+    input_variables=["task_description"],
+    partial_variables={"format_instructions": parser.get_format_instructions()},
+)
 
 llm = ChatOpenAI(
     model="openai/gpt-oss-20b:free",
@@ -17,20 +26,15 @@ llm = ChatOpenAI(
     api_key=os.getenv("OPENAI_API_KEY"),
     temperature=0.0,
 )
-parser = PydanticOutputParser(pydantic_object=TaskCard)
-prompt_template = """
-You are a task summarizer.
-Given the following informal description of an assignment, produce a JSON object matching TaskCard model.
 
-Description: {description}
-
-{format_instructions}
-"""
-prompt = prompt_template | llm | parser
 async def main():
-    description = "Сдайте к пятнице мини-отчёт по LangChain: 2 страницы, упор на агентов. Оценка: за полноту и за пример кода."
-    result = await prompt.ainvoke({"description": description})
-    print(result["messages"][-1].content)
+    task_desc = "Сдайте к пятнице мини-отчёт по LangChain: 2 страницы, упор на агентов. Оценка: за полноту и за пример кода."
+    chain = prompt_template | llm | parser
+    result = await chain.ainvoke({"task_description": task_desc})
+    print("Parsed object:\n", result)
+    print("\nSummary:")
+    for key, value in result.items():
+        print(f"{key}: {value}")
 
 if __name__ == "__main__":
     import asyncio