add parser.py

parser.py

@@ -1,50 +1,35 @@
 import os
-import json
-from typing import List
 from langchain_openai import ChatOpenAI
-from langchain_core.output_parsers import JsonOutputParser
 from langchain_core.prompts import PromptTemplate
-from pydantic import BaseModel
+from langchain.output_parsers import PydanticOutputParser
-
 from models import TaskCard
+from typing import List
 
 class TaskParser:
-    """Parser that converts raw task descriptions into TaskCard objects using a LLM."""
+    """Converts raw task text into a TaskCard using LangChain."""
 
     def __init__(self) -> None:
         self.llm = ChatOpenAI(
             model="openai/gpt-oss-20b:free",
             base_url="https://platform.brojs.ru/jrnl-bh/api/inference/v1",
             api_key=os.getenv("JOURNAL_MCP_PAT"),
-            temperature=0.1,
+            temperature=0.0,
         )
-        self.parser = JsonOutputParser(pydantic_object=TaskCard)
+        self.output_parser = PydanticOutputParser(pydantic_object=TaskCard)
         self.prompt = PromptTemplate(
+            template=(
+                "Parse the following raw task description into a structured card.\n"
+                "{format_instructions}\n\nRaw text:\n{raw_text}\n\nJSON:"
+            ),
             input_variables=["raw_text"],
-            template="""
+            partial_variables={"format_instructions": self.output_parser.get_format_instructions()},
-Parse the following raw task description into a JSON object matching the TaskCard schema.
-The output must be valid JSON and contain all required fields.
-If a field cannot be determined, use null for optional fields or an empty list for lists.
-
-Raw text:
-{raw_text}
-
-JSON output:
-""",
         )
-
+        self.chain = self.prompt | self.llm | self.output_parser
-    def _run_llm(self, raw_text: str) -> TaskCard:
-        chain = self.prompt | self.llm | self.parser
-        return chain.invoke({"raw_text": raw_text})
 
     def parse(self, raw_text: str) -> TaskCard:
-        return self._run_llm(raw_text)
+        """Parse a single raw task description."""
+        return self.chain.invoke({"raw_text": raw_text})
 
     def batch_parse(self, texts: List[str]) -> List[TaskCard]:
+        """Parse multiple raw task descriptions."""
         return [self.parse(t) for t in texts]
-
-    def save_to_file(self, card: TaskCard, filename: str) -> None:
-        with open(filename, "w", encoding="utf-8") as f:
-            json.dump(card.dict(), f, ensure_ascii=False, indent=2)
-
-# End of parser.py