From c7dd41fb690459db0ded6ab5bdc1661d9f6af45e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=D0=9A=D0=B8=D1=80=D0=B8=D0=BB=D0=BB=20=D0=9A=D1=83=D1=82?=
 =?UTF-8?q?=D0=BB=D0=B0=D1=85=D0=BC=D0=B5=D1=82=D0=BE=D0=B2?=
 <kirillkutlahmetov10@gmail.com>
Date: Tue, 26 May 2026 13:02:41 +0000
Subject: [PATCH] add parser.py

---
 parser.py | 50 ++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 50 insertions(+)
 create mode 100644 parser.py

diff --git a/parser.py b/parser.py
new file mode 100644
index 0000000..36e3ece
--- /dev/null
+++ b/parser.py
@@ -0,0 +1,50 @@
+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 models import TaskCard
+
+class TaskParser:
+    """Parser that converts raw task descriptions into TaskCard objects using a LLM."""
+
+    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,
+        )
+        self.parser = JsonOutputParser(pydantic_object=TaskCard)
+        self.prompt = PromptTemplate(
+            input_variables=["raw_text"],
+            template="""
+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:
+""",
+        )
+
+    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)
+
+    def batch_parse(self, texts: List[str]) -> List[TaskCard]:
+        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