Implement Phase 4~14: LangGraph Agent, RAG pipeline, Gradio Web UI, voice interface

- Upgrade LLM to Qwen3-14B-4bit with Thinking mode (MlxChatModel as LangChain BaseChatModel) - Add LangGraph ReAct agent with tool calling loop (search_documents, web_search, get_current_date, remember/recall_user_info) - Add RAG pipeline: BAAI/bge-m3 embeddings + Qdrant vector store + semantic chunking (SemanticSplitter via cosine similarity) - Replace fixed-size RecursiveCharacterTextSplitter with meaning-based SemanticSplitter (numpy only, no extra deps) - Add Gradio Web UI (app.py): chat, document ingestion, document management tabs - Add multi-user support (user_id isolation in DB + per-user agent cache + dropdown selector) - Add conversation history restore from MySQL on agent init (Phase 11) - Add UserProfileRepository for persistent user profile (remember/recall tools) - Add thread-local DB connections to fix pymysql thread-safety with LangGraph ToolNode - Add Phase 14 voice interface: Whisper STT (microphone → text) + macOS TTS (say -v Yuna) - Enforce search_documents-first policy in system prompt and tool descriptions - Update ROADMAP2.md: Phase 14 완료, Phase 13 청킹 부분 완료 Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-27 14:06:22 +09:00
parent cd41e9e33e
commit 06bcdb03ac
20 changed files with 1934 additions and 47 deletions
@@ -8,14 +8,16 @@ class ConversationRepository:
    def __init__(self, db: DatabaseService):
        self._db = db

-    def create_conversation(self) -> int:
+    def create_conversation(self, user_id: str = "default") -> int:
        return self._db.execute_write(
-            "INSERT INTO td_conversations () VALUES ()"
+            "INSERT INTO td_conversations (user_id) VALUES (%s)",
+            (user_id,),
        )

-    def get_latest_conversation_id(self) -> int | None:
+    def get_latest_conversation_id(self, user_id: str = "default") -> int | None:
        rows = self._db.execute(
-            "SELECT id FROM td_conversations ORDER BY created_at DESC LIMIT 1"
+            "SELECT id FROM td_conversations WHERE user_id = %s ORDER BY created_at DESC LIMIT 1",
+            (user_id,),
        )
        return rows[0]["id"] if rows else None

@@ -1,47 +1,81 @@
 from __future__ import annotations
+import threading
 from typing import Any


 class DatabaseService:
-    """MySQL 연결을 캡슐화하는 서비스. 미설정 시 graceful skip."""
+    """MySQL 연결을 캡슐화하는 서비스. 미설정 시 graceful skip.

-    def __init__(self, host: str, port: int, db: str, user: str, password: str):
+    스레드별 독립 연결(thread-local)을 사용해 LangGraph ToolNode의
+    스레드 풀 실행과 pymysql 비안전성 문제를 해결한다.
+    """
+
+    def __init__(
+        self,
+        host: str,
+        port: int,
+        db: str,
+        user: str,
+        password: str,
+    ):
        self._config = dict(host=host, port=port, db=db, user=user, passwd=password)
-        self._conn = None
+        self._local = threading.local()
+
+    # ── DB 연결 ────────────────────────────────────────────────────────
+
+    def _get_conn(self):
+        if not self._config["user"]:
+            return None
+
+        import pymysql
+        conn = getattr(self._local, "conn", None)
+        if conn is None:
+            try:
+                self._local.conn = pymysql.connect(**self._config)
+            except Exception as e:
+                print(f"[DB] 연결 실패: {e}")
+                return None
+        else:
+            try:
+                conn.ping(reconnect=True)
+            except Exception:
+                try:
+                    self._local.conn = pymysql.connect(**self._config)
+                except Exception as e:
+                    print(f"[DB] 재연결 실패: {e}")
+                    return None
+        return self._local.conn

    def connect(self) -> None:
-        if not self._config["user"]:
-            return
-        try:
-            import pymysql
-            self._conn = pymysql.connect(**self._config)
-        except Exception as e:
-            print(f"[DB] 연결 실패 (선택적 기능): {e}")
+        self._get_conn()

    def execute(self, sql: str, params: tuple = ()) -> list[dict[str, Any]]:
-        if self._conn is None:
+        conn = self._get_conn()
+        if conn is None:
            return []
-        cursor = self._conn.cursor()
+        cursor = conn.cursor()
        cursor.execute(sql, params)
        columns = [d[0] for d in cursor.description or []]
        return [dict(zip(columns, row)) for row in cursor.fetchall()]

    def execute_write(self, sql: str, params: tuple = ()) -> int:
-        """INSERT/UPDATE/DELETE 실행 후 lastrowid 반환."""
-        if self._conn is None:
+        conn = self._get_conn()
+        if conn is None:
            return 0
-        cursor = self._conn.cursor()
+        cursor = conn.cursor()
        cursor.execute(sql, params)
-        self._conn.commit()
+        conn.commit()
        return cursor.lastrowid

    def init_schema(self) -> None:
-        if self._conn is None:
+        conn = self._get_conn()
+        if conn is None:
            return
-        cursor = self._conn.cursor()
+        cursor = conn.cursor()
        cursor.execute("""
            CREATE TABLE IF NOT EXISTS td_conversations (
                id INT AUTO_INCREMENT PRIMARY KEY,
+                user_id VARCHAR(50) NOT NULL DEFAULT 'default',
                created_at DATETIME DEFAULT CURRENT_TIMESTAMP
            )
        """)
@@ -55,9 +89,35 @@ class DatabaseService:
                FOREIGN KEY (conversation_id) REFERENCES td_conversations(id)
            )
        """)
-        self._conn.commit()
+        cursor.execute("""
+            CREATE TABLE IF NOT EXISTS td_user_profile (
+                id INT AUTO_INCREMENT PRIMARY KEY,
+                user_id VARCHAR(50) NOT NULL DEFAULT 'default',
+                key_name VARCHAR(100) NOT NULL,
+                value TEXT NOT NULL,
+                updated_at DATETIME DEFAULT CURRENT_TIMESTAMP ON UPDATE CURRENT_TIMESTAMP,
+                UNIQUE KEY uq_user_key (user_id, key_name)
+            )
+        """)
+        conn.commit()
+        self._migrate_schema(conn)
+
+    def _migrate_schema(self, conn) -> None:
+        cursor = conn.cursor()
+        for sql in [
+            "ALTER TABLE td_conversations ADD COLUMN user_id VARCHAR(50) NOT NULL DEFAULT 'default'",
+            "ALTER TABLE td_user_profile ADD COLUMN user_id VARCHAR(50) NOT NULL DEFAULT 'default'",
+            "ALTER TABLE td_user_profile DROP INDEX key_name",
+            "ALTER TABLE td_user_profile ADD UNIQUE KEY uq_user_key (user_id, key_name)",
+        ]:
+            try:
+                cursor.execute(sql)
+                conn.commit()
+            except Exception:
+                pass

    def close(self) -> None:
-        if self._conn:
-            self._conn.close()
-            self._conn = None
+        conn = getattr(self._local, "conn", None)
+        if conn:
+            conn.close()
+            self._local.conn = None
@@ -0,0 +1,31 @@
+from __future__ import annotations
+from services.db.mysql_service import DatabaseService
+
+
+class UserProfileRepository:
+    """td_user_profile 테이블을 통한 사용자 장기 메모리 저장소."""
+
+    def __init__(self, db: DatabaseService):
+        self._db = db
+
+    def remember(self, key: str, value: str, user_id: str = "default") -> None:
+        self._db.execute_write(
+            """INSERT INTO td_user_profile (user_id, key_name, value)
+               VALUES (%s, %s, %s)
+               ON DUPLICATE KEY UPDATE value = VALUES(value), updated_at = NOW()""",
+            (user_id, key, value),
+        )
+
+    def recall(self, key: str, user_id: str = "default") -> str | None:
+        rows = self._db.execute(
+            "SELECT value FROM td_user_profile WHERE user_id = %s AND key_name = %s",
+            (user_id, key),
+        )
+        return rows[0]["value"] if rows else None
+
+    def get_all(self, user_id: str = "default") -> dict[str, str]:
+        rows = self._db.execute(
+            "SELECT key_name, value FROM td_user_profile WHERE user_id = %s ORDER BY updated_at",
+            (user_id,),
+        )
+        return {r["key_name"]: r["value"] for r in rows}