From 005234c953b293eeff561734ca5e71ecd4ac8da0 Mon Sep 17 00:00:00 2001
From: Roland Tannous <rolandtannous@gravityq.ai>
Date: Mon, 25 May 2026 15:25:11 +0400
Subject: [PATCH] Studio: route RAG parent-process loggers through structlog

core/rag/db.py, vector_store.py, tool.py, bm25.py, and reranker.py
all run only in the FastAPI parent process. Switch their loggers
from Python stdlib to studio's structlog get_logger so their output
shows up in the same JSON stream as the rest of the backend (the
request_completed / RAG search lines).

embeddings.py and ingestion.py stay on stdlib because they execute
inside the mp.spawn ingestion subprocess, which doesn't inherit the
parent's structlog configuration.
---
 studio/backend/core/rag/bm25.py         | 4 ++--
 studio/backend/core/rag/db.py           | 6 +++---
 studio/backend/core/rag/reranker.py     | 4 ++--
 studio/backend/core/rag/tool.py         | 5 +++--
 studio/backend/core/rag/vector_store.py | 5 +++--
 5 files changed, 13 insertions(+), 11 deletions(-)

diff --git a/studio/backend/core/rag/bm25.py b/studio/backend/core/rag/bm25.py
index c3da6806d6..28b991d168 100644
--- a/studio/backend/core/rag/bm25.py
+++ b/studio/backend/core/rag/bm25.py
@@ -17,15 +17,15 @@ A scope is ``kb_<uuid>`` or ``thread_<uuid>``. Each scope stores:
 from __future__ import annotations
 
 import json
-import logging
 import shutil
 import threading
 from pathlib import Path
 from typing import Any
 
+from loggers import get_logger
 from utils.paths.storage_roots import ensure_dir, rag_bm25_root
 
-logger = logging.getLogger(__name__)
+logger = get_logger(__name__)
 
 _load_lock = threading.Lock()
 _cache: dict[str, tuple[Any, list[str]]] = {}
diff --git a/studio/backend/core/rag/db.py b/studio/backend/core/rag/db.py
index 4fbd238843..1bb05c5fbd 100644
--- a/studio/backend/core/rag/db.py
+++ b/studio/backend/core/rag/db.py
@@ -11,14 +11,14 @@ to the RAG code path only — chat code keeps its plain sqlite handle.
 
 from __future__ import annotations
 
-import logging
 import sqlite3
 import threading
 from pathlib import Path
 
+from loggers import get_logger
 from utils.paths.storage_roots import ensure_dir, rag_root
 
-logger = logging.getLogger(__name__)
+logger = get_logger(__name__)
 
 _conn: sqlite3.Connection | None = None
 _conn_lock = threading.Lock()
@@ -96,7 +96,7 @@ def get_rag_connection() -> sqlite3.Connection:
             _load_sqlite_vec(conn)
             _ensure_schema(conn)
             _conn = conn
-            logger.info("RAG vector store: opened %s", rag_db_path())
+            logger.info("RAG vector store opened", path = str(rag_db_path()))
         return _conn
 
 
diff --git a/studio/backend/core/rag/reranker.py b/studio/backend/core/rag/reranker.py
index 45fc3bb812..1496b2c271 100644
--- a/studio/backend/core/rag/reranker.py
+++ b/studio/backend/core/rag/reranker.py
@@ -17,15 +17,15 @@ replacing the import in ``_load``.
 from __future__ import annotations
 
 import gc
-import logging
 import threading
 from typing import Any
 
+from loggers import get_logger
 from utils.rag.config import RAG_RERANK_BATCH_SIZE, RAG_RERANKER_MODEL
 
 from .retrieval import Hit
 
-logger = logging.getLogger(__name__)
+logger = get_logger(__name__)
 
 _lock = threading.Lock()
 _model: Any | None = None
diff --git a/studio/backend/core/rag/tool.py b/studio/backend/core/rag/tool.py
index 8bd05ce8c9..5ec1f039ef 100644
--- a/studio/backend/core/rag/tool.py
+++ b/studio/backend/core/rag/tool.py
@@ -16,10 +16,11 @@ LLM doesn't need to know about KB UUIDs.
 
 from __future__ import annotations
 
-import logging
 from typing import Any
 
-logger = logging.getLogger(__name__)
+from loggers import get_logger
+
+logger = get_logger(__name__)
 
 
 SEARCH_KNOWLEDGE_BASE_TOOL = {
diff --git a/studio/backend/core/rag/vector_store.py b/studio/backend/core/rag/vector_store.py
index 9517179715..64b1725c45 100644
--- a/studio/backend/core/rag/vector_store.py
+++ b/studio/backend/core/rag/vector_store.py
@@ -20,10 +20,11 @@ scope, so dims within a scope are always consistent.
 from __future__ import annotations
 
 import json
-import logging
 from typing import Iterable
 
-logger = logging.getLogger(__name__)
+from loggers import get_logger
+
+logger = get_logger(__name__)
 
 
 def kb_scope(kb_id: str) -> str: