refactor: improve transcript list performance (#480)

* refactor: improve transcript list performance

* fix: sync openapi

* fix: frontend types

* fix: remove drop table _alembic_tmp_meeting

* fix: remove create table too

* fix: remove uq_recording_object_key

server/reflector/db/meetings.py

@@ -40,6 +40,7 @@ meetings = sa.Table(
         nullable=False,
         server_default=sa.true(),
     ),
+    sa.Index("idx_meeting_room_id", "room_id"),
 )
 
 meeting_consent = sa.Table(

server/reflector/db/recordings.py

@@ -20,6 +20,7 @@ recordings = sa.Table(
         server_default="pending",
     ),
     sa.Column("meeting_id", sa.String),
+    sa.Index("idx_recording_meeting_id", "meeting_id"),
 )
 
 

server/reflector/db/rooms.py

@@ -39,6 +39,7 @@ rooms = sqlalchemy.Table(
     sqlalchemy.Column(
         "is_shared", sqlalchemy.Boolean, nullable=False, server_default=false()
     ),
+    sqlalchemy.Index("idx_room_is_shared", "is_shared"),
 )
 
 

server/reflector/db/transcripts.py

@@ -6,7 +6,6 @@ from contextlib import asynccontextmanager
 from datetime import datetime
 from pathlib import Path
 from typing import Any, Literal
-from reflector.utils import generate_uuid4
 
 import sqlalchemy
 from fastapi import HTTPException
@@ -15,6 +14,7 @@ from reflector.db import database, metadata
 from reflector.processors.types import Word as ProcessorWord
 from reflector.settings import settings
 from reflector.storage import get_transcripts_storage
+from reflector.utils import generate_uuid4
 from sqlalchemy import Enum
 from sqlalchemy.sql import false, or_
 
@@ -74,6 +74,9 @@ transcripts = sqlalchemy.Table(
     # the main "audio deleted" is the presence of the audio itself / consents not-given
     # same field could've been in recording/meeting, and it's maybe even ok to dupe it at need
     sqlalchemy.Column("audio_deleted", sqlalchemy.Boolean, nullable=True),
+    sqlalchemy.Index("idx_transcript_recording_id", "recording_id"),
+    sqlalchemy.Index("idx_transcript_user_id", "user_id"),
+    sqlalchemy.Index("idx_transcript_created_at", "created_at"),
 )
 
 
@@ -306,6 +309,7 @@ class TranscriptController:
         room_id: str | None = None,
         search_term: str | None = None,
         return_query: bool = False,
+        exclude_columns: list[str] = ["topics", "events", "participants"],
     ) -> list[Transcript]:
         """
         Get all transcripts
@@ -348,9 +352,14 @@ class TranscriptController:
         if search_term:
             query = query.where(transcripts.c.title.ilike(f"%{search_term}%"))
 
+        # Exclude heavy JSON columns from list queries
+        transcript_columns = [
+            col for col in transcripts.c if col.name not in exclude_columns
+        ]
+
         query = query.with_only_columns(
-            [
-                transcripts,
+            transcript_columns
+            + [
                 rooms.c.id.label("room_id"),
                 rooms.c.name.label("room_name"),
             ]

server/reflector/views/transcripts.py

@@ -45,7 +45,7 @@ def create_access_token(data: dict, expires_delta: timedelta):
 # ==============================================================
 
 
-class GetTranscript(BaseModel):
+class GetTranscriptMinimal(BaseModel):
     id: str
     user_id: str | None
     name: str
@@ -59,7 +59,6 @@ class GetTranscript(BaseModel):
     share_mode: str = Field("private")
     source_language: str | None
     target_language: str | None
-    participants: list[TranscriptParticipant] | None
     reviewed: bool
     meeting_id: str | None
     source_kind: SourceKind
@@ -68,6 +67,10 @@ class GetTranscript(BaseModel):
     audio_deleted: bool | None = None
 
 
+class GetTranscript(GetTranscriptMinimal):
+    participants: list[TranscriptParticipant] | None
+
+
 class CreateTranscript(BaseModel):
     name: str
     source_language: str = Field("en")
@@ -90,7 +93,7 @@ class DeletionStatus(BaseModel):
     status: str
 
 
-@router.get("/transcripts", response_model=Page[GetTranscript])
+@router.get("/transcripts", response_model=Page[GetTranscriptMinimal])
 async def transcripts_list(
     user: Annotated[Optional[auth.UserInfo], Depends(auth.current_user_optional)],
     source_kind: SourceKind | None = None,