From 55543be3b0918160ec437d5ddae760af7f074c8a Mon Sep 17 00:00:00 2001
From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com>
Date: Mon, 2 Mar 2026 13:39:10 +0000
Subject: [PATCH] fix(similarity): address code review - column-only queries,
 configurable batch size, WCAG touch targets

- Use column-only query in embeddings overview to reduce memory for 100K+ files
- Add embedding_backfill_batch_size config setting (default 50)
- Fix WCAG touch target on backfill button (min-height/min-width 44px)
- Add inline comment explaining 3 chars/token truncation estimate
- Import settings in compute_embedding task for configurable batch size

Co-authored-by: christianlouis <361235+christianlouis@users.noreply.github.com>
---
 app/api/similarity.py                        | 12 +++++++++++-
 app/config.py                                |  7 +++++++
 app/tasks/compute_embedding.py               |  3 ++-
 app/utils/similarity.py                      |  4 ++--
 frontend/templates/similarity_dashboard.html |  2 +-
 5 files changed, 23 insertions(+), 5 deletions(-)

diff --git a/app/api/similarity.py b/app/api/similarity.py
index 26bb7dc6..e7b5f844 100644
--- a/app/api/similarity.py
+++ b/app/api/similarity.py
@@ -257,7 +257,17 @@ def get_embeddings_overview(
     }
     ```
     """
-    all_files = db.query(FileRecord).order_by(FileRecord.id.desc()).all()
+    # Use column-only query to avoid loading full ORM objects into memory
+    all_files = (
+        db.query(
+            FileRecord.id,
+            FileRecord.original_filename,
+            FileRecord.ocr_text,
+            FileRecord.embedding,
+        )
+        .order_by(FileRecord.id.desc())
+        .all()
+    )
 
     files_info = []
     total_with_ocr = 0
diff --git a/app/config.py b/app/config.py
index df5e60bc..91f2237d 100644
--- a/app/config.py
+++ b/app/config.py
@@ -339,6 +339,13 @@ class Settings(BaseSettings):
             "Set this below the model's context window (e.g. 8000 for an 8192-token model)."
         ),
     )
+    embedding_backfill_batch_size: int = Field(
+        default=50,
+        description=(
+            "Maximum number of files to queue for embedding computation per "
+            "backfill run.  Keeps the worker and embedding API load bounded."
+        ),
+    )
 
     # Text quality check - AI-based assessment of embedded PDF text
     enable_text_quality_check: bool = Field(
diff --git a/app/tasks/compute_embedding.py b/app/tasks/compute_embedding.py
index fedc6585..50fc3cd6 100644
--- a/app/tasks/compute_embedding.py
+++ b/app/tasks/compute_embedding.py
@@ -9,6 +9,7 @@ import logging
 from datetime import datetime, timezone
 
 from app.celery_app import celery
+from app.config import settings
 from app.database import SessionLocal
 from app.models import FileRecord
 from app.tasks.retry_config import BaseTaskWithRetry
@@ -145,7 +146,7 @@ def backfill_missing_embeddings(self) -> dict:
     Returns:
         A dict with the number of tasks ``queued``.
     """
-    batch_size = 50  # max files to queue per run
+    batch_size = settings.embedding_backfill_batch_size
     task_id = self.request.id
     logger.info("[%s] Backfill: scanning for files missing embeddings (batch_size=%d)", task_id, batch_size)
 
diff --git a/app/utils/similarity.py b/app/utils/similarity.py
index b5948719..590084e1 100644
--- a/app/utils/similarity.py
+++ b/app/utils/similarity.py
@@ -59,8 +59,8 @@ def generate_embedding(text: str, model: str | None = None) -> list[float]:
         model = settings.embedding_model
 
     # Truncate to stay within the model's context window.
-    # Use a conservative estimate of ~3 characters per token so that the
-    # resulting text fits comfortably within ``embedding_max_tokens``.
+    # Conservative 3 chars/token estimate (actual ratio varies by language;
+    # English averages ~4 chars/token but 3 gives a safety margin).
     max_chars = settings.embedding_max_tokens * 3
     if len(text) > max_chars:
         logger.debug(
diff --git a/frontend/templates/similarity_dashboard.html b/frontend/templates/similarity_dashboard.html
index 1fdf2c9a..1090ce3a 100644
--- a/frontend/templates/similarity_dashboard.html
+++ b/frontend/templates/similarity_dashboard.html
@@ -133,7 +133,7 @@
     <strong>{{ files_missing_embedding }}</strong> file(s) have OCR text but no embedding yet.
     The background task will compute them automatically every 5 minutes, or you can
     <button onclick="triggerBackfill()" id="backfill-btn"
-            style="background: #d97706; color: white; border: none; padding: 0.2rem 0.6rem; border-radius: 0.25rem; cursor: pointer; font-size: 0.8rem;"
+            style="background: #d97706; color: white; border: none; padding: 0.2rem 0.6rem; border-radius: 0.25rem; cursor: pointer; font-size: 0.8rem; min-height: 44px; min-width: 44px;"
             aria-label="Trigger embedding computation for all files missing embeddings">
       trigger it now
     </button>.