backend/app/tasks/ml.py

@@ -35,8 +35,8 @@ def _is_video(path: Path) -> bool:
     retry_backoff_max=60,
     retry_jitter=True,
     max_retries=3,
-    # Sized for the video branch: sample 10 frames, run tagger +
-    # embedder on each (≈20 GPU ops vs 2 for an image). A loaded
+    # Sized for the video branch: sample 6 frames, run tagger +
+    # embedder on each (≈12 GPU ops vs 2 for an image). A loaded
     # ml-worker can take 5-10 min on a long video; bumped from
     # 5min/7min on 2026-05-28 after operator-flagged image 6288 (a
     # .mp4) hit the recovery sweep at 5 min while still legitimately
@@ -50,7 +50,7 @@ def tag_and_embed(self, image_id: int) -> dict:
     then enqueue per-image allowlist application.
 
     Video: sample frames between 10% and 90% of duration (VIDEO_ML_FRAMES,
-    default 10). Max-pool tagger confidences across frames, mean-pool the
+    default 6). Max-pool tagger confidences across frames, mean-pool the
     SigLIP embeddings. On no-frames returns status='no_frames' (not an error).
     """
     import os
@@ -116,7 +116,7 @@ def tag_and_embed(self, image_id: int) -> dict:
                 phase = "video_sample_frames"
                 t0 = time.monotonic()
                 frames = _sample_video_frames(
-                    src, int(os.environ.get("VIDEO_ML_FRAMES", "10"))
+                    src, int(os.environ.get("VIDEO_ML_FRAMES", "6"))
                 )
                 log.info(
                     "tag_and_embed sampled %d frame(s) in %.1fs: %s",