From 1c87a4400c8d4ad4b4ea771f3db84324473b08f9 Mon Sep 17 00:00:00 2001 From: Roland Tannous Date: Mon, 9 Mar 2026 22:00:20 +0000 Subject: [PATCH] fix: prefer tabular files over archives in Tier 1 dataset preview Tier 1 check-format was picking images.zip over testmini.parquet, causing wrong columns (image/label) and broken VLM mapping. Also log first VLM conversion failure instead of swallowing silently. --- studio/backend/utils/datasets/format_conversion.py | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/studio/backend/utils/datasets/format_conversion.py b/studio/backend/utils/datasets/format_conversion.py index fea2589489..83fb23ef82 100644 --- a/studio/backend/utils/datasets/format_conversion.py +++ b/studio/backend/utils/datasets/format_conversion.py @@ -505,6 +505,8 @@ def convert_to_vlm_format( batch_results[idx] = future.result() except Exception as e: failed_count += 1 + if failed_count == 1: + print(f"⚠️ First VLM conversion failure: {type(e).__name__}: {e}") if failed_count == 1: logger.info(f"⚠️ First VLM conversion failure: {type(e).__name__}: {e}") @@ -525,8 +527,12 @@ def convert_to_vlm_format( for sample in pbar: try: converted_list.append(_convert_single_sample(sample)) + except Exception as e: except Exception as e: failed_count += 1 + if failed_count == 1: + # Log the first failure to aid debugging + print(f"⚠️ First VLM conversion failure: {type(e).__name__}: {e}") if failed_count == 1: # Log the first failure to aid debugging logger.info(f"⚠️ First VLM conversion failure: {type(e).__name__}: {e}")