feat: add tqdm progress bar to VLM conversion and download benchmark test

studio/backend/utils/datasets/format_conversion.py

@@ -332,20 +332,26 @@ def convert_to_vlm_format(
     has_urls = isinstance(next(iter(dataset))[image_column], str)
     probe_needed = has_urls and total > PROBE_SIZE
 
+    from tqdm import tqdm
+
     print(f"🔄 Converting {total} samples to VLM format...")
     converted_list = []
     failed_count = 0
 
-    for i, sample in enumerate(dataset):
+    pbar = tqdm(dataset, total=total, desc="Converting VLM samples", unit="sample")
+    for i, sample in enumerate(pbar):
         try:
             converted_list.append(_convert_single_sample(sample))
         except Exception as e:
             failed_count += 1
 
+        pbar.set_postfix(ok=len(converted_list), failed=failed_count, refresh=False)
+
         # Early exit check after probing the first batch
         if probe_needed and (i + 1) == PROBE_SIZE:
             fail_rate = failed_count / PROBE_SIZE
             if fail_rate >= MAX_FAIL_RATE:
+                pbar.close()
                 raise ValueError(
                     f"{fail_rate:.0%} of the first {PROBE_SIZE} images failed to download "
                     f"({failed_count}/{PROBE_SIZE}). "
@@ -353,6 +359,7 @@ def convert_to_vlm_format(
                     "Consider using a dataset with embedded images instead."
                 )
             print(f"✅ Probe passed: {failed_count}/{PROBE_SIZE} ({fail_rate:.0%}) failures in first batch, continuing...")
+    pbar.close()
 
     if failed_count > 0:
         fail_rate = failed_count / total

studio/tests/test_url_download_benchmark.py

@@ -0,0 +1,54 @@
+"""
+Benchmark: fsspec URL image download throughput at different dataset sizes.
+Dataset: google-research-datasets/conceptual_captions (subset: labeled)
+
+Tests sizes: 100, 200, 300, 500, 1000, 1500, 2000
+Reports: time, success/fail rate, throughput (images/sec)
+"""
+from datasets import load_dataset, Dataset
+from PIL import Image as PILImage
+from io import BytesIO
+from itertools import islice
+import fsspec
+import time
+
+DATASET = "google-research-datasets/conceptual_captions"
+SUBSET = "labeled"
+SPLIT = "train"
+SIZES = [100, 200, 300, 500, 1000, 1500, 2000]
+
+# Load the max we need in one go
+max_size = max(SIZES)
+print(f"Loading {max_size} samples from {DATASET} (streaming)...")
+ds = load_dataset(DATASET, name=SUBSET, split=SPLIT, streaming=True)
+rows = list(islice(ds, max_size))
+full_dataset = Dataset.from_list(rows)
+print(f"Loaded {len(full_dataset)} samples")
+print(f"Columns: {full_dataset.column_names}")
+print()
+
+print(f"{'Size':>6} | {'Time':>8} | {'OK':>6} | {'Fail':>6} | {'Fail%':>6} | {'img/s':>7}")
+print("-" * 55)
+
+for size in SIZES:
+    dataset = full_dataset.select(range(size))
+    success, fail = 0, 0
+    t0 = time.time()
+
+    for sample in dataset:
+        url = sample["image_url"]
+        try:
+            with fsspec.open(url, "rb", expand=True) as f:
+                img = PILImage.open(BytesIO(f.read())).convert("RGB")
+            success += 1
+        except Exception:
+            fail += 1
+
+    elapsed = time.time() - t0
+    fail_pct = (fail / size) * 100
+    throughput = success / elapsed if elapsed > 0 else 0
+
+    print(f"{size:>6} | {elapsed:>7.1f}s | {success:>6} | {fail:>6} | {fail_pct:>5.1f}% | {throughput:>6.1f}/s")
+
+print()
+print("Done.")