folder/train/dog/golden_retriever.mp4
folder/train/dog/german_shepherd.mp4
folder/train/dog/chihuahua.mp4

folder/train/cat/maine_coon.mp4
folder/train/cat/bengal.mp4
folder/train/cat/birman.mp4

>>> from datasets import load_dataset

>>> dataset = load_dataset("path/to/folder")

>>> dataset = load_dataset("videofolder", data_dir="/path/to/folder")

folder/train/dog/golden_retriever.mp4
folder/train/cat/maine_coon.mp4
folder/test/dog/german_shepherd.mp4
folder/test/cat/bengal.mp4

folder/train/metadata.csv
folder/train/0001.mp4
folder/train/0002.mp4
folder/train/0003.mp4

file_name,additional_feature
0001.mp4,This is a first value of a text feature you added to your videos
0002.mp4,This is a second value of a text feature you added to your videos
0003.mp4,This is a third value of a text feature you added to your videos

{"file_name": "0001.mp4", "additional_feature": "This is a first value of a text feature you added to your videos"}
{"file_name": "0002.mp4", "additional_feature": "This is a second value of a text feature you added to your videos"}
{"file_name": "0003.mp4", "additional_feature": "This is a third value of a text feature you added to your videos"}

{"input_file_name": "0001.mp4", "output_file_name": "0001_output.mp4"}
{"input_file_name": "0002.mp4", "output_file_name": "0002_output.mp4"}
{"input_file_name": "0003.mp4", "output_file_name": "0003_output.mp4"}

{"videos_file_names": ["0001_left.mp4", "0001_right.mp4"], "label": "moving_up"}
{"videos_file_names": ["0002_left.mp4", "0002_right.mp4"], "label": "moving_down"}
{"videos_file_names": ["0003_left.mp4", "0003_right.mp4"], "label": "moving_right"}

file_name,text
0001.mp4,This is a golden retriever playing with a ball
0002.mp4,A german shepherd
0003.mp4,One chihuahua

>>> dataset = load_dataset("videofolder", data_dir="/path/to/folder", split="train")
>>> dataset[0]["text"]
"This is a golden retriever playing with a ball"

from huggingface_hub import HfApi
api = HfApi()

api.upload_folder(
    folder_path="/path/to/local/dataset",
    repo_id="username/my-cool-dataset",
    repo_type="dataset",
)

folder/train/00000.tar
folder/train/00001.tar
folder/train/00002.tar
...

e39871fd9fd74f55.mp4
e39871fd9fd74f55.json
f18b91585c4d3f3e.mp4
f18b91585c4d3f3e.json
ede6e66b2fb59aab.mp4
ede6e66b2fb59aab.json
ed600d57fcee4f94.mp4
ed600d57fcee4f94.json
...

>>> from datasets import load_dataset

>>> dataset = load_dataset("webdataset", data_dir="/path/to/folder", split="train")
>>> dataset[0]["json"]
{"bbox": [[302.0, 109.0, 73.0, 52.0]], "categories": [0]}

+------------------------------------------+-----------------+-----+------------------------------------------+
| caption                                  | aesthetic_score | ... | video_blob                               |
+------------------------------------------+-----------------+-----+------------------------------------------+
| "a breathtaking view of a mounta..."     | 5.2401          | ... | {position: 0, size: 4873879}             |
| "a captivating view of the sun, b..."    | 5.2401          | ... | {position: 4873920, size: 3370571}       |
+------------------------------------------+-----------------+-----+------------------------------------------+

import lance
import pyarrow as pa

import urllib.request

schema = pa.schema(
    [
        pa.field("caption", pa.utf8()),
        pa.field("aesthetic_score", pa.float64()),
        pa.field(
            "video_blob",
            pa.large_binary(),
            metadata={"lance-encoding:blob": "true"},
        ),
    ]
)

# Provide video files alongside metadata
rows = [
    {
        "video_path": "/path/to/videos/0001.mp4",
        "caption": "a breathtaking view of a mountainous landscape ...",
        "aesthetic_score": 5.240138053894043,
    },
    {
        "video_path": "0002.mp4",
        "caption": "a captivating view of the sun, bathed in hues ...",
        "aesthetic_score": 5.240137100219727,
    },
]

video_bytes = []
for r in rows:
    with open(r["video_path"], "rb") as f:
        video_bytes.append(f.read())

table = pa.table(
    {
        "caption": [r["caption"] for r in rows],
        "aesthetic_score": [r["aesthetic_score"] for r in rows],
        "video_blob": video_bytes,
    },
    schema=schema,
)

ds = lance.write_dataset(
    table,
    "./videos.lance",
    schema=schema,
    mode="create",
)

+------------------------------------------+-----------------+-----+------------------------------------------+
| caption                                  | aesthetic_score | ... | video_blob                               |
+------------------------------------------+-----------------+-----+------------------------------------------+
| "a breathtaking view of a mounta..."     | 5.2401          | ... | {position: 0, size: 4873879}             |
| "a captivating view of the sun, b..."    | 5.2401          | ... | {position: 4873920, size: 3370571}       |
+------------------------------------------+-----------------+-----+------------------------------------------+

MAX_BYTES_PER_FILE = 5 * 1024 * 1024 * 1024  # ~5 GB per file

# Write as Lance dataset with file size limits for each *.lance file
ds = lance.write_dataset(
    table,
    "./videos.lance",
    schema=schema,
    mode="create",
    max_bytes_per_file=MAX_BYTES_PER_FILE,
)