Get dataset
curl --request GET \
--url https://api.veri.studio/v1/datasets/{dataset_id} \
--header 'Authorization: Bearer <token>'import requests
url = "https://api.veri.studio/v1/datasets/{dataset_id}"
headers = {"Authorization": "Bearer <token>"}
response = requests.get(url, headers=headers)
print(response.text)const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};
fetch('https://api.veri.studio/v1/datasets/{dataset_id}', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));{
"object": "<string>",
"id": "<string>",
"name": "<string>",
"created_at": "2023-11-07T05:31:56Z",
"source_type": "<string>",
"source_uri": "<string>",
"huggingface_dataset": "<string>",
"num_rows": 123,
"format": "<string>",
"head_row": 123,
"auto_snapshot_rows": 123,
"latest_snapshot_id": "<string>",
"unsnapshotted_rows": 123,
"snapshot_count": 123
}Authorizations
API key with the vk_ prefix. Create one from the dashboard.
Path Parameters
Dataset ID
Response
The dataset
Row format. A stream's locked format (prompt | preference | completion |
chat | eval); an upload records its first row's shape, which adds
chat_no_prompt (chat rows without a prompt, still locked as chat), text,
sharegpt and alpaca (no lock). Job submit refuses GRPO on chat_no_prompt,
text, sharegpt and alpaca rows. Null on Hugging Face / volume sources, and
on a legacy dataset until its first append locks it.
Highest row_id appended so far (0 = empty stream). Includes supersede and tombstone entries, so it is the log length, not the live row count.
"cut a snapshot every N new rows" rule; null = off.
Newest snapshot id ("@snap-N"); populated by GET /v1/datasets/{id}.
Rows appended since the newest snapshot; populated by GET /v1/datasets/{id}.
curl --request GET \
--url https://api.veri.studio/v1/datasets/{dataset_id} \
--header 'Authorization: Bearer <token>'import requests
url = "https://api.veri.studio/v1/datasets/{dataset_id}"
headers = {"Authorization": "Bearer <token>"}
response = requests.get(url, headers=headers)
print(response.text)const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};
fetch('https://api.veri.studio/v1/datasets/{dataset_id}', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));{
"object": "<string>",
"id": "<string>",
"name": "<string>",
"created_at": "2023-11-07T05:31:56Z",
"source_type": "<string>",
"source_uri": "<string>",
"huggingface_dataset": "<string>",
"num_rows": 123,
"format": "<string>",
"head_row": 123,
"auto_snapshot_rows": 123,
"latest_snapshot_id": "<string>",
"unsnapshotted_rows": 123,
"snapshot_count": 123
}