Connect dataset source - Veri Documentation

POST

/

v1

/

datasets

/

connect

Connect dataset source

curl --request POST \
  --url https://api.veri.studio/v1/datasets/connect \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "name": "<string>",
  "source_type": "<string>",
  "huggingface_dataset": "<string>",
  "huggingface_config": "<unknown>",
  "volume": "<string>",
  "volume_path": "<string>",
  "credentials": "<unknown>"
}
'

import requests

url = "https://api.veri.studio/v1/datasets/connect"

payload = {
    "name": "<string>",
    "source_type": "<string>",
    "huggingface_dataset": "<string>",
    "huggingface_config": "<unknown>",
    "volume": "<string>",
    "volume_path": "<string>",
    "credentials": "<unknown>"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    name: '<string>',
    source_type: '<string>',
    huggingface_dataset: '<string>',
    huggingface_config: '<unknown>',
    volume: '<string>',
    volume_path: '<string>',
    credentials: '<unknown>'
  })
};

fetch('https://api.veri.studio/v1/datasets/connect', 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

Authorization

string

header

required

API key with the vk_ prefix. Create one from the dashboard.

Body

application/json

name

string

required

source_type

string

required

huggingface_dataset

string | null

huggingface_config

any

volume

string | null

volume_path

string | null

credentials

any

Response

The connected (or existing, on identical config) dataset

object

string

required

id

string

required

name

string

required

created_at

string<date-time>

required

source_type

string

source_uri

string | null

huggingface_dataset

string | null

num_rows

integer<int32> | null

format

string | null

Locked row format (prompt | preference | completion | chat). Null on a legacy dataset until its first append locks it.

head_row

integer<int64>

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.

auto_snapshot_rows

integer<int32> | null

"cut a snapshot every N new rows" rule; null = off.

latest_snapshot_id

string | null

Newest snapshot id ("@snap-N"); populated by GET /v1/datasets/{id}.

unsnapshotted_rows

integer<int64> | null

Rows appended since the newest snapshot; populated by GET /v1/datasets/{id}.

snapshot_count

integer<int64> | null

Connect dataset source

curl --request POST \
  --url https://api.veri.studio/v1/datasets/connect \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "name": "<string>",
  "source_type": "<string>",
  "huggingface_dataset": "<string>",
  "huggingface_config": "<unknown>",
  "volume": "<string>",
  "volume_path": "<string>",
  "credentials": "<unknown>"
}
'

import requests

url = "https://api.veri.studio/v1/datasets/connect"

payload = {
    "name": "<string>",
    "source_type": "<string>",
    "huggingface_dataset": "<string>",
    "huggingface_config": "<unknown>",
    "volume": "<string>",
    "volume_path": "<string>",
    "credentials": "<unknown>"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    name: '<string>',
    source_type: '<string>',
    huggingface_dataset: '<string>',
    huggingface_config: '<unknown>',
    volume: '<string>',
    volume_path: '<string>',
    credentials: '<unknown>'
  })
};

fetch('https://api.veri.studio/v1/datasets/connect', 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
}