Datasets

Add rows to a dataset

Add rows to a dataset as its next version. They ask the dataset’s own decisions, worded as it words them, with its kind of supervision. Rows it holds already are left out, and a context it holds keeps its side of the split. Earlier versions stay as they were. With family, one of your families on this dataset, the version records that its page added them: 404 when you have no family of that name, 410 family_deleted when you deleted it, 422 dataset_mismatch when it doesn’t grow on this dataset.

POST

datasets

{dataset_id}

versions

Add rows to a dataset

curl --request POST \
  --url https://console.sqwish.ai/v1/datasets/{dataset_id}/versions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "examples": [
    {
      "context": "<string>",
      "decisions": [
        {
          "id": "<string>",
          "question": "<string>",
          "kind": "single",
          "outcomes": "<unknown>",
          "rubric": [
            "<unknown>"
          ],
          "policy": {
            "action_costs": {},
            "abstain_below": 0.5
          }
        }
      ],
      "model": "<string>",
      "targets": {},
      "rewards": {}
    }
  ],
  "max_price_usd": "<string>",
  "family": "<string>"
}
'

import requests

url = "https://console.sqwish.ai/v1/datasets/{dataset_id}/versions"

payload = {
    "examples": [
        {
            "context": "<string>",
            "decisions": [
                {
                    "id": "<string>",
                    "question": "<string>",
                    "kind": "single",
                    "outcomes": "<unknown>",
                    "rubric": ["<unknown>"],
                    "policy": {
                        "action_costs": {},
                        "abstain_below": 0.5
                    }
                }
            ],
            "model": "<string>",
            "targets": {},
            "rewards": {}
        }
    ],
    "max_price_usd": "<string>",
    "family": "<string>"
}
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({
    examples: [
      {
        context: '<string>',
        decisions: [
          {
            id: '<string>',
            question: '<string>',
            kind: 'single',
            outcomes: '<unknown>',
            rubric: ['<unknown>'],
            policy: {action_costs: {}, abstain_below: 0.5}
          }
        ],
        model: '<string>',
        targets: {},
        rewards: {}
      }
    ],
    max_price_usd: '<string>',
    family: '<string>'
  })
};

fetch('https://console.sqwish.ai/v1/datasets/{dataset_id}/versions', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

{
  "id": "<string>",
  "name": "<string>",
  "created_at": 123,
  "sha256": "<string>",
  "version": 123,
  "status": "validated",
  "rows": 123,
  "contexts": 123,
  "duplicates_removed": 123,
  "method": "sft",
  "augmentation": "none",
  "archived_at": 123,
  "evaluation_only": true,
  "evaluation_fraction": 123,
  "split": {},
  "prompt_tuning": {
    "decisions": [
      {
        "decision": {
          "id": "<string>",
          "question": "<string>",
          "kind": "single",
          "outcomes": "<unknown>",
          "rubric": [
            "<unknown>"
          ],
          "policy": {
            "action_costs": {},
            "abstain_below": 0.5
          }
        },
        "outcomes": [
          "<string>"
        ],
        "rows": 123,
        "labels": {},
        "reason": "conflicting_decision"
      }
    ],
    "unlisted": 123
  },
  "input": {
    "format": "json",
    "sha256": "<string>",
    "bytes": 123
  },
  "labeling": {
    "job_id": "<string>",
    "source_id": "<string>",
    "source_sha256": "<string>",
    "source_input_sha256": "<string>",
    "spec_sha256": "<string>",
    "prompt_version": "<string>",
    "teacher_models": [
      "<string>"
    ],
    "row_indices": [
      123
    ],
    "selection_sha256": "<string>",
    "target_method": "mean_one_hot_teacher_votes"
  },
  "storage_window": {
    "started_at": 123,
    "ends_at": 123,
    "reserved_usd": "<string>"
  },
  "labels_to_check": 123
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "retryable": true,
    "request_id": "<string>",
    "details": [
      {
        "path": [
          "<string>"
        ],
        "message": "<string>",
        "type": "<string>"
      }
    ]
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "retryable": true,
    "request_id": "<string>",
    "details": [
      {
        "path": [
          "<string>"
        ],
        "message": "<string>",
        "type": "<string>"
      }
    ]
  }
}

Authorizations

Authorization

string

header

required

Create an API key in the console. Required when accounts are enabled.

Headers

idempotency-key

string | null

Path Parameters

dataset_id

string

required

Body

application/json

examples

Example · object[]

required

Required array length: 1 - 20000 elements

Show child attributes

max_price_usd

string | null

The most you agree to pay for its first day of storage, which a dataset above the free size holds, in USD, such as the price you were shown. If it costs more when it is admitted, it is refused with price_changed and nothing is held.

Pattern: ^\d{1,9}(\.\d{1,9})?$

family

string | null

The family whose page adds these rows, such as router: one of your families on this dataset. The version records it, so the family can say where its new data came from.

Pattern: ^[a-z](?:-?[a-z0-9]){1,62}$

Response

Successful Response

string

required

name

string

required

created_at

number

required

sha256

string

required

Names every row of the latest version: its first version's file digest, each later one's chained on.

version

integer

required

The latest version. Counts and the split are this version's.

status

string

required

Allowed value: "validated"

rows

integer

required

contexts

integer

required

duplicates_removed

integer

required

method

enum<string>

required

Available options:

sft,

reward

augmentation

string

required

Allowed value: "none"

archived_at

number | null

required

When we archived it: when credit couldn't cover its storage, or on a suspension. Restore it to start new work. Null in the library.

evaluation_only

boolean

required

evaluation_fraction

number

required

split

Split · object

required

Show child attributes

prompt_tuning

PromptTuningReadiness · object

What prompt tuning can tune in the training partition, worked out when the dataset was made. Datasets of outcome scores have none.

Show child attributes

input

InputReceipt · object

Show child attributes

labeling

LabelingLineage · object

Show child attributes

storage_window

StorageWindow · object | null

The day of storage held now, at the price it was accepted at, or null. Archiving or deleting it charges the minutes used of it; later days are priced as they start.

Show child attributes

labels_to_check

integer

How many labels prompt tuning doubted in this dataset that nobody has dismissed, each row and decision once, as its labels-to-check route lists them.

Add rows to a dataset

curl --request POST \
  --url https://console.sqwish.ai/v1/datasets/{dataset_id}/versions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "examples": [
    {
      "context": "<string>",
      "decisions": [
        {
          "id": "<string>",
          "question": "<string>",
          "kind": "single",
          "outcomes": "<unknown>",
          "rubric": [
            "<unknown>"
          ],
          "policy": {
            "action_costs": {},
            "abstain_below": 0.5
          }
        }
      ],
      "model": "<string>",
      "targets": {},
      "rewards": {}
    }
  ],
  "max_price_usd": "<string>",
  "family": "<string>"
}
'

import requests

url = "https://console.sqwish.ai/v1/datasets/{dataset_id}/versions"

payload = {
    "examples": [
        {
            "context": "<string>",
            "decisions": [
                {
                    "id": "<string>",
                    "question": "<string>",
                    "kind": "single",
                    "outcomes": "<unknown>",
                    "rubric": ["<unknown>"],
                    "policy": {
                        "action_costs": {},
                        "abstain_below": 0.5
                    }
                }
            ],
            "model": "<string>",
            "targets": {},
            "rewards": {}
        }
    ],
    "max_price_usd": "<string>",
    "family": "<string>"
}
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({
    examples: [
      {
        context: '<string>',
        decisions: [
          {
            id: '<string>',
            question: '<string>',
            kind: 'single',
            outcomes: '<unknown>',
            rubric: ['<unknown>'],
            policy: {action_costs: {}, abstain_below: 0.5}
          }
        ],
        model: '<string>',
        targets: {},
        rewards: {}
      }
    ],
    max_price_usd: '<string>',
    family: '<string>'
  })
};

fetch('https://console.sqwish.ai/v1/datasets/{dataset_id}/versions', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

{
  "id": "<string>",
  "name": "<string>",
  "created_at": 123,
  "sha256": "<string>",
  "version": 123,
  "status": "validated",
  "rows": 123,
  "contexts": 123,
  "duplicates_removed": 123,
  "method": "sft",
  "augmentation": "none",
  "archived_at": 123,
  "evaluation_only": true,
  "evaluation_fraction": 123,
  "split": {},
  "prompt_tuning": {
    "decisions": [
      {
        "decision": {
          "id": "<string>",
          "question": "<string>",
          "kind": "single",
          "outcomes": "<unknown>",
          "rubric": [
            "<unknown>"
          ],
          "policy": {
            "action_costs": {},
            "abstain_below": 0.5
          }
        },
        "outcomes": [
          "<string>"
        ],
        "rows": 123,
        "labels": {},
        "reason": "conflicting_decision"
      }
    ],
    "unlisted": 123
  },
  "input": {
    "format": "json",
    "sha256": "<string>",
    "bytes": 123
  },
  "labeling": {
    "job_id": "<string>",
    "source_id": "<string>",
    "source_sha256": "<string>",
    "source_input_sha256": "<string>",
    "spec_sha256": "<string>",
    "prompt_version": "<string>",
    "teacher_models": [
      "<string>"
    ],
    "row_indices": [
      123
    ],
    "selection_sha256": "<string>",
    "target_method": "mean_one_hot_teacher_votes"
  },
  "storage_window": {
    "started_at": 123,
    "ends_at": 123,
    "reserved_usd": "<string>"
  },
  "labels_to_check": 123
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "retryable": true,
    "request_id": "<string>",
    "details": [
      {
        "path": [
          "<string>"
        ],
        "message": "<string>",
        "type": "<string>"
      }
    ]
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "retryable": true,
    "request_id": "<string>",
    "details": [
      {
        "path": [
          "<string>"
        ],
        "message": "<string>",
        "type": "<string>"
      }
    ]
  }
}

Overview

Decisions

Models

Families

Datasets

Evaluations

Fine-tuning

Prompt tuning

Labeling

Accounts

Billing

Integrations

System

Add rows to a dataset

Authorizations

Headers

Path Parameters

Body

Response