Skip to content
Adaption
Get started
API Reference
Datasets

Get a dataset by ID

client.datasets.get(stringdatasetID, RequestOptionsoptions?): Dataset { configured_column_mapping, created_at, dataset_id, 8 more }
GET/api/v1/datasets/{dataset_id}

Get a dataset by ID

ParametersExpand Collapse
datasetID: string
ReturnsExpand Collapse
Dataset { configured_column_mapping, created_at, dataset_id, 8 more }
configured_column_mapping: ConfiguredColumnMapping | null

User-configured column mapping. Null if not yet configured.

chat: string | null
completion: string | null
context: Array<string>
prompt: string | null
created_at: string

Timestamp when the dataset was created

formatdate-time
dataset_id: string

Unique dataset identifier

error: Error | null

Error details if the dataset failed. Null otherwise.

message: string

Error message

evaluation_summary: EvaluationSummary | null

Compact evaluation summary. Null if evaluation has not completed.

grade_after: string | null

Letter grade (A-E) after augmentation

grade_before: string | null

Letter grade (A-E) before augmentation

improvement_percent: number | null

Relative improvement percentage

score_after: number | null

Quality score after augmentation

score_before: number | null

Quality score before augmentation

name: string | null

Human-readable name for the dataset

progress: Progress | null

Processing progress. Null when no run is active.

percent: number | null

Progress percentage (0-100)

processed_rows: number | null

Number of rows processed so far

total_rows: number | null

Total rows to process (samples_to_process or row_count)

row_count: number | null

Total number of rows in the dataset

run_id: string | null

ID of the currently active run

status: "pending" | "running" | "succeeded" | "failed"

Lifecycle status: pending, running, succeeded, or failed

One of the following:
"pending"
"running"
"succeeded"
"failed"
updated_at: string

Timestamp of the last update

formatdate-time

Get a dataset by ID

import Adaption from 'adaption';

const client = new Adaption({
  apiKey: process.env['ADAPTION_API_KEY'], // This is the default and can be omitted
});

const dataset = await client.datasets.get('dataset_id');

console.log(dataset.dataset_id);
{
  "configured_column_mapping": {
    "chat": "chat",
    "completion": "completion",
    "context": [
      "string"
    ],
    "prompt": "prompt"
  },
  "created_at": "2019-12-27T18:11:19.117Z",
  "dataset_id": "dataset_id",
  "error": {
    "message": "message"
  },
  "evaluation_summary": {
    "grade_after": "grade_after",
    "grade_before": "grade_before",
    "improvement_percent": 0,
    "score_after": 0,
    "score_before": 0
  },
  "name": "name",
  "progress": {
    "percent": 0,
    "processed_rows": 0,
    "total_rows": 0
  },
  "row_count": 0,
  "run_id": "run_id",
  "status": "pending",
  "updated_at": "2019-12-27T18:11:19.117Z"
}
Returns Examples
{
  "configured_column_mapping": {
    "chat": "chat",
    "completion": "completion",
    "context": [
      "string"
    ],
    "prompt": "prompt"
  },
  "created_at": "2019-12-27T18:11:19.117Z",
  "dataset_id": "dataset_id",
  "error": {
    "message": "message"
  },
  "evaluation_summary": {
    "grade_after": "grade_after",
    "grade_before": "grade_before",
    "improvement_percent": 0,
    "score_after": 0,
    "score_before": 0
  },
  "name": "name",
  "progress": {
    "percent": 0,
    "processed_rows": 0,
    "total_rows": 0
  },
  "row_count": 0,
  "run_id": "run_id",
  "status": "pending",
  "updated_at": "2019-12-27T18:11:19.117Z"
}