API Reference

Agents

Evaluation Datasets

Copy Markdown

Open in Claude

Open in ChatGPT

Open in Cursor

---

Copy Markdown

View as Markdown

Create Evaluation Dataset

client.agents.evaluationDatasets.create(EvaluationDatasetCreateParams { dataset_type, file_upload_dataset, name } body?, RequestOptionsoptions?): EvaluationDatasetCreateResponse { evaluation_dataset_uuid }

post/v2/gen-ai/evaluation_datasets

To create an evaluation dataset, send a POST request to /v2/gen-ai/evaluation_datasets.

ParametersExpand Collapse

body: EvaluationDatasetCreateParams { dataset_type, file_upload_dataset, name }

dataset_type?: "EVALUATION_DATASET_TYPE_UNKNOWN" | "EVALUATION_DATASET_TYPE_ADK" | "EVALUATION_DATASET_TYPE_NON_ADK"

Accepts one of the following:

"EVALUATION_DATASET_TYPE_UNKNOWN"

"EVALUATION_DATASET_TYPE_ADK"

"EVALUATION_DATASET_TYPE_NON_ADK"

file_upload_dataset?: APIFileUploadDataSource { original_file_name, size_in_bytes, stored_object_key }

File to upload as data source for knowledge base.

original_file_name?: string

The original file name

size_in_bytes?: string

The size of the file in bytes

formatuint64

stored_object_key?: string

The object key the file was stored as

name?: string

The name of the agent evaluation dataset.

ReturnsExpand Collapse

EvaluationDatasetCreateResponse { evaluation_dataset_uuid }

Output for creating an agent evaluation dataset

evaluation_dataset_uuid?: string

Evaluation dataset uuid.

Create Evaluation Dataset

TypeScript

HTTP

TypeScript

Python

Go

import Gradient from '@digitalocean/gradient';

const client = new Gradient({
  accessToken: 'My Access Token',
});

const evaluationDataset = await client.agents.evaluationDatasets.create();

console.log(evaluationDataset.evaluation_dataset_uuid);

200 example

{
  "evaluation_dataset_uuid": "123e4567-e89b-12d3-a456-426614174000"
}

Returns Examples

200 example

{
  "evaluation_dataset_uuid": "123e4567-e89b-12d3-a456-426614174000"
}