API Reference

Agents

Evaluation Datasets

Copy Markdown

Open in Claude

Open in ChatGPT

Open in Cursor

---

Copy Markdown

View as Markdown

Create Evaluation Dataset

agents.evaluation_datasets.create(EvaluationDatasetCreateParams**kwargs) -> EvaluationDatasetCreateResponse

post/v2/gen-ai/evaluation_datasets

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

ParametersExpand Collapse

dataset_type: Optional[Literal["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: Optional[APIFileUploadDataSourceParam]

File to upload as data source for knowledge base.

original_file_name: Optional[str]

The original file name

size_in_bytes: Optional[str]

The size of the file in bytes

formatuint64

stored_object_key: Optional[str]

The object key the file was stored as

name: Optional[str]

The name of the agent evaluation dataset.

ReturnsExpand Collapse

class EvaluationDatasetCreateResponse: …

Output for creating an agent evaluation dataset

evaluation_dataset_uuid: Optional[str]

Evaluation dataset uuid.

Create Evaluation Dataset

Python

HTTP

TypeScript

Python

Go

from gradient import Gradient

client = Gradient(
    access_token="My Access Token",
)
evaluation_dataset = client.agents.evaluation_datasets.create()
print(evaluation_dataset.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"
}