Implementation:Confident ai Deepeval EvaluationDataset Push
| Sources | Domains | Last Updated |
|---|---|---|
| DeepEval | Synthetic_Data, LLM_Evaluation, Data_Management | 2026-02-14 09:00 GMT |
Overview
The push method on the EvaluationDataset class publishes evaluation data to the Confident AI cloud platform, enabling collaborative review and centralized dataset management.
Description
push uploads the contents of an EvaluationDataset (its goldens) to the Confident AI platform under a specified alias. The alias parameter serves as the dataset identifier on the platform, and the finalized flag indicates whether the dataset is ready for evaluation use or still under review. Once pushed, the dataset is accessible through the Confident AI web dashboard for review, annotation, and programmatic retrieval.
Usage
Call this method after populating an EvaluationDataset with goldens to publish the data to the Confident AI platform for team-wide access and review.
Code Reference
Source Location: Repository: confident-ai/deepeval, File: deepeval/dataset/dataset.py (L717-751)
Signature:
def push(
self,
alias: str,
finalized: bool = True,
):
...
Import:
from deepeval.dataset import EvaluationDataset
I/O Contract
Inputs:
| Parameter | Type | Required | Description |
|---|---|---|---|
| alias | str | Yes | Dataset name/identifier on the Confident AI platform |
| finalized | bool | No | Whether the dataset is finalized and ready for use (default: True) |
Outputs:
- Dataset is uploaded and published on the Confident AI platform under the specified alias
Usage Examples
from deepeval.dataset import EvaluationDataset
dataset = EvaluationDataset(goldens=goldens)
dataset.push(alias="my-eval-dataset-v2", finalized=True)