JavaScript

import Dataframer from 'dataframer';

const client = new Dataframer({
  apiKey: 'My API Key',
});

const response = await client.dataframer.runs.generatedFiles.downloadAll('run_id');

console.log(response);

const content = await response.blob();
console.log(content);

"<string>"

DataFramer - Runs

Download all generated files with metadata as ZIP

Download all generated files and their metadata as a single ZIP archive.

The ZIP file contains:

All generated files with proper folder structure (for MULTI_FOLDER datasets)
Metadata files (.metadata) with evaluation classifications and tags
Top-level metadata (top_level.metadata) with evaluation summary and distribution analysis

The metadata is automatically generated when evaluation completes and includes:

Per-file/per-folder tags (classifications from evaluation)
Human annotation tags (if any)
Distribution analysis comparing expected vs observed distributions
Conformance scores and explanations

This endpoint is used by the web UI for downloads and is the recommended way to download evaluated results.

Benefits:

Single HTTP request downloads everything
Preserves folder structure automatically
Includes all metadata pre-formatted
More efficient for large datasets
Consistent with UI behavior

Use Cases:

Download evaluated dataset with tags for analysis
Export results for external tools
Backup generated samples with metadata
Share evaluated results with team members

GET

api

dataframer

runs

{run_id}

generated-files

download-all

JavaScript

import Dataframer from 'dataframer';

const client = new Dataframer({
  apiKey: 'My API Key',
});

const response = await client.dataframer.runs.generatedFiles.downloadAll('run_id');

console.log(response);

const content = await response.blob();
console.log(content);

"<string>"

Authorizations

Authorization

string

header

required

API Key authentication. Format: "Bearer YOUR_API_KEY"

Path Parameters

run_id

string

required

Response

ZIP file containing all generated files and metadata

Binary ZIP file containing all generated files and their metadata

Create a run (direct method)Create a spec manually

⌘I

Specs

Analysis

DataFramer - Evaluation

Datasets

Files

Generation

Health

Runs

Human Labels

Models

Red Teaming

DataFramer - Runs

DataFramer - Specs

Download all generated files with metadata as ZIP

Authorizations

Path Parameters

Response