Get datasets
Get list of datasets with pagination and filtering options. See Datasets.
Authorizations
API key authorization. Pass your API key in the Authorization header as a Bearer token. Both new (gsk_*) and legacy (gsk-) API keys are accepted, e.g. Authorization: Bearer gsk_... or Authorization: Bearer gsk-....
Query Parameters
Filter by dataset IDs
Filter by product IDs
Filter by test case IDs
Filter by version IDs
Filter by dataset names (exact match, multiple)
Filter by dataset name (partial match)
Filter by dataset types
Filter by specification IDs
Filter datasets by whether they are linked to a live (not deleted) specification. Omit for no filter.
Filter datasets that have evaluations
Filter datasets that have traces
Sort instructions (field and direction pairs)
Maximum number of results
Number of results to skip
Filter datasets created at or after this timestamp (ISO 8601 format)
Filter datasets created at or before this timestamp (ISO 8601 format)
Response
Datasets retrieved successfully
"test_123"
"prod_123"
"user_123"
"Quality Test"
QUALITY, RED_TEAMING, SCENARIOS "QUALITY"
Canonical storage URI of the ground-truth file, derived from the presigned URL supplied at creation. S3: s3://<bucket>/<key>. Azure Blob: blob URL with the SAS query stripped (e.g. https://<account>.blob.core.windows.net/<container>/<path>).
"s3://my-bucket/tests/test_123/ground-truth.csv"
Canonical storage URI of the uploaded custom test file. Same format rules as groundTruthUri.
"s3://my-bucket/tests/test_123/test.csv"
PENDING, SUCCESS, FAILED, AUGMENTING, EXTENDING, CANCELLED "SUCCESS"
Optional few-shot examples (input/output pairs) used to guide test-case generation for QUALITY tests.
"Example few-shot learning data"
BCP-47 language tag (e.g. en, es-MX). The region subtag selects the regional variety in simulated user messages and voice synthesis; generated test text keeps the base language. The value is stored as the full tag.
"es-MX"
Background noise mixed into the simulated caller audio during a voice test. Clip-backed (office, street, car) or synthetic (white, pink). Null means off; set together with backgroundNoiseLevel.
office, street, car, white, pink, null "street"
How loud the background noise is relative to the caller speech. Null means off; set together with backgroundNoiseProfile.
light, medium, heavy, null "medium"
Test variants. QUALITY: rag, entity_extraction, summarization, classification, translation, correction, other. RED_TEAMING: data_leakage, financial_attacks, illegal_activities, misuse, toxicity, custom.
"Custom variant description"
Generation strategies. "original" is the default for RED_TEAMING. At least one strategy is required for SCENARIOS tests.
"Business analyst"
100
Canonical storage URI of the data-catalog file (SCENARIOS tests only). Same format rules as groundTruthUri.
"s3://my-bucket/tests/test_123/data-catalog.json"
"spec_123"
True when the test can be extended by re-running its original generator (generated tests; QUALITY only when it has a ground-truth document). False for uploaded tests.
true