For the complete documentation index, see llms.txt. This page is also available as Markdown.

POST /v2/evals/datasets/{dataset_id}/imports

Import Eval Dataset Rows

post

Import finished runs atomically, requiring evals.update and analytics.read.

Inputs and expected outputs come from each run trace under the dataset contract. A run without a usable trace rejects the whole batch; Location is the first row.

How to use

Import 1–100 finished run IDs from the dataset project. Requires both evals.update and analytics.read. The whole batch is rejected if a trace is unusable; correct the identified runs before resubmission.

Authentication and permissions

Required permissions: evals.update, analytics.read. Resource and owner access checks also apply.

Prepare request.json

Save the example body below as request.json for the curl sample. Replace example IDs, node keys, and dynamic configuration with values for your organization; these are illustrative, not pre-existing resources.

{
  "run_ids": [
    "00000000-0000-4000-8000-000000000001"
  ]
}
Authorizations
AuthorizationstringRequired

Personal API key (sk_...) or supported user access JWT. See Authentication and authorization for endpoint restrictions and scopes. Use exactly one Authorization header.

Path parameters
dataset_idstring · uuidRequired
Body
run_idsstring · uuid[] · min: 1 · max: 100Required

Finished runs of the dataset's project to import as rows: inputs and expected output are extracted from each run trace under the dataset contract and source_run_id is set. Any run without a usable trace rejects the whole batch with a 422 naming it. Requires evals.update and analytics.read.

Responses
201

Successful Response

application/json
post/v2/evals/datasets/{dataset_id}/imports
curl
curl --fail-with-body -sS \
  "$STACKAI_BASE_URL/v2/evals/datasets/${DATASET_ID}/imports" \
  -H "Authorization: Bearer $STACKAI_API_KEY" \
  -H 'Content-Type: application/json' \
  --data-binary @request.json
{
  "response_code": "text",
  "meta": {
    "ANY_ADDITIONAL_PROPERTY": "anything"
  },
  "data": [
    {
      "dataset_row_id": "123e4567-e89b-12d3-a456-426614174000",
      "dataset_id": "123e4567-e89b-12d3-a456-426614174000",
      "url": "text",
      "position": 1,
      "inputs": {
        "ANY_ADDITIONAL_PROPERTY": "anything"
      },
      "expected_output": {
        "ANY_ADDITIONAL_PROPERTY": "anything"
      },
      "source_run_id": "123e4567-e89b-12d3-a456-426614174000",
      "created_by": "123e4567-e89b-12d3-a456-426614174000",
      "updated_by": "123e4567-e89b-12d3-a456-426614174000",
      "created_at": "2026-01-01T00:00:00.000Z",
      "updated_at": "2026-01-01T00:00:00.000Z"
    }
  ]
}

Last updated

Was this helpful?