# Evaluation Items

## Get a single evaluation item

`evaluation_items.retrieve(strevaluation_item_id, EvaluationItemRetrieveParams**kwargs)  -> EvaluationItem`

**get** `/v5/evaluation-items/{evaluation_item_id}`

Retrieve a single evaluation item by its ID within the caller's account.

By default only non-archived items are returned; pass `include_archived=true` to
also retrieve an item that has been archived. The response merges the item's cached
task results into its `data` field and exposes a `task_errors` map keyed by task
alias, so a task that failed on this item surfaces as an entry there rather than as a
request error. Use this to inspect one item's input data and per-task results; to page
through many items, use the list endpoint instead. The request fails if no item with
the given ID exists in the caller's account.

### Parameters

- `evaluation_item_id: str`

- `include_archived: Optional[bool]`

### Returns

- `class EvaluationItem: …`

  - `id: str`

    The unique identifier of the entity.

  - `created_at: datetime`

    The date and time when the entity was created in ISO format.

  - `created_by: Identity`

    The identity that created the entity.

    - `id: str`

    - `type: Literal["user", "service_account"]`

      - `"user"`

      - `"service_account"`

    - `object: Optional[Literal["identity"]]`

      - `"identity"`

  - `data: Dict[str, object]`

  - `evaluation_id: str`

  - `archived_at: Optional[datetime]`

    The date and time when the entity was archived in ISO format.

  - `dataset_item_id: Optional[str]`

  - `dataset_item_version_num: Optional[int]`

  - `files: Optional[Dict[str, str]]`

  - `object: Optional[Literal["evaluation.item"]]`

    - `"evaluation.item"`

  - `task_errors: Optional[Dict[str, TaskError]]`

    Map of task alias to error info.

    - `message: str`

      Error message

    - `type: str`

      Error type/category

  - `task_result_statuses: Optional[Dict[str, Literal["completed", "skipped", "errored", 2 more]]]`

    Per-alias task-result lifecycle status derived from `task_result_cache`. Present when at least one alias has a recorded status; `null` for legacy rows with an empty cache. Renderers use this to distinguish `prefilled` from `completed` on the wire (values themselves are already merged into `data` by `merge_task_result_cache_into_data`).

    - `"completed"`

    - `"skipped"`

    - `"errored"`

    - `"pending"`

    - `"prefilled"`

### Example

```python
import os
from scale_gp_beta import SGPClient

client = SGPClient(
    api_key=os.environ.get("SGP_API_KEY"),  # This is the default and can be omitted
)
evaluation_item = client.evaluation_items.retrieve(
    evaluation_item_id="evaluation_item_id",
)
print(evaluation_item.id)
```

#### Response

```json
{
  "id": "id",
  "created_at": "2019-12-27T18:11:19.117Z",
  "created_by": {
    "id": "id",
    "type": "user",
    "object": "identity"
  },
  "data": {
    "foo": "bar"
  },
  "evaluation_id": "evaluation_id",
  "archived_at": "2019-12-27T18:11:19.117Z",
  "dataset_item_id": "dataset_item_id",
  "dataset_item_version_num": 0,
  "files": {
    "foo": "string"
  },
  "object": "evaluation.item",
  "task_errors": {
    "foo": {
      "message": "message",
      "type": "type"
    }
  },
  "task_result_statuses": {
    "foo": "completed"
  }
}
```

## List and filter evaluation items

`evaluation_items.list(EvaluationItemListParams**kwargs)  -> SyncCursorPage[EvaluationItem]`

**get** `/v5/evaluation-items`

Return a paginated list of evaluation items belonging to the caller's account.

Pass `evaluation_id` to restrict the results to a single evaluation's items. The
`completion_status` filter selects items by whether any of their tasks errored:
`failed` returns only items that have task errors, `passed` returns only items with no
task errors, and `all` (or omitting the parameter) returns every item. Archived items
are excluded unless `include_archived=true`. Each returned item has its cached task
results merged into `data` and its errors exposed in `task_errors`, identically to the
single-item endpoint.

### Parameters

- `completion_status: Optional[Literal["failed", "passed", "all"]]`

  Filter items by completion status. Pass 'failed' to return only items with errors, 'passed' for items without errors. Pass 'all' or omit to return all items.

  - `"failed"`

  - `"passed"`

  - `"all"`

- `ending_before: Optional[str]`

- `evaluation_id: Optional[str]`

- `include_archived: Optional[bool]`

- `limit: Optional[int]`

- `sort_by: Optional[str]`

- `sort_order: Optional[SortOrder]`

  - `"asc"`

  - `"desc"`

- `starting_after: Optional[str]`

### Returns

- `class EvaluationItem: …`

  - `id: str`

    The unique identifier of the entity.

  - `created_at: datetime`

    The date and time when the entity was created in ISO format.

  - `created_by: Identity`

    The identity that created the entity.

    - `id: str`

    - `type: Literal["user", "service_account"]`

      - `"user"`

      - `"service_account"`

    - `object: Optional[Literal["identity"]]`

      - `"identity"`

  - `data: Dict[str, object]`

  - `evaluation_id: str`

  - `archived_at: Optional[datetime]`

    The date and time when the entity was archived in ISO format.

  - `dataset_item_id: Optional[str]`

  - `dataset_item_version_num: Optional[int]`

  - `files: Optional[Dict[str, str]]`

  - `object: Optional[Literal["evaluation.item"]]`

    - `"evaluation.item"`

  - `task_errors: Optional[Dict[str, TaskError]]`

    Map of task alias to error info.

    - `message: str`

      Error message

    - `type: str`

      Error type/category

  - `task_result_statuses: Optional[Dict[str, Literal["completed", "skipped", "errored", 2 more]]]`

    Per-alias task-result lifecycle status derived from `task_result_cache`. Present when at least one alias has a recorded status; `null` for legacy rows with an empty cache. Renderers use this to distinguish `prefilled` from `completed` on the wire (values themselves are already merged into `data` by `merge_task_result_cache_into_data`).

    - `"completed"`

    - `"skipped"`

    - `"errored"`

    - `"pending"`

    - `"prefilled"`

### Example

```python
import os
from scale_gp_beta import SGPClient

client = SGPClient(
    api_key=os.environ.get("SGP_API_KEY"),  # This is the default and can be omitted
)
page = client.evaluation_items.list()
page = page.items[0]
print(page.id)
```

#### Response

```json
{
  "has_more": true,
  "items": [
    {
      "id": "id",
      "created_at": "2019-12-27T18:11:19.117Z",
      "created_by": {
        "id": "id",
        "type": "user",
        "object": "identity"
      },
      "data": {
        "foo": "bar"
      },
      "evaluation_id": "evaluation_id",
      "archived_at": "2019-12-27T18:11:19.117Z",
      "dataset_item_id": "dataset_item_id",
      "dataset_item_version_num": 0,
      "files": {
        "foo": "string"
      },
      "object": "evaluation.item",
      "task_errors": {
        "foo": {
          "message": "message",
          "type": "type"
        }
      },
      "task_result_statuses": {
        "foo": "completed"
      }
    }
  ],
  "total": 0,
  "limit": 0,
  "object": "list"
}
```

## Export evaluation items to a file

`evaluation_items.export(EvaluationItemExportParams**kwargs)  -> EvaluationItemExport`

**post** `/v5/evaluation-items/export`

Export all evaluation items for a single evaluation as a downloadable file.

The evaluation is specified by `evaluation_id` in the request body. `export_format`
selects CSV, JSON, or JSONL; for CSV the per-item `data` and `files` fields are
flattened into individual columns and metric-like result columns are expanded.
`export_method` controls delivery: `direct` returns the file contents inline in the
response, while `signed_url` uploads the file to object storage and returns a
pre-signed download URL. Requesting `signed_url` in an environment where object
storage is not configured fails with a 501, so use `direct` there instead. Set
`include_archived=true` to include archived items in the export. This endpoint reads
items only and does not modify the evaluation.

### Parameters

- `evaluation_id: str`

  The ID of the evaluation to export items from.

- `export_format: Optional[ExportFormat]`

  The format of the exported evaluation items. `json` returns a single JSON array, while `jsonl` returns one JSON object per line.

  - `"json"`

  - `"jsonl"`

  - `"csv"`

- `export_method: Optional[ExportMethod]`

  The method for exporting evaluation items. `signed_url` returns a pre-signed URL, while `direct` returns the raw content.

  - `"signed_url"`

  - `"direct"`

- `include_archived: Optional[bool]`

  If true, include archived evaluation items in the export.

### Returns

- `class EvaluationItemExport: …`

  Response model for exporting evaluation items.
  This class represents the response when users export evaluation items.
  It contains either a signed URL to download the exported data from object storage,
  or the actual content bytes when direct download is used (in environments where object storage is not configured).

  - `filename: str`

    The name of the exported file

  - `content: Optional[str]`

    The raw file content as bytes, used when direct download is enabled

  - `signed_url: Optional[str]`

    Pre-signed URL to download the file from object storage, if applicable

### Example

```python
import os
from scale_gp_beta import SGPClient

client = SGPClient(
    api_key=os.environ.get("SGP_API_KEY"),  # This is the default and can be omitted
)
evaluation_item_export = client.evaluation_items.export(
    evaluation_id="evaluation_id",
)
print(evaluation_item_export.filename)
```

#### Response

```json
{
  "filename": "filename",
  "content": "content",
  "signed_url": "signed_url"
}
```

## Domain Types

### Component

- `class Component: …`

  - `data: ItemLocator`

    A pointer to the data in each evaluation item to be displayed within the component

  - `label: Optional[str]`

### Container

- `class Container: …`

  - `children: List[Child]`

    The children to be displayed within the container

    - `class Container: …`

    - `class Component: …`

      - `data: ItemLocator`

        A pointer to the data in each evaluation item to be displayed within the component

      - `label: Optional[str]`

  - `direction: Optional[Literal["row", "column"]]`

    The axis that children are placed in the container. Based on CSS `flex-direction` (see: https://developer.mozilla.org/en-US/docs/Web/CSS/flex-direction)

    - `"row"`

    - `"column"`

### Evaluation Item

- `class EvaluationItem: …`

  - `id: str`

    The unique identifier of the entity.

  - `created_at: datetime`

    The date and time when the entity was created in ISO format.

  - `created_by: Identity`

    The identity that created the entity.

    - `id: str`

    - `type: Literal["user", "service_account"]`

      - `"user"`

      - `"service_account"`

    - `object: Optional[Literal["identity"]]`

      - `"identity"`

  - `data: Dict[str, object]`

  - `evaluation_id: str`

  - `archived_at: Optional[datetime]`

    The date and time when the entity was archived in ISO format.

  - `dataset_item_id: Optional[str]`

  - `dataset_item_version_num: Optional[int]`

  - `files: Optional[Dict[str, str]]`

  - `object: Optional[Literal["evaluation.item"]]`

    - `"evaluation.item"`

  - `task_errors: Optional[Dict[str, TaskError]]`

    Map of task alias to error info.

    - `message: str`

      Error message

    - `type: str`

      Error type/category

  - `task_result_statuses: Optional[Dict[str, Literal["completed", "skipped", "errored", 2 more]]]`

    Per-alias task-result lifecycle status derived from `task_result_cache`. Present when at least one alias has a recorded status; `null` for legacy rows with an empty cache. Renderers use this to distinguish `prefilled` from `completed` on the wire (values themselves are already merged into `data` by `merge_task_result_cache_into_data`).

    - `"completed"`

    - `"skipped"`

    - `"errored"`

    - `"pending"`

    - `"prefilled"`

### Evaluation Item Export

- `class EvaluationItemExport: …`

  Response model for exporting evaluation items.
  This class represents the response when users export evaluation items.
  It contains either a signed URL to download the exported data from object storage,
  or the actual content bytes when direct download is used (in environments where object storage is not configured).

  - `filename: str`

    The name of the exported file

  - `content: Optional[str]`

    The raw file content as bytes, used when direct download is enabled

  - `signed_url: Optional[str]`

    Pre-signed URL to download the file from object storage, if applicable

### Export Format

- `Literal["json", "jsonl", "csv"]`

  - `"json"`

  - `"jsonl"`

  - `"csv"`

### Export Method

- `Literal["signed_url", "direct"]`

  - `"signed_url"`

  - `"direct"`

### Task Error

- `class TaskError: …`

  - `message: str`

    Error message

  - `type: str`

    Error type/category