NAME

OpenAPI::Client::OpenAI::Path::evals-eval_id-runs-run_id-output_items - Documentation for the /evals/{eval_id}/runs/{run_id}/output_items path.

DESCRIPTION

This document describes the API endpoint at /evals/{eval_id}/runs/{run_id}/output_items.

PATHS

GET /evals/{eval_id}/runs/{run_id}/output_items

Get eval run output items

Get a list of output items for an evaluation run.

Operation ID

getEvalRunOutputItems

$client->getEvalRunOutputItems( ... );

Parameters

• eval_id (in path) (Required) - The ID of the evaluation to retrieve runs for.

  Type: string

• run_id (in path) (Required) - The ID of the run to retrieve output items for.

  Type: string

• after (in query) (Optional) - Identifier for the last output item from the previous pagination request.

  Type: string

• limit (in query) (Optional) - Number of output items to retrieve.

  Type: integer

  Default: 20

• status (in query) (Optional) - Filter output items by status. Use `failed` to filter by failed output items or `pass` to filter by passed output items.

  Type: string

  Allowed values: fail, pass

• order (in query) (Optional) - Sort order for output items by timestamp. Use `asc` for ascending order or `desc` for descending order. Defaults to `asc`.

  Type: string

  Allowed values: asc, desc

  Default: asc

Responses

Status Code: 200

A list of output items for the evaluation run

Content Types:

• application/json

  Example (See the OpenAI spec for more detail):

  {
    "object": "list",
    "data": [
      {
        "object": "eval.run.output_item",
        "id": "outputitem_67abd55eb6548190bb580745d5644a33",
        "run_id": "evalrun_67abd54d60ec8190832b46859da808f7",
        "eval_id": "eval_67abd54d9b0081909a86353f6fb9317a",
        "created_at": 1739314509,
        "status": "pass",
        "datasource_item_id": 137,
        "datasource_item": {
            "teacher": "To grade essays, I only check for style, content, and grammar.",
            "student": "I am a student who is trying to write the best essay."
        },
        "results": [
          {
            "name": "String Check Grader",
            "type": "string-check-grader",
            "score": 1.0,
            "passed": true,
          }
        ],
        "sample": {
          "input": [
            {
              "role": "system",
              "content": "You are an evaluator bot..."
            },
            {
              "role": "user",
              "content": "You are assessing..."
            }
          ],
          "output": [
            {
              "role": "assistant",
              "content": "The rubric is not clear nor concise."
            }
          ],
          "finish_reason": "stop",
          "model": "gpt-4o-2024-08-06",
          "usage": {
            "total_tokens": 521,
            "completion_tokens": 2,
            "prompt_tokens": 519,
            "cached_tokens": 0
          },
          "error": null,
          "temperature": 1.0,
          "max_completion_tokens": 2048,
          "top_p": 1.0,
          "seed": 42
        }
      },
    ],
    "first_id": "outputitem_67abd55eb6548190bb580745d5644a33",
    "last_id": "outputitem_67abd55eb6548190bb580745d5644a33",
    "has_more": false
  }

SEE ALSO

OpenAPI::Client::OpenAI::Path

COPYRIGHT AND LICENSE

Copyright (C) 2023-2025 by Nelson Ferraz

This library is free software; you can redistribute it and/or modify it under the same terms as Perl itself, either Perl version 5.14.0 or, at your option, any later version of Perl 5 you may have available.