NAME

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

DESCRIPTION

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

PATHS

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

Get an output item of an eval run

Get an evaluation run output item by ID.

Operation ID

getEvalRunOutputItem

$client->getEvalRunOutputItem( ... );

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.

  Type: string

• output_item_id (in path) (Required) - The ID of the output item to retrieve.

  Type: string

Responses

Status Code: 200

The evaluation run output item

Content Types:

• application/json

  Example (See the OpenAI spec for more detail):

  {
    "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
    }
  }

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.