Documentation | Evaluations

API Reference

Evaluations

EvaluationsResource

Methods

client.evaluations.create() ->

Evaluation

post/v5/evaluations

Create Evaluation

client.evaluations.delete() ->

EvaluationDeleteResponse

delete/v5/evaluations/{evaluation_id}

Archive Evaluation

client.evaluations.list() -> SyncCursorPage[

Evaluation

]

get/v5/evaluations

List Evaluations

Parameters

ending_before: Optional[str]

include_archived: Optional[

bool

]

limit: Optional[int]

(maximum: 1000, minimum: 1, default: 100)

name: Optional[str]

sort_order: Optional[Literal["asc", "desc"]]

(default: "asc")

"asc"

"desc"

starting_after: Optional[str]

tags: Optional[List[str]]

views: Optional[List[Literal["tasks"]]]

(default: [])

"tasks"

Returns

Evaluation

Request example

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.evaluations.list()
page = page.items[0]
print(page.id)

200Example

{
  "has_more": true,
  "items": [
    {
      "id": "id",
      "created_at": "2019-12-27T18:11:19.117Z",
      "created_by_user_id": "created_by_user_id",
      "datasets": [
        {
          "id": "id",
          "created_at": "2019-12-27T18:11:19.117Z",
          "created_by_user_id": "created_by_user_id",
          "current_version_num": 0,
          "name": "name",
          "tags": [
            "string"
          ],
          "archived_at": "2019-12-27T18:11:19.117Z",
          "description": "description",
          "object": "dataset"
        }
      ],
      "name": "name",
      "status": "failed",
      "tags": [
        "string"
      ],
      "archived_at": "2019-12-27T18:11:19.117Z",
      "description": "description",
      "object": "evaluation",
      "tasks": [
        {
          "configuration": {
            "messages": [
              {
                "foo": "bar"
              }
            ],
            "model": "model",
            "audio": {
              "foo": "bar"
            },
            "frequency_penalty": 0,
            "function_call": {
              "foo": "bar"
            },
            "functions": [
              {
                "foo": "bar"
              }
            ],
            "logit_bias": {
              "foo": 0
            },
            "logprobs": true,
            "max_completion_tokens": 0,
            "max_tokens": 0,
            "metadata": {
              "foo": "string"
            },
            "modalities": [
              "string"
            ],
            "n": 0,
            "parallel_tool_calls": true,
            "prediction": {
              "foo": "bar"
            },
            "presence_penalty": 0,
            "reasoning_effort": "reasoning_effort",
            "response_format": {
              "foo": "bar"
            },
            "seed": 0,
            "stop": "stop",
            "store": true,
            "temperature": 0,
            "tool_choice": "tool_choice",
            "tools": [
              {
                "foo": "bar"
              }
            ],
            "top_k": 0,
            "top_logprobs": 0,
            "top_p": 0
          },
          "alias": "alias",
          "task_type": "chat_completion"
        }
      ]
    }
  ],
  "total": 0,
  "limit": 0,
  "object": "list"
}

client.evaluations.retrieve(, ) ->

Evaluation

get/v5/evaluations/{evaluation_id}

Get Evaluation

client.evaluations.update(, ) ->

Evaluation

patch/v5/evaluations/{evaluation_id}

Update Evaluation

Domain types

class Evaluation: ...

EvaluationTask =

EvaluationTask

ItemLocator = str

ItemLocatorTemplate = str