List runs

GET

runs

curl --request GET \
  --url https://api.avidoai.com/v0/runs \
  --header 'x-api-key: <api-key>'

{
  "data": [
    {
      "id": "run_1",
      "orgId": "org_123456",
      "createdAt": "2024-01-05T12:34:56.789Z",
      "modifiedAt": "2024-01-05T12:34:56.789Z",
      "taskId": "task_1",
      "threadId": null,
      "result": null,
      "status": "PENDING",
      "evals": []
    }
  ],
  "pagination": {
    "skip": 0,
    "limit": 25,
    "total": 1,
    "totalPages": 1
  }
}

Authorizations

x-api-key

string

header

required

Your unique Avido API key

Query Parameters

skip

integer

default:0

Number of items to skip

Required range: x >= 0

Example:

0

limit

integer

default:25

Number of items per page

Required range: 1 <= x <= 100

Example:

25

orderBy

string

Field to order by

Example:

"createdAt"

orderDir

enum<string>

default:desc

Order direction

Available options:

asc,

desc

Example:

"desc"

taskId

string

Filter by task ID

Example:

"456e4567-e89b-12d3-a456-426614174000"

traceId

string

Filter by trace ID

Example:

"789e4567-e89b-12d3-a456-426614174000"

status

string

Filter by evaluation status

Example:

"COMPLETED"

type

string

Filter by evaluation type

Example:

"NATURALNESS"

Response

200

application/json

Successfully retrieved evaluation runs

Paginated response containing runs

data

object[]

required

A Run represents a batch of tests triggered by a single task

data.id

string

required

Unique identifier of the run

Example:

"123e4567-e89b-12d3-a456-426614174000"

data.createdAt

string

required

When the run was created

Example:

"2024-01-05T12:34:56.789Z"

data.modifiedAt

string

required

When the run was last modified

Example:

"2024-01-05T12:34:56.789Z"

data.status

enum<string>

required

Status of the evaluation/test. Valid options: PENDING, IN_PROGRESS, PASSED, COMPLETED, FAILED.

Available options:

PENDING,

IN_PROGRESS,

PASSED,

COMPLETED,

FAILED

Example:

"COMPLETED"

data.tests

object[]

required

A Test represents a single test applying all the linked evals on a Trace

data.tests.id

string

required

Unique identifier of the run

Example:

"123e4567-e89b-12d3-a456-426614174000"

data.tests.createdAt

string

required

When the run was created

Example:

"2024-01-05T12:34:56.789Z"

data.tests.modifiedAt

string

required

When the run was last modified

Example:

"2024-01-05T12:34:56.789Z"

data.tests.status

enum<string>

required

Status of the evaluation/test. Valid options: PENDING, IN_PROGRESS, PASSED, COMPLETED, FAILED.

Available options:

PENDING,

IN_PROGRESS,

PASSED,

COMPLETED,

FAILED

Example:

"COMPLETED"

data.tests.evals

object[]

required

Array of evaluations in this run

Complete evaluation information

data.tests.task

object

required

A task that represents a specific job-to-be-done by the LLM in the user application.

data.tests.task.id

string

required

The unique identifier of the task

Example:

"123e4567-e89b-12d3-a456-426614174000"

data.tests.task.createdAt

string

required

The date and time the task was created

Example:

"2024-01-01T00:00:00.000Z"

data.tests.task.modifiedAt

string

required

The date and time the task was last updated

Example:

"2024-01-01T00:00:00.000Z"

data.tests.task.title

string

required

The title of the task

Example:

"Credit Card Block"

data.tests.task.description

string

required

The task description

Example:

"Wants to block their credit card"

data.tests.task.application

object

required

Application configuration and metadata

data.tests.task.topic

object

required

Details about a single Topic

data.tests.task.definitions

object[]

required

data.tests.task.passRate

number | null

The 30 day pass rate for the task measured in percentage

Example:

66

data.tests.task.lastTest

string | null

The date and time this task was last tested

Example:

"2024-01-01T00:00:00.000Z"

data.tests.task.inputExamples

any | null

Example inputs for the task

data.tests.traceId

string | null

Optional ID of the trace this run is associated with

Example:

"789e4567-e89b-12d3-a456-426614174000"

data.tests.result

enum<string> | null

Result of the run (if completed)

Available options:

PASSED,

FAILED

Example:

"PASSED"

data.result

enum<string> | null

Result of the run (if completed)

Available options:

PASSED,

FAILED

Example:

"PASSED"

pagination

object

required

Pagination metadata returned in a paginated response.

Get a single annotation by ID Get a single run by ID

curl --request GET \
  --url https://api.avidoai.com/v0/runs \
  --header 'x-api-key: <api-key>'

{
  "data": [
    {
      "id": "run_1",
      "orgId": "org_123456",
      "createdAt": "2024-01-05T12:34:56.789Z",
      "modifiedAt": "2024-01-05T12:34:56.789Z",
      "taskId": "task_1",
      "threadId": null,
      "result": null,
      "status": "PENDING",
      "evals": []
    }
  ],
  "pagination": {
    "skip": 0,
    "limit": 25,
    "total": 1,
    "totalPages": 1
  }
}

Webhook

Applications

Threads

Ingestion

Tasks

Evals

Tests

Topics

Annotations

Runs

Style Guides

Authorizations

Query Parameters

Response