[**axiom v0.51.1**](../../README.md)

***

[axiom](../../README.md) / [evals](../README.md) / EvalParams

# Type Alias: EvalParams\<TInput, TExpected, TOutput\>

> **EvalParams**\<`TInput`, `TExpected`, `TOutput`\> = `object`

Configuration parameters for running an evaluation.

Used with [Eval](../functions/Eval.md) to define how an evaluation should be executed.
Results are captured in EvalReport format.

## Type Parameters

### TInput

`TInput`

### TExpected

`TExpected`

### TOutput

`TOutput`

## Properties

### capability

> **capability**: `string`

***

### configFlags?

> `optional` **configFlags**: `string`[]

Optional reduction of flag namespace

***

### data

> **data**: readonly `CollectionRecord`\<`TInput`, `TExpected`\>[] \| `Promise`\<readonly `CollectionRecord`\<`TInput`, `TExpected`\>[]\> \| () => readonly `CollectionRecord`\<`TInput`, `TExpected`\>[] \| `Promise`\<readonly `CollectionRecord`\<`TInput`, `TExpected`\>[]\>

Dataset with input/expected pairs for evaluation, or a function that returns one

***

### metadata?

> `optional` **metadata**: `Record`\<`string`, `unknown`\>

Optional metadata for the evaluation

***

### scorers

> **scorers**: `ReadonlyArray`\<[`ScorerLike`](../../scorers/scorers/type-aliases/ScorerLike.md)\<`TInput`, `TExpected`, `TOutput`\>\>

Array of scoring functions to evaluate the task output

***

### step?

> `optional` **step**: `string`

***

### task

> **task**: [`EvalTask`](EvalTask.md)\<`TInput`, `TExpected`, `TOutput`\>

The task function to evaluate

***

### timeout?

> `optional` **timeout**: `number`

Optional timeout in milliseconds for task execution

***

### trials?

> `optional` **trials**: `number`

Number of times to run each case. Defaults to 1.
Each trial runs the task independently, and scores are aggregated per scorer.