axiom/dist/docs/evals/type-aliases/EvalTask.md

Axiom AI SDK provides - an API to wrap your AI calls with observability instrumentation. - offline evals - online evals

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

***

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

# Type Alias: EvalTask()\<TInput, TExpected, TOutput\>

> **EvalTask**\<`TInput`, `TExpected`, `TOutput`\> = (`args`) => `TOutput` \| `Promise`\<`TOutput`\> \| `AsyncIterable`\<`TOutput`\>

Function type for evaluation tasks that process input data and produce output.

Used with [EvalParams](EvalParams.md) to define the task that will be evaluated against a dataset.
The task output will be scored by functions defined in [EvalParams.scorers](EvalParams.md#scorers).

## Type Parameters

### TInput

`TInput`

### TExpected

`TExpected`

### TOutput

`TOutput`

## Parameters

### args

#### expected

`TExpected`

#### input

`TInput`

## Returns

`TOutput` \| `Promise`\<`TOutput`\> \| `AsyncIterable`\<`TOutput`\>

The task output, Promise, or AsyncIterable for streaming

## Example

```typescript
const textGenerationTask: EvalTask<string, string, string> = async ({ input, expected }) => {
  const result = await generateText({
    model: myModel,
    prompt: input
  });
  return result.text;
};
```