> ## Documentation Index
> Fetch the complete documentation index at: https://docs.galileo.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# createScorer

***

# Function: createScorer()

```ts theme={null}
function createScorer(
  name: string,
  scorerType: ScorerTypes,
  description?: string,
  tags?: string[],
  defaults?: object,
  modelType?: "llm" | "code" | "slm",
  defaultVersionId?: string,
  scoreableNodeTypes?: (
    | "agent"
    | "llm"
    | "retriever"
    | "tool"
    | "workflow"
    | "trace"
    | "session"
  )[],
  outputType?: OutputType,
  inputType?: InputType,
): Promise<ScorerResponse>;
```

Defined in: [src/utils/scorers.ts](https://github.com/rungalileo/galileo-js/blob/main/src/utils/scorers.ts)

Creates a new scorer.

## Parameters

### name

`string`

The name of the scorer.

### scorerType

[`ScorerTypes`](/sdk-api/typescript/reference/types/enumerations/ScorerTypes)

The type of the scorer.

### description?

`string`

(Optional) A description for the scorer.

### tags?

`string`\[]

(Optional) Tags to associate with the scorer.

### defaults?

(Optional) Default settings for the scorer. Required for LLM scorers.

#### cot\_enabled?

`null` | `boolean`

Cot Enabled

**Description**

Whether to enable chain of thought for this scorer. Defaults to False for llm scorers.

#### filters?

\| `null`
\| (
\| \{
`case_sensitive?`: `boolean`;
`filter_type?`: `"string"`;
`name`: `"node_name"`;
`operator`: `"eq"` | `"ne"` | `"contains"`;
`value`: `string`;
}
\| \{
`filter_type?`: `"map"`;
`key`: `string`;
`name`: `"metadata"`;
`operator`: `"eq"` | `"ne"` | `"not_in"` | `"one_of"`;
`value`: `string` | `string`\[];
})\[]

Filters

**Description**

List of filters to apply to the scorer.

#### input\_type?

\| `null`
\| `"basic"`
\| `"llm_spans"`
\| `"retriever_spans"`
\| `"sessions_normalized"`
\| `"sessions_trace_io_only"`
\| `"tool_spans"`
\| `"trace_input_only"`
\| `"trace_io_only"`
\| `"trace_normalized"`
\| `"trace_output_only"`
\| `"agent_spans"`
\| `"workflow_spans"`

**Description**

What type of input to use for model-based scorers (sessions\_normalized, trace\_io\_only, etc..).

#### model\_name?

`null` | `string`

Model Name

#### num\_judges?

`null` | `number`

Num Judges

#### output\_type?

\| `null`
\| `"boolean"`
\| `"categorical"`
\| `"count"`
\| `"discrete"`
\| `"freeform"`
\| `"percentage"`
\| `"multilabel"`

**Description**

What type of output to use for model-based scorers (boolean, categorical, etc.).

#### scoreable\_node\_types?

`null` | `string`\[]

Scoreable Node Types

**Description**

List of node types that can be scored by this scorer. Defaults to llm/chat.

### modelType?

(Optional) The model type for the scorer.

`"llm"` | `"code"` | `"slm"`

### defaultVersionId?

`string`

(Optional) The default version ID for the scorer.

### scoreableNodeTypes?

(`"agent"` | `"llm"` | `"retriever"` | `"tool"` | `"workflow"` | `"trace"` | `"session"`)\[]

(Optional) The node types that can be scored.

### outputType?

[`OutputType`](/sdk-api/typescript/reference/types/enumerations/OutputType)

(Optional) The output type for the scorer.

### inputType?

[`InputType`](/sdk-api/typescript/reference/types/enumerations/InputType)

(Optional) The input type for the scorer.

## Returns

`Promise`\<[`ScorerResponse`](/sdk-api/typescript/reference/types/type-aliases/ScorerResponse)>

A promise that resolves to the created scorer.