> **Experimental**
>
> `@aws-cdk/aws-bedrock-alpha` is an [**experimental**](/stability) (alpha) package: its API may change in any release, without a major version bump.
# InferenceConfiguration

LLM inference configuration.

- Stability: [Experimental](/cdk/api/stability.html)
- Source: [`bedrock/agents/prompt-override.ts`](https://github.com/aws/aws-cdk/blob/v2.275.0-alpha.0/packages/@aws-cdk/aws-bedrock-alpha/bedrock/agents/prompt-override.ts#L46)

## Example

```ts
const agent = new bedrock.Agent(this, 'Agent', {
  foundationModel: bedrock.BedrockFoundationModel.AMAZON_NOVA_LITE_V1,
  instruction: 'You are a helpful assistant.',
  promptOverrideConfiguration: bedrock.PromptOverrideConfiguration.fromSteps([
    {
      stepType: bedrock.AgentStepType.PRE_PROCESSING,
      stepEnabled: true,
      customPromptTemplate: 'Your custom prompt template here',
      inferenceConfig: {
        temperature: 0.0,
        topP: 1,
        topK: 250,
        maximumLength: 1,
        stopSequences: ["\n\nHuman:"],
      },
    }
  ])
});
```

## Properties

- `maximumLength`: number (required) — The maximum number of tokens to generate in the response.

  Integer

  min 0
  max 4096

- `stopSequences`: string[] (required) — A list of stop sequences.

  A stop sequence is a sequence of characters that
  causes the model to stop generating the response.

  length 0-4

- `temperature`: number (required) — The likelihood of the model selecting higher-probability options while generating a response.

  A lower value makes the model more likely to choose
  higher-probability options, while a higher value makes the model more
  likely to choose lower-probability options.

  Floating point

  min 0
  max 1

- `topK`: number (required) — While generating a response, the model determines the probability of the following token at each point of generation.

  The value that you set for
  topK is the number of most-likely candidates from which the model chooses
  the next token in the sequence. For example, if you set topK to 50, the
  model selects the next token from among the top 50 most likely choices.

  Integer

  min 0
  max 500

- `topP`: number (required) — While generating a response, the model determines the probability of the following token at each point of generation.

  The value that you set for
  Top P determines the number of most-likely candidates from which the model
  chooses the next token in the sequence. For example, if you set topP to
  80, the model only selects the next token from the top 80% of the
  probability distribution of next tokens.

  Floating point

  min 0
  max 1