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

# ChatConfig

<span id="atoti_ai_amazon_bedrock.ChatConfig" />

> atoti\_ai\_amazon\_bedrock.ChatConfig(<br />
>     \*,<br />
>     *model*: [str](https://docs.python.org/3/library/stdtypes.html#str),<br />
>     *temperature*: [float](https://docs.python.org/3/library/functions.html#float) | [None](https://docs.python.org/3/library/constants.html#None) = `None`,<br />
>     *top\_p*: [float](https://docs.python.org/3/library/functions.html#float) | [None](https://docs.python.org/3/library/constants.html#None) = `None`,<br />
>     *top\_k*: [int](https://docs.python.org/3/library/functions.html#int) | [None](https://docs.python.org/3/library/constants.html#None) = `None`,<br />
>     *max\_tokens*: [int](https://docs.python.org/3/library/functions.html#int) | [None](https://docs.python.org/3/library/constants.html#None) = `None`,<br />
> )

Chat config for Amazon Bedrock.

See the [corresponding Javadoc](https://docs.spring.io/spring-ai/docs/current/api/org/springframework/ai/bedrock/converse/BedrockChatOptions.html) for more details.

<Callout icon="link">
  **See also**:
  The other [`ChatConfig`](./atoti_ai.ChatConfig#atoti_ai.ChatConfig) implementations.
</Callout>

### Attributes

<h4 id="atoti_ai_amazon_bedrock.ChatConfig.model">
  *model*
</h4>

The ID of the model to use, for example `"anthropic.claude-3-sonnet-20240229-v1:0"`.

<h4 id="atoti_ai_amazon_bedrock.ChatConfig.temperature">
  *temperature*
</h4>

Controls randomness in responses from 0.0 (deterministic) to 1.0 (creative).

<h4 id="atoti_ai_amazon_bedrock.ChatConfig.top_p">
  *top\_p*
</h4>

Nucleus sampling parameter.

Controls diversity via cumulative probability.

<h4 id="atoti_ai_amazon_bedrock.ChatConfig.top_k">
  *top\_k*
</h4>

Limits vocabulary to top K tokens at each generation step.

<h4 id="atoti_ai_amazon_bedrock.ChatConfig.max_tokens">
  *max\_tokens*
</h4>

Maximum number of tokens to generate in the response.