Amazon Bedrock connector and action

Important

This connector is being replaced by Elasticsearch inference endpoints and will be removed entirely in Elastic Stack 10.0 or in January 2028, whichever comes first. To configure access to an LLM provider, create an inference endpoint with the chat_completion task type. For steps that use your own provider account and API key, refer to External inference. To use models that Elastic hosts instead, refer to Elastic Managed LLMs.

Availability of this connector depends on your deployment and version:

Elastic Cloud Serverless projects are autoscaled environments, fully managed by Elastic and available on Elastic Cloud. Availability Deprecated This functionality is deprecated. You can still use it, but it'll be removed in a future Elastic Cloud Serverless update. The Elastic Stack includes Elastic's core products such as Elasticsearch, Kibana, Logstash, and Beats. Availability Planned for deprecation This functionality is planned to be deprecated in a future Elastic Stack update. Subject to changes. This documentation corresponds to the latest patch available for each minor version. If you're not using the latest patch, check the release notes for changes. You can no longer create new connectors of this type by selecting Create connector in Kibana. Existing connectors and their rule actions continue to work, but the Connectors page hides them by default. To show them, open Display options and set Deprecated to Show.
The Elastic Stack includes Elastic's core products such as Elasticsearch, Kibana, Logstash, and Beats. Availability Deprecated in 9.5 This functionality is deprecated. You can still use it, but it'll be removed in a future Elastic Stack update. This documentation corresponds to the latest patch available for each minor version. If you're not using the latest patch, check the release notes for changes. This connector is still available, but deprecated.

The Amazon Bedrock connector uses axios to send a POST request to Amazon Bedrock.

Create connectors in Kibana

You can create connectors in Stack Management > Connectors.

Connector configuration

Amazon Bedrock connectors have the following configuration properties:

Name: The name of the connector.
API URL: The Amazon Bedrock request URL.
Region: (Optional) The AWS region used for request signing. Required when using a custom endpoint URL that does not include the region in the hostname (for example, us-east-1).
Default model: The GAI model for Amazon Bedrock to use. Current support is for the Anthropic Claude models, defaulting to Claude 2. The model can be set on a per request basis by including a "model" parameter alongside the request body.
Access Key: The AWS access key for authentication.
Secret: The secret for authentication.

Test connectors

You can test connectors as you’re creating or editing the connector in Kibana.

The Amazon Bedrock actions have the following configuration properties.

Body

A stringified JSON payload sent to the Amazon Bedrock Invoke Model API URL. For example:

{
  body: JSON.stringify({
        prompt: `${combinedMessages} \n\nAssistant:`,
        max_tokens_to_sample: 300,
        stop_sequences: ['\n\nHuman:']
  })
}

Model

An optional string that will overwrite the connector’s default model. For

Connector networking configuration

Use the Action configuration settings to customize connector networking configurations, such as proxies, certificates, or TLS settings. You can set configurations that apply to all your connectors or use xpack.actions.customHostSettings to set per-host configurations.