Google Gemini 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 Google Gemini connector uses axios to send a POST request to Google Gemini.

Create connectors in Kibana

You can create connectors in Stack Management > Connectors.

Connector configuration

Google Gemini connectors have the following configuration properties:

Name

The name of the connector.

API URL

The Google Gemini request URL.

Project ID

The project which has Vertex AI endpoint enabled.

Region

The GCP region where the Vertex AI endpoint enabled.

Default model

The GAI model for Google Gemini to use. Current support is for the Google Gemini models.

Elastic Cloud Serverless projects are autoscaled environments, fully managed by Elastic and available on Elastic Cloud. Availability Generally available This functionality is generally available and ready for production usage. Serverless interfaces and procedures might differ from classic Elastic Stack deployments. Defaults to gemini-2.5-pro.
The Elastic Stack includes Elastic's core products such as Elasticsearch, Kibana, Logstash, and Beats. Availability Generally available since 9.1 This functionality is generally available and ready for production usage. Unless stated otherwise on the page, this functionality is available when your Elastic Stack is deployed on Elastic Cloud Hosted, Elastic Cloud Enterprise, Elastic Cloud on Kubernetes, and self-managed environments. 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. Defaults to gemini-2.5-pro.
The Elastic Stack includes Elastic's core products such as Elasticsearch, Kibana, Logstash, and Beats. Availability Generally available since 9.0 This functionality is generally available and ready for production usage. Unless stated otherwise on the page, this functionality is available when your Elastic Stack is deployed on Elastic Cloud Hosted, Elastic Cloud Enterprise, Elastic Cloud on Kubernetes, and self-managed environments. 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. Defaults to gemini-1.5-pro-002. The model can be set on a per request basis by including a "model" parameter alongside the request body.

Credentials JSON

The GCP service account JSON file for authentication.

Test connectors

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

The Google Gemini actions have the following configuration properties.

Body

A stringified JSON payload sent to the Google Gemini invoke model API. For example:

{
  body: JSON.stringify({
        contents: [{
            role: user,
            parts: [{ text: 'Hello world!' }]
        }],
        generation_config: {
            temperature: 0,
            maxOutputTokens: 8192
        }
  })
}

Model

An optional string that overwrites the connector's default model.

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.