Update requirements for Elastic AI Assistant #2764
Conversation
Updates requirements for Elastic AI Assistant to include references to inference endpoint and Machine Learning node.
🔍 Preview links for changed docs |
| * {{stack}} users: an [Enterprise subscription](https://www.elastic.co/pricing). | ||
| * {{serverless-short}} users: a [Security Analytics Complete subscription](/deploy-manage/deploy/elastic-cloud/project-settings.md). | ||
| * {applies_to}`stack: ga` An [Enterprise subscription](https://www.elastic.co/pricing). | ||
| * {applies_to}`serverless: ga` A [Security Analytics Complete subscription](/deploy-manage/deploy/elastic-cloud/project-settings.md). |
There was a problem hiding this comment.
| * {applies_to}`serverless: ga` A [Security Analytics Complete subscription](/deploy-manage/deploy/elastic-cloud/project-settings.md). | |
| * {applies_to}`serverless: ga` An {{sec-serverless}} project with the [Security Analytics Complete feature tier](/deploy-manage/deploy/elastic-cloud/project-settings.md). |
This is a feature tier, not a subscription - found a couple of other occurrences #2768
There was a problem hiding this comment.
The new EASE tier also supports assistant functionality.
| * To use AI Assistant, the **Elastic AI Assistant : All** and **Actions and Connectors : Read** [privileges](/deploy-manage/users-roles/cluster-or-deployment-auth/kibana-privileges.md). | ||
| * To set up AI Assistant, the **Actions and Connectors : All** [privilege](/deploy-manage/users-roles/cluster-or-deployment-auth/kibana-privileges.md). | ||
| * A [generative AI connector](/solutions/security/ai/set-up-connectors-for-large-language-models-llm.md), which AI Assistant uses to generate responses. | ||
|
|
||
| * An [inference endpoint](/explore-analyze/machine-learning/nlp/ml-nlp-elser.md) and [Machine Learning node](/explore-analyze/machine-learning/setting-up-machine-learning.md). |
There was a problem hiding this comment.
Couple notes here:
The default inference endpoints provided are what are used out of the box (either .elser-2-elasticsearch as you linked or .multilingual-e5-small-elasticsearch coming up in 9.2) , so while necessary, they don't need to manually create one. The ML node being available (with enough memory) is sufficient.
And WRT the ML Node, this is implicit on serverless. ML Nodes + autoscaling are enabled by default, so they don't need to do anything other than be on the Security Complete/EASE tier.
| * {{stack}} users: an [Enterprise subscription](https://www.elastic.co/pricing). | ||
| * {{serverless-short}} users: a [Security Analytics Complete subscription](/deploy-manage/deploy/elastic-cloud/project-settings.md). | ||
| * {applies_to}`stack: ga` An [Enterprise subscription](https://www.elastic.co/pricing). | ||
| * {applies_to}`serverless: ga` A [Security Analytics Complete subscription](/deploy-manage/deploy/elastic-cloud/project-settings.md). | ||
| * To use AI Assistant, the **Elastic AI Assistant : All** and **Actions and Connectors : Read** [privileges](/deploy-manage/users-roles/cluster-or-deployment-auth/kibana-privileges.md). | ||
| * To set up AI Assistant, the **Actions and Connectors : All** [privilege](/deploy-manage/users-roles/cluster-or-deployment-auth/kibana-privileges.md). | ||
| * A [generative AI connector](/solutions/security/ai/set-up-connectors-for-large-language-models-llm.md), which AI Assistant uses to generate responses. |
There was a problem hiding this comment.
For the Elastic Managed LLM, the connector is already created and ready to go. Not sure if this is worth expanding here as it's the first thing the linked docs mention?
Updates requirements for Elastic AI Assistant to include references to inference endpoint and Machine Learning node.
The text will likely need help from @e40pud.