[Connectors][GenAI] Inference Service Kibana connector (#189027)

## Summary
Resolves #188043

This PR adds new connector which is define integration with Elastic
Inference Endpoint via [Inference
APIs](https://www.elastic.co/guide/en/elasticsearch/reference/current/inference-apis.html)
The lifecycle of the Inference Endpoint are managed by the connector
registered handlers:

- `preSaveHook` -
[create](https://www.elastic.co/guide/en/elasticsearch/reference/current/put-inference-api.html)
new Inference Endpoint in the connector create mode (`isEdit === false`)
and
[delete](https://www.elastic.co/guide/en/elasticsearch/reference/current/delete-inference-api.html)+[create](https://www.elastic.co/guide/en/elasticsearch/reference/current/put-inference-api.html)
in the connector edit mode (`isEdit === true`)
- `postSaveHook` - check if the connector SO was created/updated and if
not removes Inference Endpoint from preSaveHook
- `postDeleteHook` -
[delete](https://www.elastic.co/guide/en/elasticsearch/reference/current/delete-inference-api.html)
Inference Endpoint if connector was deleted.

In the Kibana Stack Management Connectors, its represented with the new
card (Technical preview badge):

<img width="1261" alt="Screenshot 2024-09-27 at 2 11 12 PM"
src="https://github.com/user-attachments/assets/dcbcce1f-06e7-4d08-8b77-0ba4105354f8">

To simplify the future integration with AI Assistants, the Connector
consists from the two main UI parts: provider selector and required
provider settings, which will be always displayed
<img width="862" alt="Screenshot 2024-10-07 at 7 59 09 AM"
src="https://github.com/user-attachments/assets/87bae493-c642-479e-b28f-6150354608dd">

and Additional options, which contains optional provider settings and
Task Type configuration:

<img width="861" alt="Screenshot 2024-10-07 at 8 00 15 AM"
src="https://github.com/user-attachments/assets/2341c034-6198-4731-8ce7-e22e6c6fb20f">


subActions corresponds to the different taskTypes Inference API
supports. Each of the task type has its own Inference Perform params.
Currently added:

- completion & completionStream
- rerank
- text_embedding
- sparse_embedding

Follow up work:

1. Collapse/expand Additional options, when the connector flyout/modal
has AI Assistant as a context (path through the extending context
implementation on the connector framework level)
2. Add support for additional params for Completion subAction to be able
to path functions
3. Add support for tokens usage Dashboard, when inference API will
include the used tokens count in the response
4. Add functionality and UX for migration from existing specific AI
connectors to the Inference connector with proper provider and
completion task
5. Integrate Connector with the AI Assistants

---------

Co-authored-by: kibanamachine <[email protected]>
Co-authored-by: István Zoltán Szabó <[email protected]>
Co-authored-by: Liam Thompson <[email protected]>
Co-authored-by: Steph Milovic <[email protected]>

.github/CODEOWNERS

@@ -1681,6 +1681,11 @@ x-pack/test/security_solution_cypress/cypress/tasks/expandable_flyout  @elastic/
 /x-pack/plugins/stack_connectors/server/connector_types/gemini @elastic/security-generative-ai @elastic/obs-ai-assistant @elastic/appex-ai-infra
 /x-pack/plugins/stack_connectors/common/gemini @elastic/security-generative-ai @elastic/obs-ai-assistant @elastic/appex-ai-infra
 
+# Inference API
+/x-pack/plugins/stack_connectors/public/connector_types/inference @elastic/appex-ai-infra @elastic/security-generative-ai @elastic/obs-ai-assistant
+/x-pack/plugins/stack_connectors/server/connector_types/inference @elastic/appex-ai-infra @elastic/security-generative-ai @elastic/obs-ai-assistant
+/x-pack/plugins/stack_connectors/common/inference @elastic/appex-ai-infra @elastic/security-generative-ai @elastic/obs-ai-assistant
+
 ## Defend Workflows owner connectors
 /x-pack/plugins/stack_connectors/public/connector_types/sentinelone @elastic/security-defend-workflows
 /x-pack/plugins/stack_connectors/server/connector_types/sentinelone @elastic/security-defend-workflows

docs/management/action-types.asciidoc

@@ -28,6 +28,10 @@ a| <<gemini-action-type,{gemini}>>
 
 | Send a request to {gemini}.
 
+a| <<inference-action-type,{inference}>>
+
+| Send a request to {inference}.
+
 a| <<email-action-type,Email>>
 
 | Send email from your server.

docs/management/connectors/action-types/inference.asciidoc

@@ -0,0 +1,126 @@
+[[inference-action-type]]
+== {infer-cap} connector and action
+++++
+<titleabbrev>{inference}</titleabbrev>
+++++
+:frontmatter-description: Add a connector that can send requests to {inference}.
+:frontmatter-tags-products: [kibana] 
+:frontmatter-tags-content-type: [how-to] 
+:frontmatter-tags-user-goals: [configure]
+
+
+The {infer} connector uses the {es} client to send requests to an {infer} service. The connector uses the <<execute-connector-api,run connector API>> to send the request.
+
+[float]
+[[define-inference-ui]]
+=== Create connectors in {kib}
+
+You can create connectors in *{stack-manage-app} > {connectors-ui}*. For example:
+
+[role="screenshot"]
+image::management/connectors/images/inference-connector.png[{inference} connector]
+// NOTE: This is an autogenerated screenshot. Do not edit it directly.
+
+[float]
+[[inference-connector-configuration]]
+==== Connector configuration
+
+{infer-cap} connectors have the following configuration properties:
+
+Name::      The name of the connector.
+Service::   The supported {infer} service provider.
+Task type:: The {infer} task type, it depends on the selected service.
+Inference ID:: The unique identifier of the {infer} endpoint.
+Provider configuration:: Settings for service configuration.
+Provider secrets:: Configuration for authentication.
+Task type configuration:: Settings for task type configuration.
+
+[float]
+[[inference-action-configuration]]
+=== Test connectors
+
+You can test connectors using the <<execute-connector-api,run connector API>> or
+while creating or editing the connector in {kib}. For example:
+
+[role="screenshot"]
+image::management/connectors/images/inference-completion-params.png[{infer} params test]
+// NOTE: This is an autogenerated screenshot. Do not edit it directly.
+[float]
+[[inference-connector-actions]]
+=== {infer-cap} connector actions
+
+The {infer} actions have the following configuration properties. Properties depend on the selected task type.
+
+[float]
+[[inference-connector-perform-completion]]
+==== Completion
+
+The following example performs a completion task on the example question.
+Input::
+The text on which you want to perform the {infer} task. For example:
++
+[source,text]
+--
+{
+  input: 'What is Elastic?'
+}
+--
+
+[float]
+[[inference-connector-perform-text-embedding]]
+==== Text embedding
+
+The following example performs a text embedding task.
+Input::
+The text on which you want to perform the {infer} task. For example:
++
+[source,text]
+--
+{
+  input: 'The sky above the port was the color of television tuned to a dead channel.',
+  task_settings: {
+    input_type: 'ingest'
+  }
+}
+--
+Input type::
+An optional string that overwrites the connector's default model.
+
+[float]
+[[inference-connector-perform-rerank]]
+==== Reranking
+
+The following example performs a reranking task on the example input.
+Input::
+The text on which you want to perform the {infer} task. Should be a string array. For example:
++
+[source,text]
+--
+{
+  input: ['luke', 'like', 'leia', 'chewy', 'r2d2', 'star', 'wars'],
+  query: 'star wars main character'
+}
+--
+Query::
+The search query text.
+
+[float]
+[[inference-connector-perform-sparse-embedding]]
+==== Sparse embedding
+
+The following example performs a sparse embedding task on the example sentence.
+Input::
+The text on which you want to perform the {infer} task. For example:
++
+[source,text]
+--
+{
+  input: 'The sky above the port was the color of television tuned to a dead channel.'
+}
+--
+
+[float]
+[[inference-connector-networking-configuration]]
+=== Connector networking configuration
+
+Use the <<action-settings, Action configuration settings>> to customize connector networking configurations, such as proxies, certificates, or TLS settings. You can apply these settings to all your connectors or use `xpack.actions.customHostSettings` to set per-host configurations.

docs/management/connectors/index.asciidoc

@@ -4,6 +4,7 @@ include::action-types/crowdstrike.asciidoc[leveloffset=+1]
 include::action-types/d3security.asciidoc[leveloffset=+1]
 include::action-types/email.asciidoc[leveloffset=+1]
 include::action-types/gemini.asciidoc[leveloffset=+1]
+include::action-types/inference.asciidoc[leveloffset=+1]
 include::action-types/resilient.asciidoc[leveloffset=+1]
 include::action-types/index.asciidoc[leveloffset=+1]
 include::action-types/jira.asciidoc[leveloffset=+1]

docs/settings/alert-action-settings.asciidoc

@@ -283,6 +283,7 @@ A configuration URL that varies by connector:
 --
 * For an <<bedrock-action-type,{bedrock} connector>>, specifies the {bedrock} request URL.
 * For an <<gemini-action-type,{gemini} connector>>, specifies the {gemini} request URL.
+* For an <<inference-action-type,{inference} connector>>, specifies the Elastic {inference} request.
 * For a <<openai-action-type,OpenAI connector>>, specifies the OpenAI request URL.
 * For a <<resilient-action-type,{ibm-r} connector>>, specifies the {ibm-r} instance URL.
 * For a <<jira-action-type,Jira connector>>, specifies the Jira instance URL.

oas_docs/examples/get_connector_types_generativeai_response.yaml

@@ -31,3 +31,14 @@ value:
     supported_feature_ids:
       - generativeAIForSecurity
     is_system_action_type: false
+  - id: .inference
+    name: Inference API
+    enabled: true
+    enabled_in_config: true
+    enabled_in_license: true
+    minimum_license_required: enterprise
+    supported_feature_ids:
+      - generativeAIForSecurity
+      - generativeAIForObservability
+      - generativeAIForSearchPlayground
+    is_system_action_type: false

x-pack/packages/kbn-elastic-assistant/impl/connectorland/use_load_action_types/index.tsx

@@ -40,8 +40,18 @@ export const useLoadActionTypes = ({
         http,
         featureId: GenerativeAIForSecurityConnectorFeatureId,
       });
-      const sortedData = queryResult.sort((a, b) => a.name.localeCompare(b.name));
 
+      const actionTypeKey = {
+        bedrock: '.bedrock',
+        openai: '.gen-ai',
+        gemini: '.gemini',
+      };
+
+      const sortedData = queryResult
+        .filter((p) =>
+          [actionTypeKey.bedrock, actionTypeKey.openai, actionTypeKey.gemini].includes(p.id)
+        )
+        .sort((a, b) => a.name.localeCompare(b.name));
       return sortedData;
     },
     {

x-pack/plugins/actions/common/connector_feature_config.ts

@@ -46,7 +46,7 @@ const compatibilityGenerativeAIForObservability = i18n.translate(
 const compatibilityGenerativeAIForSearchPlayground = i18n.translate(
   'xpack.actions.availableConnectorFeatures.compatibility.generativeAIForSearchPlayground',
   {
-    defaultMessage: 'Generative AI for Search Playground',
+    defaultMessage: 'Generative AI for Search',
   }
 );
 

x-pack/plugins/actions/docs/openapi/components/schemas/connector_types.yaml

@@ -4,6 +4,7 @@ description: The type of connector. For example, `.email`, `.index`, `.jira`, `.
 enum:
   - .bedrock
   - .gemini
+  - .inference
   - .cases-webhook
   - .d3security
   - .email

x-pack/plugins/actions/docs/openapi/components/schemas/inference_config.yaml

@@ -0,0 +1,23 @@
+title: Connector request properties for an Inference API connector
+description: Defines properties for connectors when type is `.inference`.
+type: object
+required:
+  - provider
+  - taskType
+  - inferenceId
+properties:
+  provider:
+    type: string
+    description: The Inference API service provider.
+  taskType:
+    type: string
+    description: The Inference task type supported by provider.
+  providerConfig:
+    type: object
+    description: The provider settings.
+  taskTypeConfig:
+    type: object
+    description: The task type settings.
+  inferenceId:
+    type: string
+    description: The task type settings.

x-pack/plugins/actions/docs/openapi/components/schemas/inference_secrets.yaml

@@ -0,0 +1,9 @@
+title: Connector secrets properties for an AI Connector
+description: Defines secrets for connectors when type is `.inference`.
+type: object
+required:
+  - providerSecrets
+properties:
+  providerSecrets:
+    type: object
+    description: The service account credentials. The service account could have different type of properties to encode.