stack kb context-engine post-context-engine-ai-index cli command
Elastic Cloud Serverless projects are autoscaled environments, fully managed by Elastic and available on Elastic Cloud. Availability This functionality is in technical preview and is ready for evaluation. Use with caution in production; it is not recommended for mission-critical workloads. Elastic will work to fix any issues, but features in technical preview are not subject to the support SLA of official GA features. Specific Support terms apply. Serverless interfaces and procedures might differ from classic Elastic Stack deployments. The Elastic Stack includes Elastic's core products such as Elasticsearch, Kibana, Logstash, and Beats. Availability This functionality is in technical preview and is ready for evaluation. Use with caution in production; it is not recommended for mission-critical workloads. Elastic will work to fix any issues, but features in technical preview are not subject to the support SLA of official GA features. Specific Support terms apply. 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.
Serverless
Preview
Preview
Stack
Preview
Preview
elastic stack kb context-engine post-context-engine-ai-index \
--dest <dest> \
--id <id> \
[options]
Create an AI Index
Behaviour flags:
--dry-run — validate all inputs and exit without performing any action
--deststringrequired- The data stream or index that backs the AI Index.
--idstringrequired- The unique identifier of the AI Index.
--automationsstring[]-
Automations associated with the AI Index. Defaults to an empty array when omitted.
Repeatable: pass
--automationsmultiple times to supply more than one value --descriptionstring- Human-readable description of the AI Index.
--feedback-analysisstring- The recurring feedback analysis, which reads agent signals and proposes improvement actions for the AI Index.
--sourcesstring[]-
Additional sources that provide context for the AI Index. Defaults to an empty array when omitted.
Repeatable: pass
--sourcesmultiple times to supply more than one value --tracesstring[]-
Trace sources linked to this AI Index. A write replaces the whole array. Defaults to an empty array when omitted.
Repeatable: pass
--tracesmultiple times to supply more than one value --input-filestring- path to a JSON file to use as command input
--dry-run- validate all inputs and exit without performing any action (preview changes without applying them)
--no-validate- skip input validation and send the request as-is
--output-fieldsstring- comma-separated list of fields to include in output (dot-notation supported)
--output-templatestring- Mustache-like template for custom text output (e.g. "{{id}}: {{name}}")
--json-
output as JSON