Adding english documentation on how to configure lambdas on cloudprem.

[fulmicoton-dd]

What does this PR do? What is the motivation?

We recently introduced a new feature that allows to offload Logs Cloudprem work to AWS Lambda.
This feature is experimental and AWS specific.

Merge instructions

Merge readiness:

• Ready for merge

[6/5/2025] Merge queue has been disabled on the documentation repo. If you have write access to the repo, the PR has been reviewed by a Documentation team member, and all of the required checks have passed, you can use the Squash and Merge button to merge the PR. If you don't have write access, or you need help, reach out in the #documentation channel in Slack.

AI assistance

I used to Claude code for the initial draft. It based it off our repository documentation.
https://github.com/quickwit-oss/quickwit/blob/main/docs/configuration/lambda-config.md

[Copilot]

Pull request overview

Adds documentation for configuring Lambda-based search offloading in CloudPrem (AWS-only) and links it from the CloudPrem “Configure” landing page.

Changes:

• Introduces a new lambda.md page describing Lambda search offloading, IAM prerequisites, and Helm values configuration.
• Updates the CloudPrem configure index to include a “Lambda Search Offloading” navigation entry.

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 5 comments.

File	Description
content/en/cloudprem/configure/lambda.md	New doc page covering feature overview, IAM role policies, and Helm configuration for Lambda search offloading.
content/en/cloudprem/configure/_index.md	Adds a “Lambda Search Offloading” link in the Configure section’s “what’s next” list.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

In this paragraph the documented config key path (searcher.lambda.auto_deploy.execution_role_arn) is inconsistent with the later Helm values example (cloudprem.searcher.lambda...). This is likely to confuse users; consider using the full Helm values path consistently (and also capitalize ARN as "ARN").

Suggested change

	- **The Lambda execution role**: the role assumed by the Lambda function itself at runtime. This role needs read access to your index data in S3. Its arn has to be set in the
	`searcher.lambda.auto_deploy.execution_role_arn` key as we will see in [Configuration](#configuration).
	- **The Lambda execution role**: the role assumed by the Lambda function itself at runtime. This role needs read access to your index data in S3. Its ARN has to be set in the
	`cloudprem.searcher.lambda.auto_deploy.execution_role_arn` key as we will see in [Configuration](#configuration).

[Copilot]

The lambda:InvokeFunction policy resource ARN ends with :*, which does not match the unqualified function ARN (no suffix). If CloudPrem ever invokes the function without specifying a version/alias (or during create/validation steps), this policy will deny the call. Consider including both the base function ARN and the :* variant (or using a wildcard that covers both).

Suggested change

	"Resource": "arn:aws:lambda:<REGION>:<ACCOUNT_ID>:function:quickwit-lambda-search:*"
	"Resource": [
	"arn:aws:lambda:<REGION>:<ACCOUNT_ID>:function:quickwit-lambda-search",
	"arn:aws:lambda:<REGION>:<ACCOUNT_ID>:function:quickwit-lambda-search:*"
	]

[Copilot]

<link to prerequisites> appears to be a placeholder and will render literally in the published docs. Replace it with an actual link (for example, to the "Prerequisite: IAM permissions" section anchor) and capitalize "IAM".

Suggested change

	After the <link to prerequisites> iam permissions have been properly set up, to enable Lambda offloading, add a `lambda` section under `cloudprem.searcher` in your Helm chart values file:
	After the [Prerequisite: IAM permissions](#prerequisite-iam-permissions) have been properly set up, to enable Lambda offloading, add a `lambda` section under `cloudprem.searcher` in your Helm chart values file:

[Copilot]

Spelling/capitalization in this warning is inconsistent with the rest of the CloudPrem docs ("lambda"/"Cloudprem" should be "Lambda"/"CloudPrem"). Consistent product/feature capitalization helps searchability and avoids looking like a typo in an alert banner.

Suggested change

	<div class="alert alert-warning">If a lambda configuration is present, but invalid, Cloudprem's searcher will fail to start.</div>
	<div class="alert alert-warning">If a Lambda configuration is present, but invalid, CloudPrem's searcher will fail to start.</div>

[Copilot]

The memory size value is written as 5 GiB (with a space), but elsewhere in CloudPrem docs units are written without a space (for example, 2GiB, 500MiB in content/en/cloudprem/operate/sizing.md:115-137). Aligning the unit format here would reduce ambiguity and keep documentation consistent.

[github-actions]

Preview links (active after the build_preview check completes)

New or renamed files

• https://docs-staging.datadoghq.com/paul.masurel/cloudprem-lambda/cloudprem/configure/lambda

Modified Files

• https://docs-staging.datadoghq.com/paul.masurel/cloudprem-lambda/cloudprem/configure/