[DOC] Update document for handle SageMaker throttling

[zhichao-aws]

What do you want to do?

• [x] Request a change to existing documentation
• [ ] Add new documentation
• [ ] Report a technical problem with the documentation
• [ ] Other

Tell us about your request. Provide a summary of the request and all versions that are affected. Background: https://github.com/opensearch-project/ml-commons/issues/2438 Some OpenSearch users deploy their ML models at SageMaker to encode documents. But some times users get throttling exceptions, especially during ingestion, even with bulk size 100. It is hard to diagnose the problem, and the failed documents won't be ingested (may lead to data lost). In 2.15 we implmented retry policy for this problem. The retry policy is binded with the connector client_config. We want to update the documentation about setting the policy, as well as to reduce the max_connections to reduce max concurrency.

What other resources are available? Provide links to related issues, POCs, steps for testing, etc.

[zhichao-aws]

Please assign this issue to me, I'll cut a draft PR by the end of this week.

[zhichao-aws]

document PR: https://github.com/opensearch-project/documentation-website/pull/7331