Feature: add language support to Kendra data store

[massi-ang]

Amazon Kendra supports multiple languages, both when indexing documents and when [querying them], but the Chatbot does not currently use either.

Ingestion:

The proposal is about modifying the document upload function to create a .metadata.json object in S3 (see https://docs.aws.amazon.com/kendra/latest/dg/s3-metadata.html).

The metadata file should contain at a minimum the language of the file.

Query:

At query time, the language of the query is determined via Comprehend (as with Aurora) and used for searching the index (https://docs.aws.amazon.com/kendra/latest/dg/searching-example.html#searching-index-languages)

[github-actions[bot]]

This issue is stale because it has been open for 60 days with no activity.

[github-actions[bot]]

This issue was closed because it has been inactive for 30 days since being marked as stale.