Where to place the Amazon Kendra metadata files for Amazon S3 data source?

Question

I have the following structure in Amazon S3 under my bucket:

-/kendra-analysis/
         - ead0d0af-e769-4c99-97f7-04e68d1cf8b2.txt
    -/kendra-analysis-meta/
         - ead0d0af-e769-4c99-97f7-04e68d1cf8b2.txt.metadata.json

My data source configuration in Amazon Kendra has the following:

**Data source bucket :**

**Metadata prefix :** kendra-analysis-meta/

**Include prefixes :** kendra-analysis/

It seems like my metadata is not picked up. What am I missing?

Accepted Answer

In this case, the Amazon Kendra index is looking in:

```
/kendra-analysis-meta/kendra-analysis/ead0d0af-e769-4c99-97f7-04e68d1cf8b2.txt.metadata.json
```

because it mirrors the prefix of the first order object underneath the specified metadata prefix.

See: https://docs.aws.amazon.com/kendra/latest/dg/s3-metadata.html

Where to place the Amazon Kendra metadata files for Amazon S3 data source?

Relevant content