By using AWS re:Post, you agree to the AWS re:Post Terms of Use
AWS re:Postre:Post

How to filter by field in Kendra using the Confluence connector

0

I use Kendra to index our Confluence spaces with the Confluence v2 connector. Apparently, I can only filter out content in the data source based on the document titles and don't seem to have access to the indexed fields (such as cf_label). I want to filter out content from the index based on regular expressions on the cf_label field. I am using this index in Amazon Q and am trying to remove pages based on a tag in the label field on a confluence page.

Topics
Machine Learning & AI
Tags
Amazon KendraAmazon Q
Language
English
Tom Richards
asked 14 days ago116 views
1 Answer
1

Hi Tom,

You should have granularity in selecting the Index Field. If you click on 'Add field' on the field mapping section of the data source connector, you should be able to select an existing 'Index field name', which in this case would be cf_label (If this does not currently exist within your environment, then you can also create an index field name named cf_label). From there you can select the object type (Page, Blog, etc.).

Thanks,

Autrin

AWS
autrin
answered 2 days ago
  • Tom Richards
    16 hours ago

    So I can definitely see the field in the field mapping, but I have no way in the connector to actually run an exclusion REGEX on that field. My only option is to do this on a Title field for pages. I can exclude a "Space Key" to remove an entire space. But there is no option to select a mapped field and regex against one of the fields I mapped.

You are not logged in. Log in to post an answer.

A good answer clearly answers the question and provides constructive feedback and encourages professional growth in the question asker.

Guidelines for Answering Questions

Relevant content