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

Not able to fetch Confluence documents for Bedrock Knowledge Bases

0

I have been trying to get Bedrock Knowledge Bases to fetch documents that contain "log" or "logging" from a Confluence space called "Observability" (or "OSRE" in the URL path) using different variations of the following regular expressions:

  • Space: /(Observability|OSRE)/i
  • Pages: /(log)/i

Enter image description here

Enter image description here

This doesn't get any result for all of the variations I tested and I cannot see why nothing matches.

The fetching works well though when none of these filters is applied, so the problem is not in connecting/accessing Confluence.

Am I missing anything?

Topics
Machine Learning & AIGenerative AI on AWS
Tags
Machine Learning & AIAmazon BedrockGenerative AI on AWS
Language
English
asked a year ago411 views
1 Answer
0

Hi,

Agreed on the fact that your connection seems ok.

But, did you activate the Bedrock ingestion logs to see if the documents you want to load are problematic (parsing, etc.) at ingestion time?

See https://docs.aws.amazon.com/bedrock/latest/userguide/knowledge-bases-logging.html

Best,

Didier

AWS
EXPERT
answered a year ago
EXPERT
reviewed a year ago
  • redouane
    a year ago

    Thanks for you answer @dider, I have application logs enabled and can see logs related to the following job types:

    • INGESTION_JOB_STARTED
    • CRAWLING_COMPLETED
    • COMPLETE

    But none of them has any data (shows 0 documents ingested).

    Any idea what could be missing?

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