100 Days of Gen AI: Day 29

Today I augmented my slackbot knowledge base with some additional data sources. In addition to the existing confluence data source, I also added relevant slack threads and public documentation from Terraform Cloud. Amazon Bedrock has a native option for crawling a website, so that made the Terraform Cloud documentation easy to collect. However slack messages were a bit more complicated.

Most slack messages are not relevant to Terraform Cloud usage, plus we don’t want to grant read access to the entire company slack history. For this proof of concept (and in the interest of time), I just hand selected a few slack threads, copy/pasted them into a .txt file, and uploaded this to s3 for the knowledge base to ingest. However a more robust idea for the future could be to create a slack webhook that allows you to simply add a comment to a thread such as “@help-terraform-cloud remember this thread”, which could then save the thread history to the knowledge base for future queries.