/Docs
slack
aws-bedrock

Knowledge Indexing - Slack

aiIntermediate

Overview

Extract data from their Slack conversations and turn them into Knowledge articles for a Support use-case by using AI. If you need help reach out in the community in the #ai-help channel! Slack Indexing Architecture

Set-up

  1. Import the Project into your Tray instance.
  2. Create a Data Tables in this Project. It should have the following columns:
  3. Link to Thread
  4. Original Message (part)
  5. Decision
  6. Reason
  7. Create a Vector Table in this Project. It should have the following configurations:
  8. Name: Could be anything
  9. Dimensions: 1024
  10. Metric: Cosine
  11. 💡The Embedding Model this Project uses is the Amazon Titan Embedding Text v2.
  12. Open the Slack extract workflow and open the Config Settings. Configure the Config variables:
  13. latest_timestamp: Slack threads after this timestamp will not be extracted.
  14. oldest_timestamp: Slack threads before this timestamp will not be extracted.
  15. slack_channel: The Slack channel where the workflow should grab the threads from.
  16. user_to_skip: A list of Slack user IDs whose Slack messages should be ignored. E.g. at Tray we ignore bot messages sent e.g. by a Jira bot.
  17. Open the Slack Audit + KB Creation + Vector Table Push workflow and configure some steps:
  18. data-tables-1: Pick the Data Table (the one that was created in Step 2) in this Project for this step.
  19. The columns should be in this order:
  20. Link to Thread
  21. Original Message (part)
  22. Decision
  23. Reason.
  24. vector-tables-1: Pick the Vector Table (the one that was created in Step 3) in this Project for this step.

Next Steps

Pair this with our Slackbot and other AI Agent templates to compose your first enterprise Agent. If you need help reach out in the community in the #ai-help channel!