Knowledge Indexing - Slack
This is a 'Workflow' template which means that it is a single standalone workflow.
Some workflow templates can be modified to work with other workflow templates - e.g. to convert a data sync between two services from uni-directional to bi-directional
OverviewCopy
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!
Set-upCopy
Import the Project into your Tray instance.
Create a Data Tables in this Project. It should have the following columns:
Link to Thread
Original Message (part)
Decision
Reason
Create a Vector Table in this Project. It should have the following configurations:
`Name`: Could be anything
`Dimensions`: 1024
`Metric`: Cosine
💡The Embedding Model this Project uses is the Amazon Titan Embedding Text v2.
Open the `Slack extract` workflow and open the Config Settings. Configure the Config variables:
`latest_timestamp`: Slack threads **after** this timestamp will not be extracted.
`oldest_timestamp`: Slack threads **before** this timestamp will not be extracted.
`slack_channel`: The Slack channel where the workflow should grab the threads from.
`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.
Open the `Slack Audit + KB Creation + Vector Table Push` workflow and configure some steps:
`data-tables-1`: Pick the Data Table (the one that was created in Step 2) in this Project for this step.
The columns should be in this order:
`Link to Thread`
`Original Message (part)`
`Decision`
`Reason`.
`vector-tables-1`: Pick the Vector Table (the one that was created in Step 3) in this Project for this step.
Next StepsCopy
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!