Adding a Data Set to an existing project is an essential step for you to set up RAG for your LLM pipeline. To do so, you will need to first have a fully configured Data Set.
This requires a fully configured Data Set. If you haven't done so, please see this guide first.
To add a Data Set to your LLM pipeline:
Go to your project
Add an action by clicking the "+" icon and select "Vector Database"
Select a Data Set (you will need to create and import your data source first before this step)
Add a string or variable to the input; this will be the keyword (phrase) that the system will use for database search. If you don't know what to put, you can use the default settings, or add the "payload" variable.
Hit Save