Lesson 2
Working with Knowledge Bases
This lesson covers the management of knowledge bases in Bland.
LEARNING OBJECTIVES
Create and update vector stores with POST operations
List vector stores and their details using GET operations
Delete vector stores with POST operations
What is a Knowledge Base?
A knowledge base is data converted to numbers so that a machine (like our Agent) can read it. In the scheme of Bland, you can think of knowledge base as ‘guidebooks’ or ‘answer keys’ that our Agents can use to look up information.
Why Are Knowledge Bases Useful?
So why bother with a knowledge bases when you could just tell your Agent what to do in a prompt?
If you remember from our prompting guide prompts do best when they can be kept under 2,000 words. So naturally, knowledge bases come in handy when you want your agent to have access to more information.
Quick Example
Maybe your Agent is doing some sales calls to prospective clients and it’d be handy for it to have access to all of the features, benefits, and pricing options of your current product.
Passing that info via a knowledge base is a great way to make sure you Agent can handle those kinds of questions.
Note: The agent will automatically search the knowledge base for you (if it determines that it needs more information).
Using Knowledge Bases with the Bland API
You can find API information about Knowledge Bases in our Docs here: Link
