yoheinakajima / babyagi

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Why store result in a vectorstore?

RasmusN opened this issue · comments

Why is the result from executed tasks stored in a vector store rather than a regular DB?

As far as I can see it's only used by the execution_agent to list what tasks have already been done. Why do we need an embedding index for this? Why not just index by task_id or even more simple, just keep it in memory?