versatile-data-kit
versatile-data-kit copied to clipboard
vdk-examples: llama data job
A job that uses LLamaIndex to fetch data from confluence and to create embeddings to local postgres database with pgvector
Further reading: https://github.com/vmware/versatile-data-kit/wiki/VDK-and-LLamaIndex
I am confused here. I see another example using the langchain confluence reader and also we have a confluence reader plugin.
why are we reading from confluence in 3 different ways?