search

aws-samples / Serverless-Retrieval-Augmented-Generation-RAG-on-AWS

A full-stack serverless RAG workflow. This is thought for running PoCs, prototypes and bootstrap your MVP.
MIT No Attribution
44 stars 17 forks source link

Feature: Introducing Kúzu graph database for extra-planar relationships #13

Open giusedroid opened 3 months ago

giusedroid commented 3 months ago

Kúzu is an embedded graph database. We want to explore graph-RAG capabilites to include more relevant information when retrieving semantically.

A good MVP for this would be mapping obvious relationships at ingestion that we cannot store semantically as vectors, for example

page -> next() : page
page -> previous() : page
page -> belongsToDocument() : document
page -> sectionStartsAt() : page
page -> sectionEndsAt() : page
document -> relatesToDocument() : document[]
document -> belongsToCollection() : document[] 
document -> abstract() : string

and at semantic retrieval use the relationships mapped for the retrieved vectors to provide additonal context or exclude other vectors from context placement if they are not related to the most relevant collection. Probably using them in the context of re-ranking.