Hi Logan, I built a neo4j graph database

ttheta

Hi Logan, I built a neo4j graph database separately from using the KnowledgeGraphIndex so I inserted all the cypher on my own. Now I want to use a SubQuestionQueryEngine to merge a VectorStoreIndex and my graph store, but the documentation says I have to pass query engines. But as far as I understand it, I need to use the KnowledgeGraphRAGRetriever to access my graph database. Can I use a retriever as a tool for SubQuestionQueryEngine? If I need to pass a query engine, is there an easy way I can use my existing graph data to populate an Index? PS. I know you're refactoring the knowledge graph stuff so can wait until that is released. Thanks kindly!

8 comments

LLogan M

You can take the retriever and put it into a RetrieverQueryEngine

LLogan M

Plain Text

from llama_index.query_engine import RetrieverQueryEngine

query_engine = RetrieverQueryEngine.from_args(kg_retriever, service_context=service_context)

ttheta

ok cool, thanks. I'll give it a try 😄

ttheta

Can we use the TokenCountingHandler class with the KnowledgeGraphRAGRetriever? I tried to implement it and got an error back:

WARNING  Error in retrieving from nl2graphquery: 'CompletionUsage' object has retrievers.py:790
                             no attribute 'get'

LLogan M

hmmm what version of llama-index do you have?

ttheta

Version: 0.9.22

LLogan M

I think this is fixed if you updade (I hope anyways, that token counter is a pain lol)

ttheta

hahaha. up until now i haven't been paying that much attention to tokens but I need to at least put an estimate to various costs to run this thing 😂

Add a reply

Find answers from the community

Hi Logan, I built a neo4j graph database