Find answers from the community

Updated 3 months ago

Hi, I am building a RAG app on top of

Hi, I am building a RAG app on top of llamaindex, and would want to store data from knowledge graph and summary index (the json files that are created when you persist the storage_context) remotely to a cloud Db (something like MongoDB). I cant find any good example of how to do so (since I created the knowledge graph by running code on parallel on AWS), and would now just want to save the indexes/jsons on a remote DB. If some of you habe faced similar issues, help would be much appreciated!!

3 comments

WWhiteFang_Jr

One way would be to index everything again but using Mongo this time. That can be done following this:
https://docs.llamaindex.ai/en/stable/examples/vector_stores/MongoDBAtlasVectorSearch.html

But again, Not sure if Mongo allows you to store graph info there.

You could use NebulaGraph store for saving it: https://docs.llamaindex.ai/en/stable/examples/index_structs/knowledge_graph/NebulaGraphKGIndexDemo.html#prepare-for-nebulagraph

vvrda

Thanks for the answer

vvrda

What I actually need is to load from graph database (the same as "index_from_chroma" for vector db) ? Because all I could find is creating the index again and not loading it from db

Add a reply