Find answers from the community

Updated 8 months ago

Query

Hey! I have a question, regarding this tutorial: https://docs.llamaindex.ai/en/stable/examples/retrievers/auto_merging_retriever
So, how would I go about querying the leaf nodes from an external vector database?
Query all the nodes, and get the leaf nodes? That sounds a bit expensive in terms of computation.
L
T
7 comments
I think typically only your leaf nodes would be in the vector store
The other nodes are pulled from the docstore when merging needs to happen
Oh, I see. What if the whole thing happens in an IngestionPipeline?
It's a bit more complicated
Yea definitely more complicated -- not sure I would recommend that πŸ˜… you could have a custom transformation step to sort out the leaf nodes vs. Everything else to avoid indexing non-leaf nodes (and would also give you a chance to throw the nodes into a docstore?)
Okay.. but I'm thinking it might not even be worth it to use this approach πŸ˜„
I mean it loads all the node into memory, right?
Depends if you use a remote docstore and vector store or not
Add a reply
Sign up and join the conversation on Discord