Hi I have a question about the

ggabbyjai

Hi I have a question about the composability. Most of the examples in your documentation only shows two level of indices (i.e. a graph index on top of many document indices). In theory, we could expand it to more than 2 levels, so I'd like to ask if that's feasible, and is there any example / reference that I could take a look.

For more context, the current problem I am working on may require me to have a top level index on top of multiple graph indices, and each graph index may consist of many document indices.

Attachment

6 comments

LLogan M

You can definitely do this, but be aware each layer is going to increase response time

I'm pretty sure you can just from from_indices() to create the new top layer, and you can get the graph index by using graph.root_index

ggabbyjai

Thank you for your quick response. I have a follow up question. If I want to do compare/contrast on the document index level, what would be the best approach?

LLogan M

Probably best to use a sub question query engine for that

https://gpt-index.readthedocs.io/en/latest/examples/query_engine/sub_question_query_engine.html

ggabbyjai

What is the difference between using sub question query engine and using the DecomposeQueryTransform?

LLogan M

Pretty much the same tbh, the decompose query transform is built more for graphs though.

LLogan M

the sub question query engine has an easier to understand interface imo

Add a reply

Find answers from the community

Hi I have a question about the