What does llama index Query Engine use under hood for summarization? It seems like GPT , reason why I'm asking.

Want to build something were we want data to be on premise.
Llama Index is great for on premise RAG. Which works well with local Mongo DB. But the summarization then can't work with GPT ..

@Mikko How can we use Llama Index query engine without passing documents or nodes to it. We have the embeddings already created for each document in MongoDB it also includes some metadata.

We already did that before, now we want to just use the query engine using index stored in MongoDB.

collections.aggregate from MongoDB won't suffice cause we want the summary that query_engine creates.



We followed this tutorial :
https://colab.research.google.com/drive/136MSwepvFgEceAs9GN9RzXGGSwOk5pmr?usp=sharing

Heard you can use a chatbot here to ask questions about llama index how to do that?

Hey all.

How can I use Llama Index to get summarized answers based on data and also get like a list of top 3 items that summary is based on like so:

https://imgur.com/a/9uLmSxD