Aye nice! Just tried it, super cool! How do you manage us hitting the context limit?
Hi, we generate a table of contents (ToC) for each document, so LLM can use the ToC to navigate the long documents, which can bypass the context limit. You can checkout this notebook for a quick toturial about our method: https://docs.pageindex.ai/cookbook/vectorless-rag-pageindex
Oh nicee! Wanna chat on a meet? Curious to know the usage behavior of your users & pilot it internally as well.