LlamaIndex Webinar: Tree-Structured Indexing and Retrieval with RAPTOR

​RAPTOR is a recent paper that introduces a new tree-structured technique, which hierarchically clusters/summarizes chunks into a tree structure containing both high-level and low-level pieces. During query-time, there is the option of traversing the top of the tree or querying everything as a flat list.

​This resolves issues with naive top-k RAG: naive RAG retrieves low-level details best suited at answering questions over specific facts in the document. But it struggles with any questions over higher-level context.

​We're excited to host the authors: Parth Sarthi, Salman Abdullah, Shubh Khanna et al. for a special webinar. The authors will be presenting the paper itself and we'll do a Q&A talking about tree-structured retrieval more generally.