We wrote a short tutorial on vectorless RAG with a Table of Contents (ToC). In this tutorial, we use PageIndex to create an LLM-friendly ToC for retrieval instead of using chunking/vectors.
Since a ToC is the human way of doing retrieval, we believe AI should work more like humans—and also benefit from this method.
We’re keen to hear your feedback on this approach.
We wrote a short tutorial on vectorless RAG with a Table of Contents (ToC). In this tutorial, we use PageIndex to create an LLM-friendly ToC for retrieval instead of using chunking/vectors.
Since a ToC is the human way of doing retrieval, we believe AI should work more like humans—and also benefit from this method.
We’re keen to hear your feedback on this approach.