Abstract: Aspects of the disclosed technology include machine-learning systems and methods for generating an index for machine-learning retrieval augmented generation systems. The method can include accessing a set of documents and for each document in the set of documents, parsing the electronic document into a hierarchical representation based on a layout schema, generating a plurality of document chunks from the electronic document based at least in part on the hierarchical representation, generating at least one annotation for at least one document chunk in the plurality of document chunks, and storing, in a document retrieval index, the plurality of document chunks including the at least one annotation for the at least one document chunk in the plurality of document chunks.