Generating large language model outputs from stored content items

Abstract

The present disclosure relates to systems, non-transitory computer-readable media, and methods for generating content-item-specific large language model responses from content items by segmenting a content item and selecting relevant sections of the content item to provide to a large language model to generate a corresponding output. In particular, in one or more embodiments, the disclosed systems can generate a text representation that includes a plurality of text segments each comprising a number of tokens of the text representation. Further, the systems can extract, from the plurality of text segments, segment-specific text embeddings that correspond to respective portions of the text representation of the content item. Additionally, the systems can determine a segment-specific text embedding corresponding to a model output request. Moreover, the systems can generate a model output by passing a text segment corresponding to the segment-specific text embedding to a large language model together with the model output request.

Dependencies are inferred from the claim text.