This repo provides the server side code for llmsherpa API to connect. It includes parsers for various file formats such as PDF, HTML, and text. The PDF parser offers features like sections, paragraphs, links, tables, lists, and more. The installation steps for the ingestor include running each step directly or running the docker file. A rule-based parser is preferred over a model-based parser for its speed and practicality.

1m read timeFrom github.com
Post cover image

Sort: