nlmatics/llmsherpa
PDF/document parser with layout awareness that extracts structured sections, paragraphs, tables and lists for LLM chunking pipelines.
Not currently ranked — collecting fresh signals.
star history
LLM Sherpa provides APIs for parsing and chunking documents with hierarchical layout information. The LayoutPDFReader extracts sections, subsections, paragraphs, tables, and lists while removing headers, footers and watermarks. It helps developers create optimal text chunks for vectorization and solves context window limitations by joining content spread across pages. The backend service is now fully open sourced as nlm-ingestor.
Frequently asked
- What is nlmatics/llmsherpa?
- PDF/document parser with layout awareness that extracts structured sections, paragraphs, tables and lists for LLM chunking pipelines.
- Is llmsherpa open source?
- Yes — nlmatics/llmsherpa is open source, released under the MIT license.
- What language is llmsherpa written in?
- nlmatics/llmsherpa is primarily written in Jupyter Notebook.
- How popular is llmsherpa?
- nlmatics/llmsherpa has 1.7k stars on GitHub.
- Where can I find llmsherpa?
- nlmatics/llmsherpa is on GitHub at https://github.com/nlmatics/llmsherpa.