‍

Aryn DocParse is an easy way to get high quality document parsing as an input into your retrieval-augmented generation (RAG) application. In a joint blog with Elastic, we show how to easily build a document ETL pipeline with Aryn DocParse to parse, chunk, and embed PDFs and load into an Elasticsearch cluster. You can then use that data in a RAG pipeline. Check out the blog or Jupyter notebook with the ETL code.