‍

Building a RAG application using the Amazon OpenSearch Service and need to get your parsed, enriched, and loaded? Look no further than our new blog post with AWS on their Big Data Blog: Supercharge your RAG applications with Amazon OpenSearch Service and Aryn DocParse

In this article, we show how to use DocParse to parse, extract, and OCR documents. This is a step in a Sycamore document ETL pipeline, that performs metadata extraction, data cleaning, and chunking, and loads an OpenSearch cluster in Amazon OpenSearch Service. You can also check out the Sycamore document ETL pipeline from the blog in this notebook.

We'd love to hear how you use DocParse and Sycamore with your OpenSearch deployments - drop us a line on Slack.