Using Unstructured for an End-to-End RAG Data Setup | Unstructured

In this session from RAG++ London, Ahmet Melek from Unstructured walks developers through the process of making data "RAG ready" (Retrieval-Augmented Generation). Learn how to efficiently extract data from multiple sources such as Slack, Notion, PDFs, and PowerPoints, and prepare it for use in large language models (LLMs).

Ahmet discusses the challenges of parsing unstructured data locked behind different formats and the innovative strategies Unstructured offers, such as their high-res and fast parsing options. He also demonstrates how to use Unstructured’s tools for data chunking, embedding, and uploading to various destinations like Astra DB.

Видео Using Unstructured for an End-to-End RAG Data Setup | Unstructured канала DataStax