LlamaIndex Newsletter 2024-12-03

Hello, Llama Fans! 🦙

Welcome to this week’s edition of the LlamaIndex newsletter! We’re excited to announce the launch of Azure OpenAI endpoints in LlamaParse, enabling secure document parsing integrated with LlamaCloud and Azure AI Search for seamless RAG workflows. Plus, don’t miss out our community tutorials, guides and webinars.

If you haven't explored LlamaCloud yet, make sure to sign up and get in touch with us to discuss your specific enterprise use case.

🗺️ LlamaCloud And LlamaParse:

• We have launched Azure OpenAI endpoints in LlamaParse, providing secure and compliant parsing of complex documents, integrated seamlessly with LlamaCloud and Azure AI Search for cohesive RAG workflows, including detailed guidance and code examples. Blogpost, Tweet.

💡 Guides:

• Ravitheja's video tutorial on setting up a LlamaCloud pipeline using Google Drive as a data source, detailing the process to create, deploy, and manage an index.
• PyQuant News’s video tutorial on using LlamaIndex to analyze NVIDIA's financial statements.
• MemVerge's tutorial on boosting RAG pipeline performance by integrating CXL memory with LlamaIndex, significantly increasing queries per second while preserving low latency.
• Guide to Boosting RAG Performance—learn how to use Ragas, LlamaIndex, and LiteralAI to evaluate and optimize your system, focusing on context precision, recall, and answer relevancy, and gain practical tips to improve your RAG system before deployment.

🎙️Webinars:

• Join us on December 4th at 5 PM for the Multi-Agent meet-up at GitHub HQ to explore building agentic RAG with LlamaIndex, featuring insights from industry experts and hands-on demonstrations.
• Join us on December 5th at 9 AM Pacific for a webinar exploring advanced RAG capabilities with LlamaIndex and MongoDB.