Hi there, Llama Enthusiasts! 🦙
Welcome to this week's edition of the LlamaIndex newsletter! We're celebrating a major milestone - one year of LlamaCloud! - along with exciting updates including our upcoming Fullstack Agents Hackathon with $20k in prizes, major SemTools improvements, and comprehensive guides for building production-ready document processing pipelines. Plus, don't miss our upcoming webinar on Agentic Document Processing!
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.
🤩 The Highlights:
- Production-Ready Document Processing Pipelines: Comprehensive guide showing how to combine LlamaParse with Confluent and MongoDB to create intelligent document processing systems that handle everything from complex PDFs to real-time embeddings with streaming architectures. Architecture Guide
- Fullstack Agents Hackathon - $20k in Prizes: Join us September 27th at Microsoft SV Center for an amazing hackathon! Partner with CopilotKit, Composio, Microsoft for Startups, B Capital & AI Tinkerers. Start with a boilerplate fullstack agent application and transform it into a powerful agent for your use-case. Register
- Agentic Document Processing Webinar: Don't miss our upcoming webinar on September 30th exploring how to level up your RAG & AI agents with smarter parsing, extraction & indexing of enterprise docs, including layout-/table-aware processing and human-in-loop workflows. Register
🗺️ LlamaCloud And LlamaParse:
- One Year of LlamaCloud Celebration: We're celebrating a full year of LlamaCloud with a brand new site and fantastic new developer hub! Check out all the improvements and new features we've built over the past year.
✨ Framework:
- SemTools Major Updates: Huge improvements including a new
workspacefeature that speeds up search calls over large datasets by caching embeddings with LanceDB (search time goes from minutes to seconds on 1000 papers), plus npm installation support. GitHub
✍️ Community:
- Artificial Unintelligence Conference: Free 24-hour AI conference featuring dozens of world-class speakers including our own Laurie Voss, with sessions designed for every time zone. Speakers | Agenda | Register
- Dragonfly Tutorial: New tutorial showing how to combine LlamaIndex and Dragonfly to build RAG systems in minutes for real-time AI that knows your latest data. Tutorial
- Episode 2 of Answers by GoSenso: Features Laurie Voss from LlamaIndex answering community questions about AI development and best practices. Watch here.
