Hi there, Llama Enthusiasts! 🦙
Welcome to this week's edition of the LlamaIndex newsletter! We're excited to share some incredible developments including our recognition by TechCrunch as one of the 60 companies shaping AI, groundbreaking insights on DeepSeek's vision compression technology, and powerful new integrations with our TypeScript SDK and AWS Bedrock. Plus, we've got exciting tutorials on anomaly detection workflows and text-to-SQL systems that showcase the real-world impact of AI agents.
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.
📆 Upcoming Webinar:
- Document Processing at Scale: Join us this Thursday for a webinar on document processing pipelines with LlamaParse and MongoDB. Extract meaningful insights from PDFs, reports, and contracts with intelligent parsing and vector search capabilities. Webinar Registration
🤩 The Highlights:
- Advanced Text-to-SQL with Arctic Models: Build sophisticated text-to-SQL applications using open-source Arctic models and our Workflows orchestration system, featuring semantic table retrieval, multi-step workflow orchestration, and built-in error handling for production-ready applications. Complete implementation.
- DeepSeek OCR Revolution: Deep dive into DeepSeek's new OCR model that compresses 1,000 text tokens down to just 100 vision tokens with 97% accuracy - representing a 10x compression while maintaining quality and changing how we think about document processing. Read our analysis.
- Anomaly Detection with LlamaAgents: Learn how to design, build, and deploy AI/ML-powered anomaly detection workflows using Qdrant, Supabase, and LlamaAgents in this comprehensive tutorial. Watch the tutorial, Join LlamaAgents waitlist.
🗺️ LlamaCloud & LlamaParse:
- LlamaClassify TypeScript SDK: Our state-of-the-art agentic document classification service is now available in the TypeScript SDK with a TanStack + DaisyUI demo for financial documents classification. Try the demo, Learn more.
- llamactl CLI Tool: Build and serve LlamaAgents locally with our new CLI tool featuring project initialization from templates, local development with auto-dependency installation, and instant deployment to LlamaCloud. Getting started guide.
✨ Framework:
- AWS Bedrock AgentCore Memory Integration: Use Bedrock AgentCore Memory with LlamaIndex Agents for both long-term and short-term memory management, featuring secure storage, access control, and built-in scalability. Documentation.
- TechCrunch Recognition: Proud to be named by TechCrunch and Greenfield VC as one of the 60 companies shaping AI. Read more.
✍️ Community:
- Money2020 Vegas: LlamaIndex is headed to Money2020 in Las Vegas to meet with fintech and financial leaders, showcasing how AI agents are transforming underwriting, compliance, and operations. Book a meeting.
- Snowflake Build Session: Join our session at Snowflake Build featuring Tuan Celik demonstrating how to create powerful data analysis agents using Arctic Text2SQL R1 7B model and LlamaIndex Workflows. Register for Snowflake Build.
- AI Leader Series: Watch our latest interview with Dhruv Shah, VP of AI Engineering at One Carlyle, discussing how intelligent agents are transforming finance by combining innovation, reliability, and trust. Watch the interview.
