Hi there, Llama Lovers! 🦙
Welcome to this week's edition of the LlamaIndex newsletter! We're thrilled to share some exciting updates, including the launch of LlamaResearcher, a new tool for deep research, enhancements to our agent workflows, and the introduction of a powerful new layout agent. Dive into the highlights below and explore our tutorials and guides to maximize your experience with these innovative features.
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:
- LlamaResearcher - Deep Research with Llama4: A fully open-source project by Clelia Bertelli that offers a complete deep research solution using Llama4. It allows users to submit queries, evaluate them for safety, and generate essays based on web searches. Learn more, Repo.
- MCP Server Management Tool: A handy tool by Marcus Schiesser that simplifies the discovery, installation, configuration, and removal of MCP servers from a single CLI interface. Discover more.
- Multimodal Agent Workflows: A significant update enabling multi-agent systems to handle interleaved text and image messages, enhancing reasoning capabilities. Guide here.
🗺️ LlamaCloud & LlamaParse:
- Grounding Agents with Visual Citations: A new tutorial that shows how to ground agents with visual citations using LlamaParse's layout agent feature. Check it out.
✨ Framework:
- New Layout Agent: A state-of-the-art layout agent that enhances document parsing and extraction with precise visual citations. Learn more.
- Building RAG Workflows: A quickstart tutorial on building a RAG workflow from scratch using Llama 4, focusing on ingestion, retrieval, and generation. Get started.
✍️ Community:
- Auth for GenAI: Excited to see @auth0's Auth for GenAI ship with native @llama_index support, simplifying authentication in agent workflows. Explore the SDK.
- Building a Full-Stack Agent Application: A massive upgrade to create-llama, allowing you to spin up a web application with just one line of code. Check it out.
- Comparing Llama 4 and DeepSeek-R1: A community comparison of Llama 4 and DeepSeek-R1 using RAG techniques. Learn more.
Thank you for being part of our community! We look forward to seeing how you leverage these new features and enhancements in your projects. Stay tuned for more updates!