LlamaIndex 周报：LlamaClassify 推出 TypeScript SDK，新增原生 MCP 搜索集成

Hi there, Llama Enthusiasts! 🦙

Welcome to this week's edition of the LlamaIndex newsletter! We're thrilled to share some exciting developments including the expansion of LlamaClassify to TypeScript. Plus, we've got native MCP search integration, and hands-on workshops to help you build production-ready AI systems.

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

Explore our free and paid plans today.

🤩 The Highlights:

• LlamaClassify TypeScript SDK: Our state-of-the-art agentic document classification service is now available in TypeScript, complete with a financial documents classification demo. Demo, Docs
• Native MCP Search Integration: LlamaIndex now ships with native MCP search for our documentation, enabling coding agents to directly access search tools with lexical search, regex search, and complete page content access. Implementation Details, Try it
• Vibe-Coding Demo: Watch how to create an agent workflow for financial document classification and deploy it to the cloud using Claude Code with vibe-llama. Video, Docs

🗺️ LlamaParse And LlamaParse:

• From Documents to Insight: Integrating LlamaParse with MongoDB: Last week, we hosted a webinar with our friends at MongoDB, where we walked through an end-to-end pipeline to build an agent, capable of handling complex documents. Did you miss it? Watch it here.

✨ Framework:

• Agent Workflows with Memory: Learn how to augment LlamaIndex agent workflows with memory and persistent states for building context-rich AI systems. Video Tutorial, Docs

✍️ Community:

• Fully Connected London: LlamaIndex is sponsoring and speaking at Weights & Biases Fully Connected London (Nov 4–5) with a talk on "Automating knowledge work with AI agents" by Tuana Celik. Event Details