LlamaIndex 周报：LlamaExtract 公测、MCP 集成与 Agent 模板

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 LlamaExtract in public beta, a step-by-step tutorial on building agentic reasoning systems, and a collection of templates for automating knowledge work. Dive into these highlights and more to enhance your experience with our tools!

Explore our free and paid plans today.

🤩 The Highlights:

Step-by-Step Tutorial on Corrective RAG: Check out this fantastic tutorial by @akshay_pachaar on building an agentic reasoning system for search and retrieval (specifically, corrective RAG) from scratch using @llama_index workflows. Learn more.
Task-Specific Agent Templates: We’re curating a collection of templates that show you how to build task-specific agents to automate knowledge work. With just a few lines of code, you can orchestrate workflows for various tasks, including processing slide decks and extracting invoice line items. Explore the templates and sign up for LlamaParse.
Model Context Protocol Integration: Connect your LlamaIndex agents to any Model Context Protocol server! This integration allows you to use tools exposed by any MCP-compatible server in your LlamaIndex agent with just one line of code. Install the integration and see a full demo.

🗺️ LlamaParse & LlamaParse:

LlamaExtract Public Beta: LlamaExtract is now in public beta! This tool allows you to extract structured data from long, complex documents effortlessly. Read the full post and sign up for LlamaExtract.

✨ Framework:

Enhanced Workflows for LlamaIndex: We’re excited to announce updates that allow you to orchestrate complex, customizable event-driven agent workflows using @llama_index. This enhancement is crucial for building robust AI solutions. Check out the introduction to workflows.

✍️ Community:

AI and Web Development Insights: Join industry experts at @WeAreDevs WebDev & AI Day on March 27 to learn about AI's role in platform engineering and developer tools. Learn more about the event and get a 15% discount on us! Claim your discount.
5th LLM x Law Hackathon: Participate in the upcoming hackathon at @stanford on April 6, where innovators will develop AI solutions for legal work. Sign up to participate.
Updated AnthropicAI Cookbook: We’ve expanded our @AnthropicAI cookbook with new features, including basic API setup, streaming support, and multi-modal capabilities. Check it out here.
Real-Time Knowledge Graph Exploration: Explore a knowledge graph in real-time using LLMs with the impressive demo from @yworks showcasing their SDK for visualizing knowledge graphs. Read their blog or head to the repo.

Thank you for being part of our community! Stay tuned for more updates, and don’t hesitate to reach out with any questions or feedback.