Today is National Llama Day.

“Intelligent Document Processing” 📑🧪 as an industry is gone . With our latest release this week, *anyone* can build and deploy a specialized document agent in seconds ⚡️🤖, and customize the steps via code. Let’s take a tour through our invoice processing and contract matching

I’m excited to kick off the first of our short courses focused on agents, starting with Building Agentic RAG with LlamaIndex, taught by @jerryjliu0, CEO of @llama_index. This covers an important shift in RAG (retrieval augmented generation), in which rather than having the

Unlock LLM agents! This tutorial guides beginners from basics to advanced, with practical examples using LangChain & LlamaIndex. Dive in! https://t.co/hJ01Y3pxHp #LLMAgents #AI #LangChain #LlamaIndex #GenAI #Tutorial #Python #OpenSource

Memory for Agents in LlamaIndex @llama_index uses flexible memory blocks to blend short-term chat history and long-term memory via plug-and-play blocks: > StaticMemoryBlock for static information > FactExtractionMemoryBlock for facts extracted from the chat history >

Build a 100% local, private, and secure MCP client. You can connect it to any MCP server. Step-by-step guide:

The Azure Container Apps Samples page with JavaScript & TypeScript samples and AI-powered patterns with RAG, MCP, LangChain, LlamaIndex https://t.co/tfDfMTenuK #Azure #ContainerApps #JavaScript #TypeScript #AI #LangChain #LlamaIndex #RAG #MCP #CloudNative #msftadvocate

For the first time in human history, you can: 1️⃣ Take a bucket of docs/PDFs 🪣📑 2️⃣ Make sense of it 3️⃣ Extract insights / search over it with super high accuracy with effectively 0 humans involved. This is a neat joint stack we copublished with @MongoDB, check it out!

🚀 Top 15 AI Agent Builders Crushing It in 2025! LangChain, AutoGPT, CrewAI, LlamaIndex & more 🔥 Who's your pick? #AIAgents #AI2025

watching people build "production ready RAG" with these frameworks https://t.co/Su62w3YzjR

We are updating the integrations in our core documentation. We are publishing all the improvements and implementations developed in recent days. Check out our integration guides with: -LangChain; -CrewAI; -OpenAI Assistants; -LlamaIndex; -Anthropic; -Raw API / cURL.

The biggest bottleneck in RAG isn’t your vector DB or your embedding model. It’s your Ingestion Pipeline. 📉 @llama_index just solved the problem. If you feed a single PDF containing 10 different invoices into your retrieval system, you are polluting your context window.

Explore the new course Building Agentic RAG with LlamaIndex, taught by @jerryjliu0, CEO and co-founder of @Llama_Index. Build and debug agents that navigate, summarize, and analyze data from multiple sources. Start learning today: https://t.co/Zn3p5YQ1IG

A tutorial on customizing your LlamaIndex RAG application! Answers to all your FAQs with code snippets...👇

Build a powerful AI finance agent with Python and LlamaIndex (get the code and walkthrough below):

Build Financial Analyst Agents with Python and LlamaIndex:

Drag & Drop to build AI Agent Workflows. LlamaIndex just released a visual UI to build and run complex agentic workflows. Works with OpenAI, Claude and Gemini. 100% Opensource.

LlamaIndex provides the key components to easily connect/index your data for LLM use. 🗂️🛠️🧠 Over the past two weeks we’ve made LlamaIndex much more modular and much more powerful. Let’s take a tour - we’d love your feedback as to how to best improve each module! 🧵

This is an extremely exciting initiative on Saturday. I'm especially excited about the fact that they're creating evals for their task! Bummer it's only in SF. Folks who are there should give this a shot!! I was asked to share the event, but I wanted to find a moment to write