🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Did you know? You can retrieve images and illustrative figures from your LlamaCloud Indexes as well as text! This is great for presentations, reports, and other document types that have rich imagery. Enabling this feature is as simple as toggling the "Multi-modal indexing"

RAG POCs are easy, but building production-grade retrieval is legitimately hard. These are things you don’t realize when you’re first starting out building agents - “wow my chat over 10 pdfs works in 10 mins!”. We learned these lessons as we built out LlamaCloud and wanted to

We're all in on context engineering! A related topic that imo is table stakes for every AI engineer/user: workflow engineering 🛠️ A lot of agent use cases revolve around automating work that otherwise a human would have to perform - customer support, legal research, report

While the term “prompt engineering” focused on providing the right instructions to an LLM, “context engineering” puts a lot more focus on filling the context window of an LLM with the most relevant information, wherever that information may come from. 🧠 Context could include

Build citable AI applications with Anthropic's tool calling and citations feature in LlamaIndex 🔗 LlamaIndex now supports Anthropic's server-side tool calling with automatic citations, making it easy to build AI apps that can cite their sources and provide traceable

Practical Techniques for Context Engineering 💡 This is a fantastic blog post from Tuana and Logan Markewich on a comprehensive breakdown of the types of context an LLM can interact with, and the core dimensions you have to consider: 1️⃣ Knowledge Base or tool selection -

This guest post from DeepEval shows you how to build better RAG applications by combining LlamaIndex with comprehensive evaluation: 🎯 Use Answer Relevancy, Faithfulness, and Contextual Precision metrics to measure both your retriever and generator components 🔧 Set up

🧠 Missed the Agent Memory livestream livestream with Laura G Funderburk 🐍🥑 & Tuana ? You can watch the full session on YT 👇 We're now building memory-aware agents, from short-term memory buffers to long-term memory. This session breaks down how memory gives LLM agents real

🔍 Extracting the core knowledge from documents is a common problem for many people, from students to corporate employees - and many people have found NotebookLM useful . But what if you could have your own, fully open-source NotebookLM, running on your computer at any time you

Our next office hours on July 8th will be all about MCP. Join the team in our Discord server to ask all of your LlamaIndex questions, but also get a rundown of: · LlamaCloud MCP servers · Using existing MCP tools with Agent Workflows · Serving agent workflows as MCP · Extending

Introducing NotebookLlama - an open-source version of NotebookLM! 📓🦙 NotebookLlama is a full implementation of NotebookLM that includes all the capabilities that makes it so great for researchers+business users: ✅ Create a knowledge repository of documents. Has likely higher

Join us for another AI Hack Night at GitHub where you'll build cutting-edge applications with AI Agents, MCPs, RAG and more! 🚀 This hands-on event gives you 2.5 hours to create something amazing alongside fellow developers in San Francisco. 🎤 Lightning talks from leading AI

Build a complete structured data extraction workflow with human-in-the-loop validation for data extraction 📄🔄 This demo notebook shows how you can use LLMs to pre-process your data to create exactly the schema you need for bulk extraction work. 📋 Parse documents using

Tomorrow! Our next office hours hangout will be all about MCP. Join the team in our Discord server to ask all of your LlamaIndex questions, but also get a rundown of: ➡️ LlamaCloud MCP servers ➡️ Using existing MCP tools with Agent Workflows ➡️ Serving agent workflows as MCP ➡️

One of the biggest pain points in using LLMs for large-scale document extraction is actually coming up with the schema in the first place - it’s a long and tedious process ⏳ We built an two-stage, e2e agent workflow that does both schema generation and extraction: 1️⃣ It first

Want to see how you can use LlamaCloud tooling as MCP tools? Well, we have a few MCP server templates, and in this video Tuana walks you through our LlamaCloud MCP server in Python 👇 · Use your extract agents as MCP tools · Query any index you have in LlamaCloud as MCP

Build a complete RAG pipeline using our LlamaParse document parser with Snowflake Cortex for enterprise-grade document processing and search. This tutorial shows you how to combine LlamaParse's agentic parsing capabilities with Snowflake's powerful data platform: 📄 Parse

Building the MCP Toolbox for Documents 🛠️📑 This is a fantastic tutorial from Tuana showing you how to give your favorite AI agent frontend (in this case Claude Desktop) access to all the tools to process and manipulate document context, thanks to LlamaCloud. 1️⃣ Do

Friend of LlamaIndex Yujian Tang has launched a LinkedIn learning course that's all about using LlamaIndex for RAG! The course covers how to: ➡️ Build a retrieval-augmented generation application from scratch in Python. ➡️ Mix and match the different tools needed to build an RAG

Build RAG applications with Google Cloud's Gemini models using our LlamaIndex integration 🚀 Google Cloud Platform has created a comprehensive sample app showing how to combine Gemini's powerful language capabilities with LlamaIndex for production-ready applications. 🔧