Simple to Complex Agentic RAG Crash Course over your PDFs 🔥 This blog post by Sulaiman Shamasna gives you a comprehensive tour through building agentic RAG over your PDFs, starting with individual components (routing, tool use, multi-step reasoning), and expanding into full

I’ve noticed that the majority of RAG and agent use cases are internal-facing (internal enterprise search, research, etc.). What I like about this case study collab with GymNation is they were able to deploy AI agents for a range of different external use cases and quantify

Building a Hybrid PDF+SQL agent from scratch 🤖 This notebook shows you how to build a custom agent that can either query your unstructured data retriever (courtesy of LlamaCloud) or a SQLite database of structured data. Use our event-driven workflows to define an agent system

Building a knowledge slackbot over Notion with Llama 3.1 🔥 This video by Jason Zhou is a great overview of Llama 3.1’s innate tool calling abilities, as well as the full sequence of steps needed to create a full functioning agentic Slackbot: 1. Setup a connection to Notion

A big category of “advanced RAG” applications is to expand the output to be a unit of knowledge work, beyond an unformatted chatbot response. More specifically, this “unit” can be a full research report, slide deck, or Excel spreadsheet. This has been a big topic of interest to

An underrated part of the LlamaIndex 🦙 ecosystem is LlamaTrace - a full-blown observability and evaluation solution in partnership with Arize AI, that’s currently completely free for any developer to signup and use! 💫 For instance, check out this blog by Farzad Sunavala that shows

Auto-Document Retrieval 📑 It increasingly makes sense to retrieve entire documents instead of chunks for RAG - but given a large set of documents, how do you retrieve the right ones? This notebook shows you how to combine the benefits of RAG with structured querying to more

Get LLMs to generate a PowerPoint deck from your speaker notes! This is a great example of how LLMs can free you up from mechanical work to spend more time on creativity. Built in pure TypeScript by Laurie Voss, this app: 📝 Summarizes your speaking notes into slides 🖥️ Generates

Learn how to build LlamaIndex Workflows in this event from AI Makerspace! 🚀 Learn how workflows' Event-Driven Architecture (EDA) produces more effective agent implementations: 🔹 Understand the differences between pipeline, graph, and event-driven approaches 🔹 Master core

How to evaluate your RAG pipeline for financial reports using LlamaIndex and Giskard 📊🔍 In this guide, learn to assess the performance of your Retrieval-Augmented Generation system: 🔹 Generate diverse test questions automatically 🔹 Evaluate RAG components: Generator,

🙌 Join us for a deep dive and live Q&A on the NVIDIA and LlamaIndex 🦙 #DevContest 🌟 📆 Sept 5 at 9 a.m. PT 📍 On Discord: nvda.ws/3MydIYA We'll cover all the details and resources you will need -- whether you're an experienced developer or new to NVIDIA and LlamaIndex.

In our latest case study, see how Netchex used LlamaIndex to create AskHR + Netchex AI, revolutionizing employee support for small to medium-sized businesses. 🚀 Developed by just two engineers in one month 🤖 Implements advanced RAG pipelines for context-aware responses 📊

create-llama remains the best way to go from zero to sixty in LlamaIndex, with a ton of templates to match your use-case. Our latest addition is a multi-agent workflow in Python! The example flow uses three agents to generate a blog post: ⭐️ a researcher the retrieves content

Announcing the launch of llama-deploy, our system for deploying microservices based on LlamaIndex Workflows! We've learned a lot in the last few months since llama-agents and Workflows were released and this is a major step forward in our evolution: ➡️ Seamless deployment of

If you want to see an end-to-end example of deploying an agentic system as microservices using llama-deploy, Logan Markewich has got you! This open-source full-stack example shows how to build an agentic chatbot system using Reflex as the front-end framework and LlamaIndex

Automatic meeting creation + scheduling with Cerebras Llama3.1 + LlamaIndex 🦙 + Composio. Amazing what you can build in just 50 lines of code! #BuiltonCerebras

If your laptop can handle it, you can run Reflection 70B using Ollama and start working with it from LlamaIndex today!

Learn to build advanced agentic RAG pipelines with LlamaIndex and Amazon Bedrock! Go step by step: 🔍 Create a RAG pipeline using Amazon Bedrock models and top-k vector search 🧠 Implement dynamic query routing for semantic search or summarization 🔀 Use query decomposition to

We’ve made a huge new release that lets you build a multi-agent application in one CLI command 🔥 This template creates an agentic report generation system consisting of a researcher, writer, and reviewer. Every agent step is streamed through to the UI along with the inputs and

Automating quarterly/annual financial analysis with agentic workflows 📈🤖 This blog post by ManthaPavanKumar shows you how to build a simple agentic summarization system that can perform analysis on each financial quarter and then aggregate the results together to produce a