🔥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

🚀 Run LlamaIndex 🦙 workflows in an OpenAI-style chat UI with just a few lines of code! ✨ Dev mode now lets you edit workflow code directly in the UI Chat UI Features: 1. Canvas panel for editing code/document artifacts 2. AI-generated UI components for workflow events 3. PDF

💡Managing Anthropic Claude Code in a large monorepo? I built a script to automate setup across multiple packages after struggling with our LlamaIndex 🦙 TypeScript repo (70+ packages!) No more manual configuration! Check out the solution: github.com/marcusschiesse… Try it and

LlamaIndex now supports the new OpenAI Responses API features: · Call any remote MCP server · Use code interpreters by using it as one of the built-in-tools · AND generate images with streaming.

Join LlamaIndex at the AI Engineer World Fair AI Engineer in San Francisco (June 3-5)! 🦙🌉 Meet our team, including CEO Jerry Liu, and learn about cutting-edge GenAI applications: 🎤 Jerry Liu speaks on "Building Knowledge Agents to Automate Document Workflows" (June 5,

We’re constantly releasing updates and new features to LlamaCloud. LlamaParse lets you make use of the latest LLMs when parsing complex documents, getting them ready to be used in further AI applications. And now, it supports Anthropic Sonnet 4.0 in agent and LVM modes.

Learn how to build a custom multimodal embedder for LlamaIndex! This guide shows you how to: ➡️ Override LlamaIndex's default embedder for AWS Titan Multimodal support ➡️ Create a custom embedding class handling both text and images ➡️ Integrate it with Pinecone for efficient

Enhanced structured output support for @openai, now in LlamaIndex! @openai recently expanded their structured output support to include new data types like Arrays, Enums and more, plus string constraint fields like dates and times, emails, and IP addresses. We support all of

Sonnet 4.0 is one of the best, if not the best, models for PDF parsing (matched ~only by Gemini 2.5 Pro) We have the rate limits on LlamaCloud, and two modes (use Sonnet 4.0 as an LLM agent, or use as an LVM on top of screenshot) Signup here: cloud.llamaindex.ai

Join us at the AI Engineer World Fair in San Francisco, June 3-5! 🦙🌉 The LlamaIndex team is bringing our A-game to booth G11. Here's what you can expect: ➡️ Chat with our CEO Jerry Liu and AI engineers about agents, AI, and LlamaIndex ➡️ Attend Jerry's talk on June 5th:

Dear Karsten Wildberger from Digitalministerium, a free ChatGPT Plus subscription for every German citizen would cost about 20 billion EUR per year, assuming no discounts. To support you (and our country), I’m offering the source code for BundesGPT at no cost. Additionally, I'm

Happening now in NYC: our CEO Jerry Liu is heading our workshop on agents in finance! We got interest from hundreds of applicants but our capacity was limited, so follow us to make sure you find out about the next one! Learn more about our enterprise offerings here:

RAG is dead, long live agentic retrieval! At LlamaIndex we've been saying for a long time that naive RAG is not enough for a modern application. Following from that conviction, we've built agentic strategies directly into LlamaCloud that you can adopt with just a few lines of

Obviously naive RAG sucks, but it's pretty clear that agents still need the right retrieval tools in order to access massive amount of enterprise context. 🤖🔎 This is a fantastic blog post by Sourabh Desai showing how we've carefully crafted a universal retrieval interface

🚀 We're proud to sponsor the Gradio Agents & MCP Hackathon - the largest MCP and AI agent development event of 2025! Join 1200+ developers (and growing!) building the future of AI agents using the most powerful tooling like Model Context Protocol, LlamaIndex, and

We're so back We've got a banger AI agents workshop lined up for the AI Engineer World Fair with some exciting releases! If you're building AI agents in the enterprise, and you like the jacket that I'm wearing in the photo, come sign up on the form! I'd love to chat.

Ever think “I read it somewhere... but where?” That’s why I built e-library-agent 📚 → Organize, search & explore reads Built with: ⚙️ ingest-anything 🗄️ Qdrant 🦙 LlamaIndex 🦙 + Linkup 🚀 FastAPI 🎨 Gradio 🔗 github.com/AstraBert/e-li…

An agent to manage your virtual collection of books 📚 Built with LlamaIndex 🦙 workflows check it out! 👇

How does Sonnet 4.0 compare vs. Gemini 2.5 Pro on document understanding? 👇 I’ve found Sonnet 4.0 to be much better at table parsing. Check out the screenshot below 🖼️ - I compared both models’ visual reasoning capabilities over a screenshot of a dense Caltrain schedule packed

A huge (and probably underrated) promise of LLMs is inhaling a million PDFs and making sense of them through automated extraction. The baseline 🟡: Stuff tokens into a function-calling LLM with a Pydantic schema, get back structured JSON. You can do this with most frameworks in