LlamaIndex

We’re introducing a brand-new tutorial 💫 on how to build an agentic workflow that can ensure contract compliance 📝🧑⚖️ - given a vendor contract, pull apart the relevant clauses and make sure that each clause is consistent with the relevant guidelines (e.g. GDPR), and then produce a final report at the end. It’s a great example of how to interleave 1️⃣ parsing/extraction and 2️⃣ retrieval and 3️⃣ report generation to solve e2e tasks. Core components: LlamaIndex workflows, LlamaParse, LlamaCloud Notebook: https://lnkd.in/gKbm6qwY

Learn "everything you need to know about LlamaIndex" from Tyler Reed! This tutorial is super detailed, and goes into how to: ➡️ Build a basic RAG application in just 5 lines of code using query and chat engines ➡️ Master the complete RAG pipeline: loading data, indexing, storing (using Chroma), and querying ➡️ Add observability to monitor costs and debug using LlamaTrace ➡️ Create AI agents with custom tools ➡️ Use LlamaParse to handle complex PDFs with tables and charts ➡️ Learn through 7 practical projects, from simple RAG to advanced features This is an amazing intro to everything LlamaIndex, so check it out: https://lnkd.in/gDMPKN2j

Parse only exactly what you need with LlamaParse parsing instructions A powerful feature of LlamaParse is parsing instructions. These allow you to give natural-language instructions to the parser, allowing it to transform a naïve parsing of every word in the document to a context-aware version that reflects only the information you care about. It can handle unusual reading orders, complex tables and images, and more. In this video, Ravi Theja Desetty demonstrates how the feature performs in real-world use cases: https://lnkd.in/dXGJ9AUV

Build a multimodal RAG pipeline using both images and text! In this video from Fahd Mirza, he dives into LlamaCloud's multi-modal capabilities: ➡️ Setup is simple: upload documents, toggle multimodal, pick processing mode ➡️ Works via Python or JavaScript APIs ➡️ Handles mixed content (tables, images, text) in a single pipeline Check out the video here: https://lnkd.in/gC3SDmCU Or learn more about LlamaCloud: https://lnkd.in/gaVTXJWp

Google launched its latest Gemini 2.0 models and we had day-0 support (but forgot to post about it! 😂) You can get it today: pip install llama-index-llms-gemini or pip install llama-index-llms-vertex Simon Willison says the vibes are good: https://lnkd.in/gVH5wTPe Learn more here: https://lnkd.in/ghJZR66c

🪄 Magical week for Serverless GPUs: yesterday, we introduced scale-to-zero and today, we reduce prices for our L4, L40S, and A100s, making high-performance GPUs more affordable and efficient! 🚀 Combine scale-to-zero, autoscaling, and our new lower prices for huge improvements in efficiency: more compute for less. 💥 Here’s the price update: • L4: $1.00 → $0.70/hour • L40S: $2 → $1.55/hour • A100: $2.70 → $2/hour These dropped prices and the ability to scale-to-zero means you can use your AI budget for larger models, more predictions, or simply better performance! 🙌 We also updated the pricing page on our website to display prices by the hour for easier reading. We still bill per second so you only pay for what you use, with a transparent cost structure. So, no surprises! ⏱️ Whether you’re running inference, training models, or fine-tuning, Serverless GPUs let you scale AI projects w/o managing infrastructure 🧑💻 Want to run inference with a 7B model or a 400B model? We offer Instances with multiple A100 options, which also benefit from the price drop 🚀 💬 Need more GPUs or have questions? GPUs are available in self-service, but if you’d like to chat about production needs, you can book a call with us https://lnkd.in/g2n8s2DG We can't wait to see what you'll build with our Serverless GPUs! Deploy your workloads on A100, L4, L40S, or any Serverless GPU that suits your needs over on the Koyeb platform 🚀 Who wants faster inference and fine-tuning? Campbell, Claire, Eliot, Flore, Guillaume, Prakul, Simon, Stephen, Sumay, Timo, Thibaut, Thibaut, Alon, Naor, Dr. Megan, John

Build RAG agents that respect your SharePoint permissions structure! We have a lot of customers who use the @Azure stack to connect to their enterprise data sources like SharePoint, and a frequent feature request was the ability to have the application respect permissions from SharePoint when answering questions about documents. This is now built-in to LlamaCloud! Learn more about this feature here: https://lnkd.in/gkinxkqm

Learn how Calsoft created CalPitch, a tool that helps their business development department by researching prospects and writing outreach emails with human-in-the-loop for review. This is a great example of how AI can be used to augment and accelerate existing teams. The system: 🚀 Automates prospect research and email crafting 🎯 Generates highly personalized pitches at scale 📊 Improves conversation rates and team productivity Read the full story: https://lnkd.in/gg8KP9R7

Extract and interpret SVG charts from PDFs and other complex document formats with LlamaParse! When building a RAG application the most interesting data is often locked away in charts and diagrams. LlamaParse has the ability to extract and interpret these charts, converting them into Markdown and Mermaid representations. Check out the demo video from Ravi Theja Desetty here: https://lnkd.in/gajwCZVZ Learn more about LlamaParse: https://lnkd.in/gngXzAWh

We’ve become increasingly interested in document agent workflows that can automate practical workflows beyond one-step RAG/IDP tasks. 📑🤖 First up - an e2e invoice processing agent 🧾: given an invoice, extract out the relevant information, match it with the relevant vendor contract and apply any vendor-specific discounts, and generate a payments plan. Powered by LlamaIndex workflows, LlamaParse for parsing/extraction, and LlamaCloud indexing. https://lnkd.in/gWa2Gk9y