LlamaIndex

Accelerate mechanical maintenance with AI: Learn how a RAG-powered mechanic's assistant won 3rd place at LlamaIndex's hackathon! OilyRAGs, an AI-driven catalog for mechanics, showcases the power of Retrieval-Augmented Generation in transforming traditional industries: 🔧 6000% faster model number decoding and parts lookup 🚤 Focused on the $50+ billion marine industry 📱 Multimodal, hands-free interface for on-the-spot diagnostics Key technical features: ➡️ LlamaIndex for RAG pipeline and workflow implementation ➡️ Pinecone for vector storage ➡️ OpenAI for language model and embeddings ➡️ Arize AI Phoenix for observability Read the full explanation: https://lnkd.in/gaWBeweh

We're pleased to announce two new features of LlamaParse, hot off the presses: 1. Continuous mode (in beta): if you have tables that span multiple pages, Continuous Mode will stitch them together into one seamless table, no matter how long. 2. Excel spreadsheet output: if you want to parse a document directly into a spreadsheet, now you can! Plus the two modes work in combination! Check out the full blog post to learn more: https://lnkd.in/gTFN3sZq

Reminder: the 3-day Llama Impact Hackathon in San Francisco starts next week! 🦙 Build AI solutions using Meta's Llama 3.2 models and compete for a $15,000 cash prize pool, including a special $1000 prize for best use of LlamaIndex. The hackathon runs from November 8-10, with both in-person and online options available. Don't miss out on this opportunity to showcase your skills and potentially unlock Meta's $100,000 Llama 3.1 Impact Grant! Register now and learn more: https://lu.ma/1mkqg22a

Good telemetry is important when building a complex, production application and Open Telemetry is the industry standard. Braintrust now lets you log traces directly from LlamaIndex using Open Telemetry to their observability platform. Check out their docs here: https://lnkd.in/giSsAqDf

Learn to build an automated research paper report generator using LlamaIndex that downloads papers from arXiv, processes them with LlamaParse, and indexes them in LlamaCloud! Report generation is an increasingly important use-case so we're doubling down on making it easy. In this demo from Ravi Theja Desetty you'll learn how to: ➡️ Generate queries based on a report outline and classify them for LLM vs index-based answers ➡️ Handle paper downloading, metadata extraction, and document parsing automatically ➡️ Use Pydantic models to extract key metadata like author names, companies, and AI topics ➡️ Create structured reports with sections & subsections filled from both LLM and indexed content It supports customizable report outlines and templates for different use cases. Check it out here: https://lnkd.in/gCXKzeuH

Super excited to announce the 1st edition of LLM x Hackathon in Paris in partnership with CodeX, The Stanford Center for Legal Informatics, Koyeb, LlamaIndex, Neon, Mistral AI, and the The GenAI Collective! ⬇️ After 4 successful editions with thousands of participants worldwide, we're bringing this event to STATION F, Paris. 🇫🇷 LLMs have the potential to transform legal research, contract analysis, data privacy, regulation and much more. Join us for a day to build solutions that consider the safe and trustworthy integration of LLMs for legal work! ⚖️ This an amazing event for the legal & tech community looking at how LLMs can be applied to the field: Alan, Fabien, Guillaume, Gregoire, Laura, Marek, Quentin Want to get involved? reach out to me, Alisdair Broshar or Dr. Megan Ma! Thank you to our core technological & legal partners: Raouf Chebri, Sophia Yang, Ph.D., Pierce Kelaita, Marie Torelli, Chen GU, Thu Ha N., Campbell Hutcheson, Pierre-Loic Doulcet, Atli Cervantes Register on luma: https://lu.ma/63trnmfl #AI #LLMs

An agent is only as good as its tools, and Toolhouse is here with dozens of high-quality tools to help you! Participants at our recent hackathon found Toolhouse a huge time-saver, providing ready-made tools that plug straight into LlamaIndex agents, and now they've launched a Python SDK to make that even quicker. Check out the quickstart to create a LlamaIndex agent with Toolhouse tools in 3 lines of code: https://lnkd.in/davBHZUR Or head over to the Python SDK: https://lnkd.in/dSHcaWtf

Create a LlamaIndex app in minutes with create-llama 🚀 🔧 Set up a full-stack Next.js or Python FastAPI backend 📊 Choose from pre-configured use cases like Agentic RAG or Data Analysis 📁 Easily ingest and index various file types, including PDFs, CSVs, and more Run 'npx create-llama@latest' to begin, or watch our demo video for a walkthrough. Customize your app with different LLMs, vector stores, and tools in pro mode for even more flexibility. Get started now: https://lnkd.in/gPTYt6um

Just launched at GitHub Universe: Microsoft Azure AI App Templates, and LlamaIndex is one of the first apps to be featured! Check out the announcement: https://lnkd.in/g8yQiFzp Or these in-depth instructions on how to deploy one of the app templates: https://lnkd.in/gDfQbECq Or head straight to the template gallery and start building! https://lnkd.in/gq57QKvw

Recently Cohere released multi-modal embeddings, allowing you to combine images and text in the same vector space. See how to use them in LlamaIndex in this notebook, along with Qdrant to store the embeddings! https://lnkd.in/gcmYu5CW Cohere's Embed 3 has industry-leading performance, and you can learn more about it on their blog: https://lnkd.in/em8HecWi