LlamaIndex

LlamaCloud now lets you manage your data pipelines all in one place, no matter what LLM application you’re building (simple RAG, complex agentic workflow) New feature releases ✨: 1. Team features - add multiple users to an organization and have a central view of all your projects/indexes!  2. Metadata management - easily attach metadata through UI and API Come signup on our waitlist 👉: https://lnkd.in/gFyTJeCc Create an account: https://lnkd.in/gi8dxGnt Docs: https://lnkd.in/gyvcTMJP

Automatically creating a knowledge graph with LLMs is hard - one issue is you end up with a lot of duplicates. Here’s a seriously cool Cypher snippet by Tomaz Bratanic and others at Neo4j that performs entity deduplication for you, using a combination of text embeddings and word distance. Result is you can use LLMs to do extraction over separate chunks and consolidate at the end! Check out our full guest blog post by Tomaz Bratanic here: https://lnkd.in/gEa_6N3e

Building Agentic RAG - Llama3 edition 🦙💫 We’re excited to collaborate with some folks at AI at Meta to release an entire set of cookbooks on agentic RAG: from routing and tool use to layering on an agent reasoning loop to building a multi-document agent. This is directly inspired by our DeepLearning.AI course on Agentic RAG. Here we’re able to show that you’re also able to use purely local models (llama 3) for complex agent workflows over your data. There are a variety of integrations to help run Llama 3, from Groq to Fireworks AI This includes the following: L1: Router Engine L2: Tool Calling L3: Building an Agent Reasoning Loop L4: Building a Multi-Document Agent Github resources here: https://lnkd.in/e7_2z7ka

We’re excited to feature LlamaTrace - a collaborative effort with Arize AI to introduce advanced LLM tracing, observability, and evaluation for any LLM application workflows 🦙🔥 There are of course many great tools for LLM tracing/evals, and we have great integrations with many of them. But we’re really excited about LlamaTrace as a differentiated experience for the three following reasons: 1. The tracing is really really detailed. Don’t just log pre-hardcoded LLM prompt calls or retrieval calls. Thanks to the integration with our LlamaIndex instrumentation module, virtually your entire call stack is logged, letting you view the inputs/outputs of every span. 2. It is one-click. Set an environment variable, call one line of LlamaIndex code, and you’re ready to go. 3. It’s integrated with LlamaCloud. If you’re logged into LlamaCloud, you should get an automated redirect/authentication to LlamaTrace! Anyone can signup for an account on LlamaTrace: https://llamatrace.com/ Blog: https://lnkd.in/gPnqWiyU Shoutout to the Arize AI team for the partnership in this effort. Looking forward to see what you can build! An example cookbook: https://lnkd.in/g7eysknD

Check out our NebulaGraph Database integration with LlamaIndex 💫 LlamaIndex uniquely lets you build powerful GraphRAG capabilities with our property graph index: - Sophisticated extractors such as letting you extract according to a pre-defined schema - Customize the extraction process - Define properties on nodes and edges - Get out of the box retrievers (vector + keyword), and easily define a custom retriever. This was a huge effort from the Nebula folks, including Wey Gu, to adapt the Nebula abstractions. Check out our guide: https://lnkd.in/g9gkTdkE

Last week we launched llama-agents, a brand new multi-agent deployment framework, and the response has been enthusiastic -- the repo is at 1100 stars and counting! Mervin Praison ✅ has a great walkthrough of how to use lllama-agents on YouTube, covering: ➡️ What is llama-agents for? ➡️ Step-by-step guide to setting up a multi-agent service ➡️ How llama-agents differs from other frameworks Check out the video: https://lnkd.in/gbSRfnsZ Or head straight to the repo: https://lnkd.in/g37FkPyx

$1M+ ARR built on LlamaIndex! Meet Lyzr AI, a full-stack autonomous AI agent framework that provides companies with AI sales development representatives, AI content marketers and more. Lyzr relies on LlamaIndex for data connectors and RAG functionality, and the results have been impressive! ➡️ From $100k to $1.5M+ ARR in 60 days ➡️ High accuracy and low error rates ➡️ Happy customers and low churn! Check out our case study: https://lnkd.in/gyvvj4KH

LlamaCloud lets you as the AI engineer spend less time on data ETL/management and more time on the fun stuff around prompting and agentic orchestration. We have a full repository of cookbooks showing you how to use LlamaCloud to manage your data in a vector store while letting you build simple QA pipelines, chatbots, agentic knowledge assistants. Besides the high-level API we also have cookbooks showing you how to customize documents, add metadata, and separate indexes per user. All available in our LlamaCloud demo repo: https://lnkd.in/g4DWzySf Signup (get immediate access to LlamaParse!): https://lnkd.in/gi8dxGnt Waitlist: https://bit.ly/llamacloud

This Saturday 7/13 join us along with AGI House, Together AI, SambaNova Systems, Numbers Station AI and Codeium for a hackathon at AGI House! Apply today: https://lnkd.in/gwz4XG-V

🎉Exciting News: we've integrated Yi models with LlamaIndex for more efficient retrieval and indexing capabilities, helping you build smarter and faster RAG apps with ease! 📗Check out demo notebook:  https://lnkd.in/gzyqF4fd 🛠️Install Yi from LlamaHub: https://lnkd.in/gNbPU3vz