LlamaIndex Newsletter 2024-10-29

Greetings, Llama Lovers! 🦙

Welcome to this week’s edition of the LlamaIndex newsletter! We’re bringing you updates on using LlamaCloud for efficient RFP response generation, along with a guide to building a multi-agent concierge system for customer service. This edition also features our new video series on advanced knowledge assistants, covering topics from RAG basics to Auto retrieval and corrective RAG techniques with LlamaCloud. Plus, check out the Gift Genie project from our recent hackathon, a creative system that generates and debates gift ideas.

If you haven't explored LlamaCloud yet, make sure to sign up and get in touch with us to discuss your specific enterprise use case.

🤩 The highlights:

• Knowledge Management for RFP Response Generation: Explore how LlamaCloud indexes unstructured data to support complex agent workflows for RFP report generation. Cookbook, Tweet.
• Multi-Agent Concierge System Guide: Step-by-step guide to building a customer service system using LlamaIndex, from a basic agent to a multi-agent orchestrated setup with human-in-the-loop features. Code.
• New Knowledge Assistant Video Series: Check out our video series on building advanced knowledge assistants, covering topics from RAG to auto-retrieval and corrective RAG with LlamaCloud.
• Gift Genie Project: Tanmesh and Lily Su hackathon project, Gift Genie, creates an agentic system that generates gift ideas and evaluates the best options through self-debate. Blogpost, Code.

🗺️ LlamaCloud And LlamaParse:

• Knowledge Management for RFP Response Generation: Demonstrates how to use LlamaCloud for indexing unstructured data, enabling complex agentic workflows that enhance RFP report generation. Cookbook, Tweet.
• Guide to Building a Multi-Agent Concierge System on developing a robust customer service application using LlamaIndex, starting with a basic agent and incorporating tool use, human-in-the-loop for critical actions, and expanding to a multi-agent system coordinated by an orchestrator.
• New video series on building advanced knowledge assistants:
  • From RAG to Knowledge Assistants.
  • Advanced RAG: Auto-Retrieval (with LlamaCloud).
  • Advanced RAG: Corrective RAG (with LlamaCloud)

✨ Framework:

• We have LlamaIndex.TS as part of Vercel's AI SDK, simplifying the creation of LLM-powered web apps with an adapter that efficiently streams responses from LlamaIndex to your front-end. Tweet.

💡 Use-case:

• Gift Genie: A Project by Tanmesh and Lily Su at LlamaIndex hackathon to build an agentic system that comes up with a list of gift ideas, then debates with itself over which is best. Blogpost, Code.
• A case study on building an AI sales assistant for NVIDIA using LlamaIndex and NVIDIA Inference Microservices, demonstrating how AI can improve sales operations by providing representatives with real-time, accurate information. Blogpost.

✍️ Community:

• Yuki Watanabe’s tutorial on Building Advanced RAG with MLflow and LlamaIndex Workflow.
• Ryan Nguyen’s tutorial on Building SQL Agent for Enterprise-Scale with 500+ Tables.
• DBOS’s tutorial on How To Build a Serverless RAG Application in 9 Lines of Code.

🔊 Webinars:

• Jerry Liu spoke about LlamaIndex's vision for intelligent AI assistants at the 2024 Ray Summit.
• Jerry Liu and Jason Lopatecki AI Agents Masterclass with Arize AI.

💻 Hackathon:

• Join us for the 3-day Llama Impact Hackathon in San Francisco from November 8-10, featuring Meta's Llama 3.2 models, a $15,000 prize pool, and a chance to unlock a $100,000 grant; participate in-person or online.

👥 Recruitment:

• We are actively seeking talented individuals for our team at LlamaIndex. If you believe you are a good fit for any of the following roles, please feel free to reach out to us.
  1. Founding AI Engineer
  2. Founding AI Data Engineer
  3. Founding AI Engineer, Backend
  4. Founding Full-Stack Product Engineer