LlamaIndex Newsletter 2024–02–06

Hello, LlamaIndex Explorers 🦙,

Step into a week full of exciting updates at LlamaIndex! Our community’s vibrant contributions and extensive educational resources are here to amplify your LlamaIndex exploration.

Before diving into the updates, we have an exciting announcement: We’ve launched a $2,000 bounty program with Replit. This initiative invites open-source contributors to create projects and templates focused on advanced RAG with LlamaIndex, from building RAG across thousands of documents to implementing cutting-edge RAG research and crafting advanced templates.

We’re inspired by your creativity! If you have a project, article, or video you’re excited about, we’re eager to see it. Send your amazing work to news@llamaindex.ai. If you haven’t subscribed to our newsletter yet, don’t miss out. Visit our website and subscribe today to get all the newest updates from LlamaIndex straight to your inbox.

🤩 The highlights:

1. Ollama Multimodal Integration Launch: Introduced day-1 integration with Ollama Multi-Modal for developing local multimodal applications, including image extraction, multimodal RAG, and captioning. Notebook, Tweet
2. create-llama Enhanced RAG: Updated create-llama for improved website content crawling and the creation of comprehensive RAG applications. Tweet.
3. Nomic Embedding: Guide to Building a Fully Open Source Retriever with Nomic Embed and LlamaIndex.

✨ Feature Releases and Enhancements:

• We introduced day-1 integration with the Ollama Multi-Modal release enabling the creation of local multimodal applications on MacBook, including structured image extraction, multimodal RAG, and image captioning. Notebook, Tweet
• We have updated create-llama on crawling a website’s content, and create a full-stack RAG application based on the data. Tweet.

🗺️ Guides:

• Guide to Building a Fully Open Source Retriever with Nomic Embed and LlamaIndex.

🎥 Demo:

• LlamaBot: Rohan developed an open-source Discord bot that listens to, remembers, and answers questions across servers, was inspired by a similar bot for Slack and developed using LlamaIndex, Gemini Pro, and Qdrant Engine. GitHub Repository, Tweet.

✍️ Tutorials:

• Wenqi Glantz tutorial on Jump-start Your RAG Pipelines with Advanced Retrieval LlamaPacks and Benchmark with Lighthouz AI.
• Ravi Theja tutorial on Enhancing Retrieval Performance with Alpha Tuning in Hybrid Search in RAG.
• Wenqi Glantz tutorial on 12 RAG Pain Points and Proposed Solutions.
• Cobus Reyling tutorial on Agentic RAG With LlamaIndex.
• ChristopherGS tutorial on Retrieval Augmented Generation (RAG) with Llama Index and Open-Source Models.
• Andrei workshop tutorial on Evaluation of Multimodal RAG Systems using the LlamaIndex.
• Tutorial on Building RAG application with Pinecone and LlamaIndex.
• Sudalai Rajkumar tutorial on RAG — Encoder and Reranker evaluation.
• Harshad Suryawanshi tutorial on RAGArch: Building a No-Code RAG Pipeline Configuration & One-Click RAG Code Generation Tool Powered by LlamaIndex.
• Otmane Boughaba’s tutorial on Building a Local RAG API with LlamaIndex, Qdrant, Ollama, and FastAPI.
• Iulia Brezeanu tutorial on How to Find the Best Multilingual Embedding Model for Your RAG.

🎥 Events

• Jerry Liu keynote on Beyond Naive Rag: Adding Agentic Layers.

🏢 Calling all enterprises:

Are you building with LlamaIndex? We are working hard to make LlamaIndex, even more, Enterprise-ready and have sneak peeks at our upcoming products available for partners. Interested? Get in touch.