In this issue:
NEW Advanced Search Capabilities with Milvus 2.4
The latest with RAG
Zilliz Cloud Available on Azure Marketplace
Community Spotlights: build a WatsonX virtual healthcare assistant or a video game recommender system with Milvus
Upcoming events – Introducing a new Berlin Unstructured Data meetup!
🔎 Milvus 2.4 Unlocks Advanced Search Capabilities
📣JUST IN! Milvus 2.4 introduces features designed to revolutionize vector search capabilities 📣
Here are some new updates you can try on Milvus, our free open-source vector database:
GPU Indexing capability leveraging NVIDIA’s cutting-edge CUDA-Accellerated Graph Index for Vector Retrieval (CAGRA).
Enhance retrieval quality with multivector support: end-to-end infrastructure solution for multivector search and reranker functionalities.
Grouby search – Enhance resource efficiency and developer productivity by ensuring users receive relevant and meaningful search results
Sparse embeddings – Enhance the accuracy of text search using hybrid search methodologies
Regular expression & Inverted Index – Experience up to a 30x increase in performance for filtering scalar data types
Read more about the Milvus 2.4 updates here.
Get started with Milvus on GitHub.
📣 RAG! RAG! RAG!
Ok now that I have your attention, here’s the latest on Zilliz’s most popular use case: Retrieval Augmented Generation (RAG)
🦙 Build an AI Agent for RAG with Milvus and LlamaIndex
This tutorial combines the two most popular types of LLM applications: retrieval augmented generation (RAG) and AI agents. Walk through building an AI Agent for RAG using Milvus, LlamaIndex, and GPT 3.5 with sample data from Lyft and Uber.
💀 Will RAG Be Killed by Long-Context LLMs?
In this blog, we explore the intricacies of Gemini’s long-context capabilities, limitations, and impact on the evolution of RAG techniques. Most importantly, we’ll discuss whether RAG is on the verge of demise and how to optimize RAG systems.
These embedding models are tailored to AI RAG applications. In this blog, We show the MTEB leaderboard of embedding models and explain how to use it. Then, we go through the six different embedding models automatically included in Zilliz Pipelines.
☁️ Cloud Update: Zilliz Cloud is Now Available on Azure Marketplace
We are excited to announce that Zilliz Cloud is now available on Azure Marketplace after its successful integration into AWS and GCP marketplaces. You can now choose your preferred cloud system for vector database management and integrate smoothly into your existing Azure workflows!
Read more about this update here.
Get started now with a free Zilliz Cloud account.
👥 Community Spotlights
Ruslan Magana Vsevolodovna created a virtual assistant doctor for an enhanced patient experience by using WatsonX Assistant with Milvus as a vector database. See the demo and a walkthrough in his blog here!
Baraa Zaid shares how to build a video game recommender system with Milvus, FastAPI, and Docker in this article!
Upcoming Events
March 27: Unstructured Data Meetup – South Bay Edition (in-person)
Join us for our NEW Unstructured Data Meetup in Sunnyvale, CA to talk about GenAI and enjoy food and beverages! Learn about sparse vectors in Milvus with Yi Wang, how to chat with your data, privately and locally with Jay Rodge, and Voyage AI embedding for your RAG apps with Tengyu Ma.
Register here: https://lu.ma/odhcf97e
March 28: Exploring Sparse and Dense Embeddings: A Guide for Effective Information Retrieval with Milvus (virtual)
Learn the differences between sparse and dense vectors and examples of how to use them in Milvus from Zilliz’s Head of AI/ML, @ Frank Liu. He will go over the ins and outs of sparse and dense vectors and when you’d want to use one over the other.
Register here.
April 4: Unlocking Advanced Search Capabilities with Milvus 2.4: Accelerated GPU Search, Multi-Vector Search, and Beyond (virtual)
Milvus 2.4 is here! Join us to learn about the innovative features in Milvus 2.4 and demonstrate them in action with Zilliz’s VP of Engineering, James Luan. Through live demos, we’ll show you how to effectively utilize the new features, ensuring you understand both the concept and the practical application.
Register here.
April 11: How MindStudio Crafted a No-Code Pathway for RAG App Builders (virtual)
@ MindStudio is a no-code platform transforming how custom AI-powered applications are built across different sectors. Learn from @ Dmitry Shapiro and @ Sean Thielen about how they made Retrieval Augmented Generation (RAG) accessible to all without any coding required.
Register here.
April 16: SF Unstructured Data Meetup (in-person)
Hear talks about Zilliz Serverless, Advanced RAG apps with LlamaIndex, and Voyage AI embeddings at our April SF meetup!
Register here: https://lu.ma/c21bia16
April 16: Berlin Unstructured Data Meetup (in-person)
Zilliz’s first Europe Unstructured Data Meetup is debuting in ✨Berlin ✨on April 16! There will be talks about vector databases from Stephen Batifol, state-of-the-art general text embeddings by Bo Wang, and automatic detection of hallucinations within LLMs by Morena Bastiaansen
Register here: https://lu.ma/2hd0p2ey
