large_Forrester-Wave-Leader.jpeg

medium_Forrester-Wave-Leader.jpeg

small_Forrester-Wave-Leader.jpeg

thumbnail_Forrester-Wave-Leader.jpeg

Forrester-Wave-Leader.jpeg

Discover why Forrester named Zilliz a Leader in Vector Databases for AI. Accelerate your AI initiatives with Zilliz's innovative vector processing solutions.

The Forrester Wave™: Vector Database Providers, Q3 2024

large_ebook- semantic search transformation in retail.png

medium_ebook- semantic search transformation in retail.png

small_ebook- semantic search transformation in retail.png

thumbnail_ebook- semantic search transformation in retail.png

ebook- semantic search transformation in retail.png

A Comprehensive Guide to Implementing Vector Search for Better Discovery, Higher Conversions, and Revenue Growth

Supercharge Your Retail Search with AI-Powered Semantic Search | Free Download

Supercharge Your Retail Search with AI-Powered Semantic Search

thumbnail_Thumbnail-Definitive-Guide-to-Choosing-a-Vector-Database.png

Thumbnail-Definitive-Guide-to-Choosing-a-Vector-Database.png

Confused by the growing number of vector database solutions? Download this free guide to compare features, understand use cases, and find the best database for managing unstructured data at scale.

The Definitive Guide to Choosing a Vector Database | Free Download

The Definitive Guide to Choosing a Vector Database

medium_Zilliz Cloud BYOC.png

small_Zilliz Cloud BYOC.png

thumbnail_Zilliz Cloud BYOC.png

Zilliz Cloud BYOC.png

Discover how Zilliz Cloud BYOC enables enterprises to deploy a fully managed vector database within their own cloud, ensuring complete data control, security, and compliance. Download the guide to explore AI-powered search for regulated industries.

Zilliz Cloud BYOC: Secure, Scalable Vector Search for Enterprises

Zilliz Cloud BYOC: Enterprise Vector Database for Regulated Industries

large_Legal.png

medium_Legal.png

small_Legal.png

thumbnail_Legal.png

Legal.png

Discover how vector databases, like Zilliz Cloud, are transforming the way legal teams manage and search vast datasets, from contracts to multimedia content.

Ebook: Vector Search in Legal Technology | Free Download

A Comprehensive Guide to Transforming Legal Research, Document Management, and Contract Analysis 

large_Video Surveillance.png

medium_Video Surveillance.png

small_Video Surveillance.png

thumbnail_Video Surveillance.png

Video Surveillance.png

Explore how vector search can enhance your video surveillance systems, improve security, and drive operational efficiency.

Transform Your Video Surveillance with Vector Search | Download Paper

Transform Your Video Surveillance with Vector Search

large_why-matter-paper-cover.png

medium_why-matter-paper-cover.png

small_why-matter-paper-cover.png

thumbnail_why-matter-paper-cover.png

why-matter-paper-cover.png

A vector database is optimized for vector embeddings. Learn what vector databases are, how they work, why they’re useful & more.

Why Vector Databases Matter for Unstructured Data

thumbnail_Milvus Performance Report-2024-07-29.png

Milvus Performance Report-2024-07-29.png

Read how Milvus 2.3 continues to make significant performance gains for vector collection workloads, and support billion scale collection. 

Download the benchmark report to learn about our evaluation of Milvus performance in 2024. See how Milvus 2.2.3 is now faster than Milvus 2.0.

Milvus Performance Report | Zilliz

Milvus Performance Report

thumbnail_Frame 4184.png

Frame 4184.png

This paper introduces FARGO, a novel framework that revolutionizes how we approach the Maximum Inner Product Search (MIPS) problem

Understanding Fast Maximum Inner Product Search 

FARGO: Fast Maximum Inner Product Search via Global Multi-Probing

small_Frame 4183.png

thumbnail_Frame 4183.png

Frame 4183.png

This paper introduces Starling, a framework that revolutionizes vector database segment handling through a novel dual-component architecture

Starling: I/O-Efficient Disk-Resident Graph Index Framework

Starling: An I/O-Efficient Disk-Resident Graph Index Framework for High-Dimensional Vector Similarity Search on Data Segment

small_LP_Manu_ paper.png

thumbnail_LP_Manu_ paper.png

LP_Manu_ paper.png

Zilliz built a cloud-native vector database that supports the scalability requirements of managing tens of billions of vectors with high elasticity performance.

How Zilliz built a Cloud Native Vector SaaS

Manu: A Cloud Native Vector Data Management System

small_LP_Milvus_ paper.png

thumbnail_LP_Milvus_ paper.png

LP_Milvus_ paper.png

Learn how Zillz built Milvus, an open source data management system, to efficiently manage large-scale vector data.

Purpose-built for high for large scale vectors 

Milvus: A Purpose-Built Vector Data Management System

Inside the AI Agent Revolution with Stefan Webb & Stephen Batifol

Prompt, Score, Repeat: Principled RAG and Agent Design

Structured Output with Outlines

Learn to build a local, open-source browser agent from scratch—gain full control, transparency, and hands-on AI agent development skills.



meetup.svg

Training

Stefan Webb

Build a Local Open-Source Browser Agent from Scratch

Discover how to integrate Vision Language Models with Browser Use and Milvus to create an agentic system capable of real-time visual and textual analysis.

Stephen Batifol is a Developer Advocate at Zilliz.

Stephen Batifol

Agentic AI in Action: Real-Time Vision, Memory & Autonomy with Browser Use & Milvus

We will examine the concepts underpinning modern agents using our basic clone, Deep Searcher, as an example.


What Makes "Deep Research"? A Dive into AI Agents

We'll explore the architecture that makes it possible to run a Multimodal RAG System and demonstrate how to build one using Milvus, LlamaIndex, and vLLM for deploying open-source LLMs on your infrastructure. 


Deploying a Multimodal RAG System Using Open Source Milvus, LlamaIndex, and vLLM

In this hands-on workshop, you'll learn how to implement powerful hybrid search solutions with just raw text input. 


Hands-On Workshop: Build Hybrid Search Apps with Milvus 2.5

In this talk, you will learn how to build an Agentic RAG System using Llama Agents and Milvus. 


Building an Agentic RAG locally with Milvus, Ollama and Llama Agents

Hands-on demo: Build GenAI apps with Zilliz Cloud. Learn vector search, create a chatbot, and explore advanced techniques.

Frank Liu

Hands-On Demo: Building and Scaling Vector Search Apps with Zilliz Cloud

This webinar will demo evaluating a RAG pipeline using Milvus and RAG metrics like context F1-score and answer correctness.

Christy Bergman is a passionate Developer Advocate at Zilliz. 

Christy Bergman

RAG Evaluation with Ragas

In this talk, Stephen will show you how you can build an Agentic RAG System using Langchain and Milvus. 


Building an Agentic RAG locally with Milvus, Ollama and LangGraph

Join us for a webinar with Haystack about building full-stack open source agents with Haystack and Milvus.

Tilde (they/them) is a San Francisco-based artist and engineer and the Senior Developer Advocate at deepset. 

Tilde Thurium

Answer 'What's for Dinner?' with Vector Search and Natural Language using Haystack and Milvus

Join us for a technical training webinar where we will showcase how you can build a RAG using Milvus.

A Beginners Guide to Building a RAG App Using Open Source Milvus

In this hands-on tutorial, we’ll introduce LLMs and two main problems they face when it comes to production. First, high cost. Second, lack of domain knowledge. We then introduce vector databases as a solution to this problem. We cover how a vector database can facilitate data injection and caching through the use of vector embeddings.

Then we’ll use this knowledge to build an LLM application using LlamaIndex and Milvus, the world’s most popular vector database.

What you’ll need:
- Python 3.9 or above
- A basic understanding of vectors and databases

What you’ll learn:
- What is a vector database
- Why do LLMs face data issues?
- How to deal with data issues in an LLM

Yujian Tang, Developer Advocate at Zilliz. 

Yujian Tang

Tutorial: Working with LLMs at Scale

In this hands-on tutorial, we’ll introduce embeddings and vector search from both an ML- and application-level perspective. We’ll start with a high-level overview of embeddings and discuss best practices around embedding generation and usage. Then we’ll use this knowledge to build a semantic text search application. Finally, we’ll see how we can put our application into production using Milvus, the world’s most popular open-source vector database.

What you’ll need:
- Python 3.9 or above
- A basic understanding of vectors and databases

What you’ll learn:
- What is vector database
- What is semantic similarity
- How to use a vector database to find similar texts

Tutorial: Building a Semantic Text Search Application

Discover how Milvus 2.6 slashes AI infrastructure costs while boosting performance

Webinar

James Luan

Introducing Milvus 2.6: Scalable AI at Lower Costs with James Luan, VP of Engineering at Zilliz

Join our monthly demo for a technical overview of Zilliz Cloud, a highly scalable and performant vector database service for AI applications.

Rohit Nijhawan

Monthly Product Demo: Discover the Power of Zilliz Cloud

Discover how to build powerful, language-agnostic vector database applications using ONNX with Milvus.

No Python? No Problem. Vector Database Applications with Milvus + ONNX Across Languages

Jay Byoun

Learn how to integrate Feast with Milvus to support vector-based retrieval in RAG systems 


Francisco Javier Arceo

Smarter RAG Pipelines: Scaling Search with Milvus and Feast

Extract docs with Crawl4AI, then use Milvus' full text & vector search to achieve precise document retrieval.

Erbli Kuka

Milvus Hybrid Search: Combining Keyword Precision with Semantic Power for Next-Gen Data Retrieval

Ameek Singh

Build a simple AI agent with advanced multimodal RAG capabilities using Friendli Serverless Endpoints and Milvus DB.

Soomin Chun

Accelerate AI Agents with Multimodal RAG powered by Friendli Endpoints and Milvus

We'll explore how new multimodal foundation models are trained to understand tabular data and demonstrate practical ways to unlock hidden value in your organization's data assets.


A Table is Worth 1000 Words

This presentation delves into the cutting-edge landscape of foundation models for time-series analysis. 

Foundation Models for Time-Series

Overcome the ambiguity of current embedding model evaluation approaches through TDA clustering on your dataset!

Gabriel Alon

Gunnar Carlsson

How to Optimize Your Embedding Model Selection and Development through TDA Clustering 

Dive into the use of Milvus as a high-performance vector database tailored for handling large-scale document collections, focusing on European Commission and Parliament acts.

Alessandro Saccoia

Vector Databases for Enhanced Classification

This talk will share insights into building image-text search and Composite Image Retrieval (CIR) using multimodal embeddings and the Milvus open source vector database

Multimodal Retrieval-Augmented Generation (RAG) with Vector Database

​Sneak Peak of Milvus 2.5 - Quick look at our BM25 implementation and sparse vector optimizations


Dense Embeddings != Complete Search - A Sneak Peek of Milvus 2.5

Learn how to manage and control access to data in vector databases, especially when dealing with sensitive information in enterprise settings


Rob Quiros

Beyond RAG Partitions: Per-User, Per-Chunk Access Policy

Learn advanced techniques to optimize your RAG system for production, including query transformation, Colbert rerankers etc.

Aravind Parameswaran

Advanced RAG Optimization To Make it Production-ready

Master practical approaches to evaluate and optimize RAG systems, equipped with the knowledge to implement these tools effectively in your own applications.


Evaluating Retrieval-Augmented Generation

Learn why you should use a RAG pipeline for LLM apps and follow a demo by Cloudera. 

Christopher Burns

Chris Joynt

RAG Pipelines with Real-Time Data

Join our upcoming webinar with InfluxDB to learn the powerful combination of time series data and vector similarity search to revolutionize urban traffic management.

Anais Dotis-Georgiou

Time Series to Vectors: Leveraging InfluxDB and Milvus for Similarity Search

Learn how data engineering can resolve common challenges associated with deploying and scaling effective AI usage.

Tim Spann is the Principal Developer Advocate at Zilliz. 

Tim Spann

Data Engineering Best Practices for AI

Live demo of Datavolo, powered by Apache NiFi, which highlights how data engineers can implement production-grade multimodal pipelines for AI.


Sam Lachterman

Multimodal Pipelines for AI Apps: Journey To Day 2

This webinar introduces Zilliz Cloud's latest features designed to address challenges head-on, enabling you to build and maintain robust, efficient AI infrastructure.


Jiang Chen

Building Resilient AI Infrastructure: Deep Dive Zilliz Cloud's New Production-Ready Features 

This session will dive into the architecture decisions that enable the Milvus vector database to seamlessly scale horizontally, provide users with tunable consistency, orchestrate in-memory and on-disk indexing, and scalable search strategies.


Powering GenAI with Scalable Vector Solutions

The newly introduced Fivetran’s Milvus Connector further extends the data landscape to make every data source semantic-searchable

Abhijeeth Padarthi

Build AI-powered Search for Every Data Source with Fivetran and Milvus

Afraid of losing control over your data with AI? Meet PrivateGPT, the framework for GenAI applications with privacy at core

Daniel Gallego Vico

AI breaks Privacy: How PrivateGPT Fixes It

In this webinar, we will look at how Unstract, an open-source platform purpose-built for structured document data extraction, solves challenges with scaling structured document data.

Shuveb Hussain

Challenges in Structured Document Data Extraction at Scale with LLMs

We'll vectorize a dataset of text and images into the same embedding space, store them in Milvus, retrieve all relevant data given an LLM query, and input multimodal data as context into GPT-4o.


Multimodal RAG with Milvus and GPT-4o

Tim will do a presentation on why you should add a Cloud Native Vector Database to your Data and AI platform.

Unstructured Data Processing from Cloud to Edge

The presentation will delve into the ASIMOV project, a novel initiative that leverages Retrieval-Augmented Generation (RAG) to provide precise,  domain-specific assistance to telecommunications engineers and technicians. The session will focus on the unique capabilities of Milvus DB, the chosen vector database for the project, and its advantages over other vector databases.


Nandula Asel Karunasingha serves as a Senior Data Scientist in Network Analytics and Automation. 

Nandula Asel Karunasingha

Aditha Iddamalgoda is the Senior Executive in Network Analytics and Automation at Dialog. 

Aditha Iddamalgoda

Dumindu Ranasinghearachchi  is the Lead Engineer in Network Analytics and Automation at Dialog. 

Resources