Zilliz's Milvus Skill (pymilvus, 7 files) and Zilliz Cloud Skill (zilliz-cli, 14 modules) bring vector-DB dev and ops into one Claude Code session.

Zilliz Skills Breakdown: How AI Agents Master Vector Databases

Notion solved vector search scaling in two years. The next bottleneck — offline context engineering, unified data, and the real-time/offline gap — is harder.

Notion's Vector Search Is Excellent. Their Next Problem Is Harder.

Manage your vector database from your terminal or AI coding agent. Zilliz CLI and Agent Skills work with Claude Code, Cursor, Codex, and Copilot.

Introducing Zilliz CLI and Agent Skills for Zilliz Cloud

Zilliz Cloud Functions auto-generate embeddings via OpenAI, Voyage AI, Cohere, or Zilliz Hosted Models. Built-in reranking — just insert text and search.

Introducing Functions and Model Inference on Zilliz Cloud: Automatic Embedding and Reranking with Hosted Models

We benchmarked 10 embedding models on cross-modal, cross-lingual, long-document, and dimension compression tasks. See which one fits your RAG pipeline.

How to Choose the Best Embedding Model for RAG in 2026: 10 Models Benchmarked

Turbopuffer vs. Zilliz Cloud: A Performance and Cost Benchmark for Multi-Tenant Vector Search

Turbopuffer vs. Zilliz Cloud: A Compliance and Enterprise Readiness Evaluation for Multi-Tenant Vector Search

If unstructured data is the context of AI, then the ceiling of AI applications will be set not just by models, but by how mature the infrastructure for unstructured data becomes.

How Zilliz Ended Up at the Center of NVIDIA’s Unstructured Data Story at GTC 2026

We're announcing the general availability of Customer-Managed Encryption Keys (CMEK) on Zilliz Cloud.

Introducing Customer-Managed Encryption Keys (CMEK) on Zilliz Cloud

The Zilliz Cloud Plugin brings the full power of Zilliz Cloud directly into your Claude Code terminal as natural-language conversations.

Zilliz Cloud Just Landed in Claude Code

Zilliz Cloud Had the Answer Before the Crisis. Zilliz Cloud is the world's first vector database with native cross-region disaster recovery.

The AWS Outage Was a Wake-Up Call for Vector Database Cross-Region Disaster Recovery

Run Claude Code from your phone with Remote Control, Happy Coder, or SSH + Tailscale. Comparison table, setup steps, and tools for typing, memory, and parallel tasks.

3 Easiest Ways to Use Claude Code on Your Mobile Phone

A real-world benchmark comparing Turbopuffer and Zilliz Cloud on cost, latency, recall, and consistency for production-scale vector search workloads.

Storage Cost Isn’t the Whole Story: Why We Disagree with Turbopuffer’s Trade-offs

Write tests, not code reviews. How a test-first workflow with 6 parallel Claude Code sessions turns a 2M-line C++ codebase into a daily shipping pipeline.


My Wife Wanted Dior. I Spent $600 on Claude Code to Vibe-Code a 2M-Line Database Instead. 

Turn your Mac into an AI gateway for WhatsApp, Telegram, Discord, iMessage, and more — in under 5 minutes.

How to Install and Run OpenClaw (Previously Clawdbot/Moltbot) on Mac

Milvus 2.6 marks a shift from “vector search + glue code” to a more advanced retrieval engine, and it is now Generally Available (GA) on Zilliz Cloud (a managed Milvus service).

A Developer's Guide to Exploring Milvus 2.6 Features on Zilliz Cloud

Zilliz Cloud launches in AWS eu-west-1 (Ireland) — bringing low-latency vector search, EU data residency, and full GDPR-ready infrastructure to European AI teams. Now live across 30 regions on five cloud providers.

Zilliz Cloud Now Available in AWS Europe (Ireland)

Zilliz Cloud BYOC is now generally available on all three major clouds. Deploy fully managed vector search in your own AWS, GCP, or Azure account — your data never leaves your VPC. 


Zilliz Cloud BYOC Now Available Across AWS, GCP, and Azure

Learn how Sudachi normalization and Milvus/Zilliz hybrid search improve Japanese RAG accuracy with BM25 + vector fusion, AWS Bedrock embeddings, and practical code examples.


How to Improve Retrieval Quality for Japanese Text with Sudachi, Milvus/Zilliz, and AWS Bedrock

A practical guide to context engineering for production LLM systems, covering RAG, context processing, memory, agents, and multimodal context.

Top 10 Context Engineering Techniques You Should Know for Production RAG

An inside look at how Zilliz built vector databases for real-world use, focusing on scalability, stability, and running them reliably at scale.

How Zilliz Saw the Future of Vector Databases—and Built for Production

Milvus 2.6.x is now GA on Zilliz Cloud, delivering faster vector search, smarter hybrid queries, and lower costs for production RAG and AI applications.

Milvus 2.6.x Now Generally Available on Zilliz Cloud, Making Vector Search Faster, Smarter, and More Cost-Efficient for Production AI

Zilliz Cloud Global Cluster delivers multi-region resilience, automatic failover, and fast global AI search with built-in security and compliance.

Introducing Zilliz Cloud Global Cluster: Region-Level Resilience for Mission-Critical AI

A simple, step-by-step guide to migrating from Milvus to Zilliz Cloud. Learn both endpoint and backup methods for a smooth, scalable vector database migration.

Why and How to Migrate from Self-Hosted Milvus to Zilliz Cloud

Discover Zilliz Cloud’s Business Critical Plan—offering advanced security, compliance, and uptime for mission-critical AI and vector database workloads.

Introducing Business Critical Plan: Enterprise-Grade Security and Compliance for Mission-Critical AI Applications

Explore how Milvus scales for large datasets and complex queries with advanced features, and discover how to migrate from Weaviate to Zilliz Cloud.

Why Teams Are Migrating from Weaviate to Zilliz Cloud — and How to Do It Seamlessly

Learn how Zilliz Cloud bridges cost and performance with tiered storage and enterprise-grade features, and how to migrate data from AWS S3 Vectors to Zilliz Cloud.

Migrating from S3 Vectors to Zilliz Cloud: Unlocking the Power of Tiered Storage

Discover how DeepSeek-OCR uses visual tokens and Contexts Optical Compression to boost long-context LLM efficiency and reshape RAG performance.

DeepSeek-OCR Explained: Optical Compression for Scalable Long-Context and RAG Systems

This release offers a rebuilt tiered storage with lower costs, a new Business Critical plan for enhanced security,  and pricing updates, among other features. 

Zilliz Cloud Update: Tiered Storage, Business Critical Plan, Cross-Region Backup, and Pricing Changes

The addition of the Azure North Europe (Ireland) region further expands our global footprint to better serve our European customers. 

Zilliz Cloud Now Available in Azure North Europe: Bringing AI-Powered Vector Search Closer to European Customers

Learn practical context engineering strategies for AI agents. Explore frameworks, tools, and techniques to improve reliability, efficiency, and cost.

Context Engineering Strategies for AI Agents: A Developer’s Guide

With the latest upgrade, Zilliz Cloud introduces smarter autoscaling—a fully automated, more streamlined, elastic resource management system. 


Smarter Autoscaling in Zilliz Cloud: Always Optimized for Every Workload

AWS S3 Vectors aims for 90% cost savings for vector storage. But will it kill vectordbs like Milvus? A deep dive into costs, limits, and the future of tiered storage.


Will Amazon S3 Vectors Kill Vector Databases—or Save Them?

SSO is GA on Zilliz Cloud, delivering the enterprise-grade identity management capabilities your teams need to deploy vectorDB with confidence.

Announcing the General Availability of Single Sign-On (SSO) on Zilliz Cloud

Zilliz Cloud Audit Logs are now GA, giving enterprises real-time visibility, compliance-ready trails, and stronger security across AWS, GCP, and Azure.

Zilliz Cloud Audit Logs Goes GA: Security, Compliance, and Transparency at Scale

What's new in Zilliz Cloud? Smarter autoscaling with scale-down, audit logs GA, enhanced SSO, and Milvus 2.6 in Private Preview.


Zilliz Cloud Update: Smarter Autoscaling for Cost Savings, Stronger Compliance with Audit Logs, and More 

Learn how vector-based code retrieval cuts Claude Code token consumption by 40%. Open-source solution with easy MCP integration. Try claude-context today.

Why I’m Against Claude Code’s Grep-Only Retrieval? It Just Burns Too Many Tokens

Build production-ready enterprise RAG with AWS Bedrock, Nova models, Zilliz Cloud, and LangChain. Complete tutorial with deployable code.

How to Build an Enterprise-Ready RAG Pipeline on AWS with Bedrock, Zilliz Cloud, and LangChain

Discover how context engineering unifies prompts, RAG, and tools to build smarter, production-ready AI agents powered by Milvus.

Why Context Engineering Is Becoming the Full Stack of AI Agents

We're thrilled to announce that Zilliz Cloud is now available in the AWS Sydney, Australia region (ap-southeast-2). 

Zilliz Cloud Launches in AWS Australia, Expanding Global Reach to Australia and Neighboring Markets

Autonomous driving faces a data bottleneck. Learn how AI-native vector databases like Zilliz solve scale, cost, and insight challenges across AV pipelines.



The Real Bottlenecks in Autonomous Driving — And How AI Infrastructure Can Solve Them

Explore how MinHash LSH and Milvus handle data deduplication at the trillion-scale level, solving key bottlenecks in LLM training for improved AI model performance.

Data Deduplication at Trillion Scale: How to Solve the Biggest Bottleneck of LLM Training 

Zilliz Cloud adopts Arm-based AWS Graviton3 CPUs to cut costs, speed up AI vector search, and power billion-scale RAG and semantic search workloads.

Zilliz Cloud Delivers Better Performance and Lower Costs with Arm Neoverse-based AWS Graviton

Zilliz Cloud on AWS powers secure, scalable, ultra-fast vector search for enterprise AI apps, with BYOC, sub-10ms latency, and zero-DevOps simplicity.

Zilliz Cloud Enterprise Vector Search Powers High-Performance AI on AWS

Zilliz Cloud expands to Azure Central India. This new region helps customers meet compliance, reduce latency, and optimize cloud costs when building AI applications. 

Expanding Our Global Reach: Zilliz Cloud Launches in Azure Central India

Discover VDBBench 1.0, an open-source tool for benchmarking vector databases with real-world production data, streaming ingestion, and concurrent workloads.

Announcing VDBBench 1.0: Open-Source VectorDB Benchmarking with Your Real-World Production Workloads

Developers can easily manage and query vector databases with natural language via Zilliz MCP Server in AI-native environments.

Introducing Zilliz MCP Server: Natural Language Access to Your Vector Database

Zilliz shines in G2's Summer 2025 Grid® Report as both "Highest Performer" and "Easiest to Use," solving the performance-usability dilemma.

Zilliz Named "Highest Performer" and "Easiest to Use" in G2's Summer 2025 Grid® Report for Vector Databases

Join us in celebrating Milvus, the vector database that hit 35.5K stars on GitHub. Discover our story and how we’re making AI solutions easier for developers.

Our Journey to 35K+ GitHub Stars: The Real Story of Building Milvus from Scratch 

Explore why choosing the right vector database is critical for scaling AI agents, and why traditional solutions fall short in production.

Why Not All VectorDBs Are Agent-Ready

We've enhanced the entire collection creation experience to bring advanced capabilities directly into the interface, making it faster and easier to build production-ready schemas without switching tools.

Creating Collections in Zilliz Cloud Just Got Way Easier

Zilliz Cloud BYOC on GCP offers enterprise vector search with full data sovereignty and seamless integration.

Announcing the General Availability of Zilliz Cloud BYOC on Google Cloud Platform

Explore strategies for developing AI agents that can handle rapid growth. Don't let inadequate systems undermine your success during critical breakthrough moments.

Build for the Boom: Why AI Agent Startups Should Build Scalable Infrastructure Early

Zilliz democratizes AI vector search with Milvus 2.6 and Zilliz Cloud for powerful, affordable scalability, cutting costs in infrastructure, operations, and development.

Democratizing AI: Making Vector Search Powerful and Affordable

Explore eight advanced RAG variants that can solve real problems you might be facing: slow retrieval, poor context understanding, multimodal data handling, and resource optimization.


8 Latest RAG Advancements Every Developer Should Know

Whether you like it or not, here's the truth: SQL is destined for decline in the era of AI. 

Why AI Databases Don't Need SQL

Discover how Video AI models transform industries by enabling real-time analysis of visual data. Explore their impact on sports, security, and content creation.


AI Agents Are Quietly Transforming E-Commerce — Here’s How

Explore Zilliz Cloud BYOC-I, the solution that balances AI innovation with data control, enabling secure deployments in finance, healthcare, and education sectors.

Zilliz Cloud Introduces Advanced BYOC-I Solution for Ultimate Enterprise Data Sovereignty

Compare Function Calling, MCP, and A2A protocols for AI agents. Learn which standard best fits your development needs and future-proof your applications.

The Great AI Agent Protocol Race: Function Calling vs. MCP vs. A2A

Discover how video AI transforms raw footage into meaningful embeddings, enabling efficient scene search and action recognition. Explore the technology behind the magic.

From Pixels to Embeddings: How Video AI Represents Visual Data

AI agents are software programs powered by AI that can perceive their environment, make decisions, and take actions to achieve a goal—often autonomously. 

What Exactly Are AI Agents? Why OpenAI and LangChain Are Fighting Over Their Definition?

Discover how Chain-of-Agents enhances Large Language Models by effectively managing context injection, improving response quality while addressing token limitations.


Chain of Agents (COA): Large Language Models Collaborating on Long-Context Tasks

Explore how to use the Sizing Tool to select the optimal configuration for your Milvus deployment. 

Demystifying the Milvus Sizing Tool

Optimize vector search with Zilliz Cloud’s level and recall features to tune accuracy, balance performance, and power AI applications.

Balancing Precision and Performance: How Zilliz Cloud's New Parameters Help You Optimize Vector Search

See how Milvus vector database enhances multi-camera tracking with similarity-based matching for better surveillance in retail, warehouses and transport hubs.


Milvus/Zilliz + Surveillance: How Vector Databases Transform Multi-Camera Tracking

Hands-on tutorial on how to create a streamlined, powerful RAG pipeline that balances efficiency, accuracy, and scalability using the QwQ-32B and Milvus.

How to Build RAG with Milvus, QwQ-32B and Ollama

Explore CoRAG, a novel retrieval-augmented generation method that refines queries iteratively to improve multi-hop reasoning and factual answers.


Chain-of-Retrieval Augmented Generation

NVIDIA's Cosmos platform enables safe, digital twin training of GenAI models for physical applications, overcoming data scarcity and safety challenges.

Cosmos World Foundation Model Platform for Physical AI

TableGPT2 automates tabular data insights, overcoming schema variability, while Milvus accelerates vector search for efficient, scalable decision-making.

1 Table = 1000 Words? Foundation Models for Tabular Data

Use a vector database for AI-powered similarity search; use an object-relational database for complex data modeling with both relational integrity and object-oriented features.

Vector Databases vs. Object-Relational Databases

Use a vector database for similarity search and AI-powered applications; use a document database for flexible schema and JSON-like data storage.

Vector Databases vs. Document Databases

MCP + Milvus: Streamline AI agent development with standardized data access, eliminating integration hassles while enhancing context and flexibility.


How to Use Anthropic MCP Server with Milvus

VidTok tokenizes videos to reduce redundancy while preserving spatial and temporal details for efficient processing.

VidTok: Rethinking Video Processing with Compact Tokenization

Discover how Topological Data Analysis (TDA) reveals hidden embedding model weaknesses and helps optimize vector database performance.


Optimizing Embedding Model Selection with TDA Clustering: A Strategic Guide for Vector Databases

Exploring five similarity metrics for vector search: L2 or Euclidean distance, cosine distance, inner product, and hamming distance. 

Similarity Metrics for Vector Search

Use a vector database for similarity search and semantic relationships; use a time series database for tracking value changes over time.

Vector Databases vs. Time Series Databases

Discover how vector databases enhance AI reliability in legal tech, ensuring accurate, compliant, and trustworthy AI-powered legal solutions.


Bringing AI to Legal Tech: The Role of Vector Databases in Enhancing LLM Guardrails

Discover the best RAG evaluation tools to improve AI app reliability, prevent hallucinations, and boost performance across different frameworks.


Top 10 RAG & LLM Evaluation Tools You Don't Want To Miss

Use a vector database for AI-powered similarity search; use a key-value database for high-throughput, low-latency simple data lookups.

Vector Databases vs. Key-Value Databases

KNN is a supervised machine learning technique and algorithm for classification and regression. This post is the ultimate guide to KNN. 

What is the K-Nearest Neighbors (KNN) Algorithm in Machine Learning?

Explore Milvus WebUI to monitor, manage, and optimize your vector database with real-time insights, performance tracking, and system health monitoring.

Milvus WebUI: A Visual Management Tool for Your Vector Database

Enhance legal document analysis with Zilliz Cloud’s Semantic Search and RAG. Improve accuracy, efficiency, and scalability for contracts, case law, and compliance.



Legal Document Analysis: Harnessing Zilliz Cloud's Semantic Search and RAG for Legal Insights

A vector database stores, indexes, and searches unstructured data through vector embeddings for fast information retrieval and similarity search. 

What is a Vector Database and how does it work: Implementation, Optimization & Scaling for Production Applications

Learn the right ETL tools for unstructured data to power AI. Explore key challenges, tool comparisons, and integrations with Milvus for vector search.


Selecting the Right ETL Tools for Unstructured Data to Prepare for AI

Use a vector database for AI-powered similarity search; use a graph database for complex relationship-based queries and network analysis.

Vector Databases vs. Graph Databases

In this article, we will talk about the o1 series from a developer's perspective, exploring how these models can be implemented for sophisticated use cases. 

OpenAI o1: What Developers Need to Know

Learn how to set up DeepSeek-R1 on your local machine using Ollama, AnythingLLM, and Milvus in just 10 minutes. Bypass busy servers and enhance AI responses with custom data.


DeepSeek Always Busy? Deploy It Locally with Milvus in Just 10 Minutes—No More Waiting!

In this article, we will explore how multimodal AI enhances AI systems by bridging audio, text, and vector search. 

Enhancing Multimodal AI: Bridging Audio, Text, and Vector Search

Explore the evolution of Text-to-Speech technology from mechanical devices to neural networks. Learn how TTS works, compare popular models, and implement it using Google Cloud Platform.


From Text to Speech: A Deep Dive into TTS Technologies

explore how Cloudera can be integrated with Milvus to effectively implement some of the key functionalities of RAG pipelines. 

Building RAG Pipelines for Real-Time Data with Cloudera and Milvus

Discover how audio transformers enhance sound processing. Explore their principles, selection criteria, popular models, applications, and key challenges.


Choosing the Right Audio Transformer: An In-depth Comparison

In contrast to OpenAI’s Deep Research, this example ran locally, using only open-source models and tools like Milvus and LangChain.

Introducing DeepSearcher: A Local Open Source Deep Research

we're excited to announce Zilliz Cloud's integration with Datadog, enabling comprehensive monitoring and observability for your vectorDB deployments. 

Proactive Monitoring for Vector Database: Zilliz Cloud Integrates with Datadog

Discover how AI and vector databases are revolutionizing video surveillance with real-time analysis, faster threat detection, and intelligent search capabilities for enhanced security.

AI Integration in Video Surveillance Tools: Transforming the Industry with Vector Databases

Discover audio data, its characteristics, processing techniques, and key challenges. Learn how to tackle them effectively in AI applications.


Getting Started with Audio Data: Processing Techniques and Key Challenges

Discover how DeepSeek R1's open-source AI model with superior reasoning capabilities and lower costs is disrupting the AI landscape and challenging tech giants like OpenAI.


Why Deepseek is Waking up AI Giants Like OpenAI And Why You Should Care

In this blog, we'll examine LLM guardrails, technical systems, and processes designed to ensure LLMs' safe and reliable operation.

Everything You Need to Know About LLM Guardrails

 Explore DeepSeek-VL2, the open-source MoE vision-language model. Discover its architecture, efficient training pipeline, and top-tier performance.


DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding

Discover DeepRAG, an advanced retrieval-augmented generation (RAG) model that improves LLM accuracy by retrieving only essential data through step-by-step reasoning.

Introducing Zilliz CLI and Agent Skills for Zilliz Cloud

Introducing Functions and Model Inference on Zilliz Cloud: Automatic Embedding and Reranking with Hosted Models

Turbopuffer vs. Zilliz Cloud: A Performance and Cost Benchmark for Multi-Tenant Vector Search

Turbopuffer vs. Zilliz Cloud: A Compliance and Enterprise Readiness Evaluation for Multi-Tenant Vector Search

AI Assistant