Empower and celebrate women in AI at the Women in AI RAG Hackathon at Stanford. Engage with experts, build innovative AI projects, and compete for prizes. 


Emily Kurze

Empowering Women in AI: RAG Hackathon at Stanford

RocketQA is a highly optimized dense passage retrieval framework designed to enhance open-domain question-answering (QA) systems. 

Denis Kuria is a freelance technical writer at Zilliz. 

Denis Kuria

RocketQA: Optimized Dense Passage Retrieval for Open-Domain Question Answering

This blog explores why Postgres, with its vector search add-on, pgvector, works well for smaller projects and simpler use cases but reaches its limits for large-scale vector search. 

Stephen Batifol is a Developer Advocate at Zilliz.

Stephen Batifol

Beyond PGVector: When Your Vector Database Needs a Formula 1 Upgrade

Lexical search offers exact term matching; full-text search allows for fuzzy matching; semantic search understands context and intent.

Ruben Winastwan, Freelance Technical Writer

Ruben Winastwan

Semantic Search vs. Lexical Search vs. Full-text Search

GPL is an unsupervised domain adaptation technique for dense retrieval models that combines a query generator with pseudo-labeling. 


 Haziqa Sajid, Freelance Technical Writer

 Haziqa Sajid

GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval

This post explores the key components of RAG, its evolution, technical implementation, evaluation methods, and potential for real-world applications. 


Advancing LLMs: Exploring Native, Advanced, and Modular RAG Approaches

Rob Quiros shared how integrating permissions and authorization into partitions can secure data at the chunk level, addressing privacy concerns.


Yesha Shastri, Freelance Technical Writer

Yesha Shastri

Building Secure RAG Workflows with Chunk-Level Data Partitioning

Annoy is a lightweight, open-source library designed for fast, approximate nearest-neighbor searches in high-dimensional vector spaces.


Fendy Feng

ShriVarsheni R

What is Annoy?

This blog will discuss the growing need to detect machine-generated text, past detection methods, and a new approach: Binoculars. 

Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text

Discover how Augmented SBERT uses data augmentation to enhance the bi-encoder for pairwise sentence scoring. 

Augmented SBERT: A Data Augmentation Method to Enhance Bi-Encoders for Pairwise Sentence Scoring

AI agents are like having a supercharged assistant by your side—analyzing data, making decisions, and seamlessly integrating with tools and environments. 

Top 10 AI Agents to Watch in 2025 🚀

LLM frameworks simplify workflows, enhance performance, and integrate seamlessly with existing systems, helping developers unlock the full potential of LLMs with less effort.

10 Open-Source LLM Frameworks Developers Can’t Ignore in 2025

Discover how engineering teams can revolutionize legal workflows using OCR, vector databases, and RAG systems. Learn implementation strategies and best practices for modern legal tech.

Chris Churilo

Optimizing Legal Tech with OCR, Cross-Lingual Processing, Vector Databases, and RAG Systems

RA-DIT, or Retrieval-Augmented Dual Instruction Tuning, is a method for fine-tuning both the LLM and the retriever in a RAG setup to enhance overall response quality.

Enhancing RAG with RA-DIT: A Fine-Tuning Approach to Minimize LLM Hallucinations

 In this blog, we will explore Qwen and vLLM and how combining both with the Milvus vector database can be used to build a robust RAG system.

Benito Martin

Building RAG Applications with Milvus, Qwen, and vLLM

Voyager is an Approximate Nearest Neighbor (ANN) search library optimized for high-dimensional vector data.

Simon Mwaniki 

What is Voyager?

This tutorial has demonstrated how to leverage Milvus and Friendli Serverless Endpoints to implement advanced RAG and multi-modal queries. 

Wonook is currently doing research and software engineering at FriendliAI. 

Wonook Song

Leveraging Milvus and Friendli Serverless Endpoints for Advanced RAG and Multi-Modal Queries

We're thrilled to announce the release of Milvus 2.5, a significant step in our journey to build the world's most complete solution for all search workloads. 

Steffi Li

Introducing Milvus 2.5: Built-in Full-Text Search, Advanced Query Optimization, and More 🚀

Many-Shot In-Context Learning is an NLP technique where a model generates predictions by observing multiple examples within the input context. 

Unlocking the Power of Many-Shot In-Context Learning in LLMs

A step-by-step guide to building an AI-powered FAQ system using Milvus as the vector database, LangChain.js for workflow coordination, and Strapi for content management

Build RAG with LangChainJS, Milvus, and Strapi

Matryoshka Representation Learning (MRL) is a method for generating hierarchical, nested embeddings that capture information at multiple levels of abstraction. 

Matryoshka Representation Learning Explained: The Method Behind OpenAI’s Efficient Text Embeddings

The Data Prep Kit (DPK) is an open-source toolkit by IBM Research designed to streamline unstructured data preparation for building AI applications. 

Introducing IBM Data Prep Kit for Streamlined LLM Workflows

In this tutorial, we will explore how to build a robust RAG application by combining the capabilities of Milvus, a scalable vector database optimized for similarity search, and DBRX. 

Building a RAG Application with Milvus and Databricks DBRX

The Goldfish Loss technique prevents the verbatim reproduction of training data in LLM output by modifying the standard next-token prediction training objective.

Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs

We discussed the checkability training approach to help LLMs generate accurate answers that humans can easily understand and verify. 


Prover-Verifier Games Improve Legibility of LLM Outputs

Zilliz Cloud delivers reliable vector storage and search, while Vectorize automates your RAG pipelines and keeps your embeddings up-to-date. 

Jamie Ferguson focuses on shaping the product strategy and driving growth at Vectorize, drawing on her technical background in AI and engineering.

Jamie Ferguson

Deliver RAG Applications 10x Faster with Zilliz and Vectorize

AXN (Adaptive Cross-Encoder Nearest Neighbor Search) uses a sparse matrix of CE scores to approximate k-NN results, reducing computation while maintaining high accuracy.

Next-Gen Retrieval: How Cross-Encoders and Sparse Matrix Factorization Redefine k-NN Search

We’ve explored how multi-tenancy frameworks play a critical role in the scalability, security, and performance of RAG-powered knowledge bases. 

Robert Guo

Designing Multi-Tenancy RAG with Milvus: Best Practices for Scalable Enterprise Knowledge Bases

An overview of various RAG pipeline architectures, retrieval and evaluation frameworks, and examples of biases and failures in LLMs.


Evaluating Retrieval-Augmented Generation (RAG): Everything You Should Know

Purpose-built vector databases outperform dual-system setups by unifying Sparse-BM25 and semantic search in a single, efficient implementation.

Jiang Chen

Elasticsearch Was Great, But Vector Databases Are the Future

GLiNER is an open-source NER model using a bidirectional transformer encoder. 


GLiNER: Generalist Model for Named Entity Recognition Using Bidirectional Transformer

Mixture-of-Agents (MoA) is a framework where multiple specialized LLMs, or "agents," collaborate to solve tasks by leveraging their unique strengths. 


Mixture-of-Agents (MoA): How Collective Intelligence Elevates LLM Performance

RouteLLM is an open-source framework that enables developers to efficiently route tasks to the most suitable LLMs based on cost, latency, and accuracy.

RouteLLM: An Open-Source Framework for Navigating Cost-Quality Trade-Offs in LLM Deployment

Compare top vector database vendors, run benchmarks, and choose the right solution for your AI-driven applications. Download the guide now!


Making Sense of the Vector Database Landscape

LaVA is a multimodal model that combines text-based LLMs with visual processing capabilities through visual instruction tuning. 


LLaVA: Advancing Vision-Language Models Through Visual Instruction Tuning

This blog explores how RAG works, RAG challenges, and advanced RAG techniques like Small to Slide RAG and ColPali. 


Advanced RAG Techniques: Bridging Text and Visuals for More Accurate Responses

We'll learn to build a Voice Assistant, a specialized Agentic RAG system designed for voice interactions, with Milvus, Llama 3.2, and other GenAI tools. 

Stop Waiting, Start Building: Voice Assistant With Milvus and Llama 3.2

Vector Quantization (VQ) is a data compression technique representing a large set of similar data points with a smaller set of representative vectors, known as centroids. 

Unlocking the Power of Vector Quantization: Techniques for Efficient Data Compression and Retrieval

Explore Zilliz Cloud’s three CU options and learn how to choose the most suitable one for your business

How to Select the Most Appropriate CU Type and Size for Your Business?

This new UI is cleaner, more intuitive, and specifically designed to streamline workflows, reduce cognitive load, and boost productivity

Koko Lv

Zilliz Cloud’s Redesigned UI: A Streamlined and Intuitive User Experience

A 10x faster Performance with Cardinal vector search engine,  production-ready features including Multi-replica, Data Migration, Authentication, and more 


New for Zilliz Cloud: 10X Performance Boost and Enhanced Enterprise Features

ScaNN is an open-source library developed by Google for fast, approximate nearest neighbor searches in large-scale datasets. 


What is ScaNN (Scalable Nearest Neighbors)?

Google’s ScaNN is a library for ANNS. This guide walks you you through implementing ScaNN and demonstrate how to integrate it with Milvus. 


Getting Started with ScaNN

Milvus offers row-level RBAC (Role-Based Access Control) which is a robust solution for managing data access with precision and efficiency. 


Ken Zhang is a Senior Product Manager at Zilliz

Ken Zhang

Enabling Fine-Grained Access Control with Milvus Row-Level RBAC

introduce Llama 3.1 and 3.2 and explore how to build a RAG app with Llama 3.2 and Milvus. 

Learn Llama 3.2 and How to Build a RAG Pipeline with Llama and Milvus

LoRA (Low-Rank Adaptation) is a technique for efficiently fine-tuning LLMs by introducing low-rank trainable weight matrices into specific model layers.

LoRA Explained: Low-Rank Adaptation for Fine-Tuning LLMs

This blog will guide you through creating a Multimodal RAG with Milvus and vLLM. 

Deploying a Multimodal RAG System Using vLLM and Milvus

Transformers4Rec is a powerful and flexible library designed for creating sequential and session-based recommendation systems with PyTorch.

Transformers4Rec: Bringing NLP Power to Modern Recommendation Systems

Knowledge distillation is a machine learning technique in which the knowledge of a large, complex model (teacher) is transferred to a smaller, simpler model (student). 

Knowledge Distillation: Transferring Knowledge from Large, Computationally Expensive LLMs to Smaller Ones Without Sacrificing Validity

Robert Tran, the Co-founder and CTO of Inkeep, shared how Inkeep and Zilliz built an AI-powered assistant for their documentation site. 

How Inkeep and Milvus Built a RAG-driven AI Assistant for Smarter Interaction

Organizations can ensure privacy at every layer of their data pipeline by anonymizing or masking PII using the PII Marker before data reaches the vector database. 

Victor Bian

Safe RAG with HydroX AI and Zilliz: PII Masking for Responsible GenAI

Voyager: a new open-source library for fast nearest-neighbor searches. Voyager uses the HNSW algorithm, outperforming its previous library, Annoy. 

Getting Started with Voyager: Spotify's Nearest-Neighbor Search Library

XLNet is a transformer-based language model that builds on BERT's limitations by introducing a new approach called permutation-based training. 

XLNet Explained: Generalized Autoregressive Pretraining for Enhanced Language Understanding

ALIGN model is designed to learn visual and language representations from noisy image-alt-text pairs.

ALIGN Explained: Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision

Run ghastly multimodal analytics and Retrieval Augmented Generation with our "ghosts" collections in the open-source Milvus vector database.


Tim Spann is the Principal Developer Advocate at Zilliz. 

Tim Spann

Catch a Cute Ghost this Halloween with Milvus

HNSWlib is an open-source C++ and Python library implementation of the HNSW algorithm, which is used for fast approximate nearest neighbor search. 

Understanding HNSWlib: A Graph-based Library for Fast Approximate Nearest Neighbor Search

Florence is a large-scale vision-language model developed by Microsoft, particularly effective for applications requiring multimodal capabilities. 

Florence: An Advanced Foundation Model for Computer Vision by Microsoft 

Explore How GetYourGuide use LLMs to improve customer experiences and How RAG address common LLM issues 

The Role of LLMs in Modern Travel: Opportunities and Challenges Ahead

BentoML shares its research insights in AI orchestration, demonstrating solutions for optimizing performance issues when self-hosting AI models. 

Trevor Trinh

The Practical Guide to Self-Hosting Compound LLM Systems

Discuss multimodal retrieval and composed image retrieval (CIR) techniques, including Pic2Word, CompoDiff, CIReVL, and MagicLens. 

David Wang

Combining Images and Text Together: How Multimodal Retrieval Transforms Search

Mamba is a new architecture for sequence modeling, designed to offer an alternative to the Transformer models commonly used in machine learning. 

The Potential Transformer Replacement: Mamba

In this article, we explored various RAG components and discussed the approaches with optimal performance in each component. 

Best Practices in Implementing Retrieval-Augmented Generation (RAG) Applications 

Contrastive Captioners (CoCa) is an AI model developed by Microsoft that is designed to bridge the capabilities of language models and vision models.

Understanding CoCa: Advancing Image-Text Foundation Models with Contrastive Captioners

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

Sydney Blanchard

The Importance of Data Engineering for Successful AI with Airbyte and Zilliz

Compare Qdrant Cloud and Zilliz Cloud (fully managed Milvus) in this in-depth benchmark, cost, and features comparison.

How to Choose a Vector Database: Qdrant Cloud vs. Zilliz Cloud

RGB-X models: advanced ML models in computer vision that extend traditional RGB data by combining additional depth, infrared, or surface normals data. 

Unlocking Rich Visual Insights with RGB-X Models

Explore AI privacy challenges and solutions like PrivateGPT, discussing their benefits, security features, and practical setup suggestions. 

Securing AI: Advanced Privacy Strategies with PrivateGPT and Milvus

In this article, we'll explore the evolution of MAS from a methodological or approach-based perspective.

The Evolution of Multi-Agent Systems: From Early Neural Networks to Modern Distributed Learning (Methodological)

In this article, we'll discuss the evolution of MAS from its early days to the most recent developments from an algorithmic perspective. 

The Evolution of Multi-Agent Systems: From Early Neural Networks to Modern Distributed Learning (Algorithmic) 

ColPali is an advanced document retrieval model designed to index and retrieve information directly from the visual features of documents, particularly PDFs. 

ColPali: Enhanced Document Retrieval with Vision Language Models and ColBERT Embedding Strategy

Explore how Milvus matches OpenSearch in speed and scalability and surpasses it with its specialized vector search capabilities 

Scaling Search for AI: How Milvus Outperforms OpenSearch

Mixture of Experts (MoE): a neural network architecture to improve model efficiency and scalability by selecting specialized experts for different tasks.


What is Mixture of Experts (MoE)? 

Exploring how domain-specific models and agentic AI systems can capture, share, and apply specialized knowledge for problem-solving in the semiconductor manufacturing industry.

Industrial Problem-Solving through Domain-Specific Models and Agentic AI: A Semiconductor Manufacturing Case Study

Object detection is a computer vision technique that uses neural networks to classify and locate objects, such as humans, buildings, or cars, in images or video. 

What is Object Detection? A Comprehensive Guide

This blog will demonstrate how GCL can be integrated with Milvus, a leading vector database, to create optimized Retrieval-Augmented Generation (RAG) systems.

A Different Angle: Retrieval Optimized Embedding Models

Compare Weaviate Cloud vs. Zilliz Cloud and Milvus in this in-depth benchmark, cost, and features comparison.

How to Choose A Vector Database: Weaviate Cloud vs. Zilliz Cloud

Understand the role of vector databases such as Milvus, how Qarbine simplifies the analytics process, and how Milvus and Qarbine can be integrated to create advanced GenAI applications. 


Modern Analytics & Reporting with Milvus Vector DB and GenAI

PagedAttention and vLLM solve important challenges in serving LLMs, particularly the high costs and inefficiencies in GPU memory usage when using it for inference. 


Efficient Memory Management for Large Language Model Serving with PagedAttention

In this blog, we’ll explore how companies like Hydrox AI and AI Alliance are tackling the critical challenges of AI safety and evaluation.


Evaluating Safety & Alignment of LLM in Specific Domains

Contributing to open source software is a rewarding way to improve your programming skills, collaborate with others, and give back to the development community. Learn how to contribute to Milvus with this beginner guide!


Stefan Webb

Contributing to Open Source Milvus: A Beginner’s Guide

This article will cover five reasons to migrate from Milvus to Zilliz Cloud. We will focus on performance, scalability, security, availability and cost. 

Top 5 Reasons to Migrate from Open Source Milvus to Zilliz Cloud

In this blog, we will implement a multimodal similarity search system. This system will use JinaCLIP to generate multimodal embeddings and the Milvus vector database to store and retrieve similar embeddings given a certain query. 

From CLIP to JinaCLIP: General Text-Image Representation Learning for Search and Multimodal RAG

In this blog post, we explain how to build a GraphRAG Agent using Neo4j and Milvus. By combining the strengths of graph databases and vector search, this agent provides accurate and relevant answers to user queries. 


Jason Koo

Building a GraphRAG Agent With Neo4j and Milvus

A Transformer model is a type of architecture for processing sequences, primarily used in natural language processing (NLP). 

Vector Database Stories