Exploring how Milvus makes SmartNews’s ad recommender more scalable, reliable, and up-to-date.

large_How SmartNews Transforms Real-Time  Ad Recommendations with Milvus.png

medium_How SmartNews Transforms Real-Time  Ad Recommendations with Milvus.png

small_How SmartNews Transforms Real-Time  Ad Recommendations with Milvus.png

thumbnail_How SmartNews Transforms Real-Time  Ad Recommendations with Milvus.png

How SmartNews Transforms Real-Time  Ad Recommendations with Milvus.png

Transforming Ad Recommendations: SmartNews's Journey with Milvus

A start-to-finish tutorial for RAG retrieval and question-answering chatbot on custom documents using Milvus, LangChain, and an open-source LLM. 

large_Nov 28——Building an Open Source Chatbot Using LangChain and Milvus in Under 5 Minutes.png

medium_Nov 28——Building an Open Source Chatbot Using LangChain and Milvus in Under 5 Minutes.png

small_Nov 28——Building an Open Source Chatbot Using LangChain and Milvus in Under 5 Minutes.png

thumbnail_Nov 28——Building an Open Source Chatbot Using LangChain and Milvus in Under 5 Minutes.png

Nov 28——Building an Open Source Chatbot Using LangChain and Milvus in Under 5 Minutes.png

Building an Open Source Chatbot using LangChain and Milvus in Under 5 Minutes

Building an Open Source Chatbot Using LangChain and Milvus in Under 5 Minutes

An ultimate guide on understanding, setting up, and implementing FAISS. 

Accelerated Vector Search

large_June 04——Setting Up With Facebook AI Similarity Search.png

medium_June 04——Setting Up With Facebook AI Similarity Search.png

small_June 04——Setting Up With Facebook AI Similarity Search.png

thumbnail_June 04——Setting Up With Facebook AI Similarity Search.png

June 04——Setting Up With Facebook AI Similarity Search.png

What is Faiss?

Mastering Efficient Similarity Search with Faiss Library

Advent of Code is a fun and festive way to learn new open-source skills and win swag this December. Learn how to participate by reading this blog. 

large_Advent of Code.png

medium_Advent of Code.png

small_Advent of Code.png

thumbnail_Advent of Code.png

Advent of Code.png

Advent of Code for Open Source

A tutorial that guides you through connecting with Milvus in minutes. 

large_Getting Started with a Milvus Connection.png

medium_Getting Started with a Milvus Connection.png

small_Getting Started with a Milvus Connection.png

thumbnail_Getting Started with a Milvus Connection.png

Getting Started with a Milvus Connection.png

Getting Started with a Milvus Connection

Learn why Milvus, an open-source vector database, is pivotal in enabling Credal's vision for "Useful AI, made safe."

large_How Credal AI Unlocks Secure, Governable GenAI with Milvus-20231103-030950.png

medium_How Credal AI Unlocks Secure, Governable GenAI with Milvus-20231103-030950.png

small_How Credal AI Unlocks Secure, Governable GenAI with Milvus-20231103-030950.png

thumbnail_How Credal AI Unlocks Secure, Governable GenAI with Milvus-20231103-030950.png

How Credal AI Unlocks Secure, Governable GenAI with Milvus-20231103-030950.png

How Milvus Powers Credal’s Mission for “Useful AI, Made Safe”

Zilliz Cloud is now available on Microsoft Azure, making its debut in the azure-east-us region.

large_Nov. 08 —— Zilliz Cloud Is Now Available on Azure (1).png

medium_Nov. 08 —— Zilliz Cloud Is Now Available on Azure (1).png

small_Nov. 08 —— Zilliz Cloud Is Now Available on Azure (1).png

thumbnail_Nov. 08 —— Zilliz Cloud Is Now Available on Azure (1).png

Nov. 08 —— Zilliz Cloud Is Now Available on Azure (1).png

Zilliz Cloud Now Available on Microsoft Azure

Zilliz Cloud now offers the beta version of Milvus 2.3, marking a significant update in vector database technology. Learn more in this post. 

large_Milvus 2.3 Beta and Enterprise Upgrades on Zilliz Cloud.png

medium_Milvus 2.3 Beta and Enterprise Upgrades on Zilliz Cloud.png

small_Milvus 2.3 Beta and Enterprise Upgrades on Zilliz Cloud.png

thumbnail_Milvus 2.3 Beta and Enterprise Upgrades on Zilliz Cloud.png

Milvus 2.3 Beta and Enterprise Upgrades on Zilliz Cloud.png

Milvus 2.3 Beta and Enterprise Upgrades on Zilliz Cloud

Explore how our recent data ingestion features and integrations streamline data flows and provide developer-friendly experiences.

large_Data Ingestion8-index-types.png

medium_Data Ingestion8-index-types.png

small_Data Ingestion8-index-types.png

thumbnail_Data Ingestion8-index-types.png

Data Ingestion8-index-types.png

Enhancing Data Flow Efficiency: Zilliz Introduces Upsert, Kafka Connector, and Airbyte Integration

Exploring new features and enhancements of Milvus, such as support for Array data types, complex delete expressions, TiKV integration, and more.

large_Milvus 2.3.2 & 2.3.3 Zilliz.png

medium_Milvus 2.3.2 & 2.3.3 Zilliz.png

small_Milvus 2.3.2 & 2.3.3 Zilliz.png

thumbnail_Milvus 2.3.2 & 2.3.3 Zilliz.png

Milvus 2.3.2 & 2.3.3 Zilliz.png

What is New in Milvus 2.3.2 & 2.3.3

What’s New in Milvus 2.3.2 & 2.3.3

Exploring how LangChain implements self querying, a way to build simple retrieval augmented generation (RAG) applications using an LLM, a vector database, and prompts. 

large_Oct 26——How LangChain Implements Self Querying.png

medium_Oct 26——How LangChain Implements Self Querying.png

small_Oct 26——How LangChain Implements Self Querying.png

thumbnail_Oct 26——How LangChain Implements Self Querying.png

Oct 26——How LangChain Implements Self Querying.png

How LangChain Implements Self Querying

Planning to join the 50,000+ attendees at AWS re:Invent this year? Stop by the Milvus booth (#1339) and meet the team from Zilliz.

large_2023_reInvent_Sponsor_Static+Social_Templates_1920x1080.002.png

medium_2023_reInvent_Sponsor_Static+Social_Templates_1920x1080.002.png

small_2023_reInvent_Sponsor_Static+Social_Templates_1920x1080.002.png

thumbnail_2023_reInvent_Sponsor_Static+Social_Templates_1920x1080.002.png

2023_reInvent_Sponsor_Static+Social_Templates_1920x1080.002.png

Join us at AWS re:Invent 2023

In this post, the third installment in our Chat Towards Data Science series, we’ll cover how to ground our RAG results for Towards Data Science via LlamaIndex.

large_Grounding Our Chat Towards Data Science Results.png

medium_Grounding Our Chat Towards Data Science Results.png

small_Grounding Our Chat Towards Data Science Results.png

thumbnail_Grounding Our Chat Towards Data Science Results.png

Grounding Our Chat Towards Data Science Results.png

Grounding Our Chat Towards Data Science Results

Exploring neural network language models, specifically recurrent neural networks, and taking a sneak peek at how embeddings are generated. 

NLP Advanced Guide

large_Nov 08——An Introduction to Modern NLP.png

medium_Nov 08——An Introduction to Modern NLP.png

small_Nov 08——An Introduction to Modern NLP.png

thumbnail_Nov 08——An Introduction to Modern NLP.png

Primer on Neural Networks and Embeddings for Language Models.png

Primer on Neural Networks and Embeddings for Language Models

OpenAI released its new Assistants feature, offering built-in retrieval capabilities. Though powerful in helping developers tap into the potential of additional knowledge, the new feature has many limitations, such as storage constraints and lack of customization. This blog discusses all the challenges the new Assistants feature has and offers a solution to address those challenges. 

large_Nov.14---Customizing OpenAI Built-In Retrieval Using Milvus Vector Database.png

medium_Nov.14---Customizing OpenAI Built-In Retrieval Using Milvus Vector Database.png

small_Nov.14---Customizing OpenAI Built-In Retrieval Using Milvus Vector Database.png

thumbnail_Nov.14---Customizing OpenAI Built-In Retrieval Using Milvus Vector Database.png

Nov.14---Customizing OpenAI Built-In Retrieval Using Milvus Vector Database.png

Customizing OpenAI Built-In Retrieval Using Milvus Vector Database 

Do We Still Need Vector Databases for RAG with OpenAI's Releasing of Its Built-In Retrieval?

From Siri to chatbots, the applications of natural language processing are ubiquitous in our daily lives. Learn about the 10 most popular LLMs taking 2023 by storm and another 10 basic NLP models. 


NLP Basics

large_Popular NLP Models to Empower Your ML Applications.png

medium_Popular NLP Models to Empower Your ML Applications.png

small_Popular NLP Models to Empower Your ML Applications.png

thumbnail_Popular NLP Models to Empower Your ML Applications.png

Popular NLP Models to Empower Your ML Applications.png

A review of seven Large Language Models taking 2023 by storm as well as of 10 basic NLP models

Top 20 NLP Models to Empower Your ML Application

Exploring Milvus’s newly released range search feature, how it differs from the traditional KNN search, and when to use it.

large_Unlock Recommendation Use-Cases with Milvus' New Range Search.png

medium_Unlock Recommendation Use-Cases with Milvus' New Range Search.png

small_Unlock Recommendation Use-Cases with Milvus' New Range Search.png

thumbnail_Unlock Recommendation Use-Cases with Milvus' New Range Search.png

Unlock Recommendation Use-Cases with Milvus' New Range Search.png

Unlock Advanced Recommendation Engines with Milvus' New Range Search

In case you missed it, here's a recap of Zilliz at HackNC 2023.

large_Recapping HackNC-20231109-064740.png

medium_Recapping HackNC-20231109-064740.png

small_Recapping HackNC-20231109-064740.png

thumbnail_Recapping HackNC-20231109-064740.png

Recapping HackNC-20231109-064740.png

Zilliz at HackNC 2023

This post covers Natural Language Processing fundamentals that are essential to understanding all of today’s language models.

large_Nov 03——Tokens, N-Grams, and Bag-of-Words Models.png

medium_Nov 03——Tokens, N-Grams, and Bag-of-Words Models.png

small_Nov 03——Tokens, N-Grams, and Bag-of-Words Models.png

thumbnail_Nov 03——Tokens, N-Grams, and Bag-of-Words Models.png

Nov 03——Tokens, N-Grams, and Bag-of-Words Models.png

An introduction to modern NLP by way of tokens, n-grams, and bag-of-words models

Natural Language Processing Fundamentals: Tokens, N-Grams, and Bag-of-Words Models

Discover the intricacies of Natural Language Processing (NLP) from sentiment analysis to question answering, and learn how vector databases, like Zilliz, revolutionize NLP by enabling efficient storage and retrieval of embeddings. 

large_Nov 03——A Beginner's Guide to NLP-20231103-032516.png

medium_Nov 03——A Beginner's Guide to NLP-20231103-032516.png

small_Nov 03——A Beginner's Guide to NLP-20231103-032516.png

thumbnail_Nov 03——A Beginner's Guide to NLP-20231103-032516.png

Nov 03——A Beginner's Guide to NLP-20231103-032516.png

A Beginner's Guide to Natural Language Processing

An Introduction to Natural Language Processing

If you didn't catch CalHack 2023, read this recap complete with attendee and prize stats as well as overviews of winning projects.  

large_NOV 03——Recapping Cal Hacks.png

medium_NOV 03——Recapping Cal Hacks.png

small_NOV 03——Recapping Cal Hacks.png

thumbnail_NOV 03——Recapping Cal Hacks.png

NOV 03——Recapping Cal Hacks.png

Zilliz at CalHacks 2023

The newly released Confluent Kafka Sink Connector enables seamless real-time vector data streaming from Confluent to Milvus or Zilliz, unleashing the full potential of unstructured data and significantly enhancing real-time Generative AI powered by large language models (LLMs) like OpenAI’s GPT-4.


large_Oct 26——Breaking Barriers_ Zilliz and Confluent Integration for Real-Time AI Applications-20231026-113527.png

medium_Oct 26——Breaking Barriers_ Zilliz and Confluent Integration for Real-Time AI Applications-20231026-113527.png

small_Oct 26——Breaking Barriers_ Zilliz and Confluent Integration for Real-Time AI Applications-20231026-113527.png

thumbnail_Oct 26——Breaking Barriers_ Zilliz and Confluent Integration for Real-Time AI Applications-20231026-113527.png

Oct 26——Breaking Barriers_ Zilliz and Confluent Integration for Real-Time AI Applications-20231026-113527.png

Announcing Confluent's Kafka Connector for Milvus and Zilliz Cloud: Unlocking the Power of Real-Time AI

Learn why Alexandr Guzhva, one of the authors of the FAISS library, joined Zilliz as Principal Software Engineer.

large_Alexandr-Guzhva-Why-I-Joined-Zilliz.png

medium_Alexandr-Guzhva-Why-I-Joined-Zilliz.png

small_Alexandr-Guzhva-Why-I-Joined-Zilliz.png

thumbnail_Alexandr-Guzhva-Why-I-Joined-Zilliz.png

Alexandr-Guzhva-Why-I-Joined-Zilliz.png

Alexandr Guzhva: Why I Joined Zilliz

Using the Milvus vector database, Troop built a solution that empowers individuals for collective financial activism in major corporations. Here’s the technical challenge they set out to solve and how Milvus supports their solution.

large_How Troop Uses Milvus Vector Database to Unlock the Collective Power of Retail Investors.png

medium_How Troop Uses Milvus Vector Database to Unlock the Collective Power of Retail Investors.png

small_How Troop Uses Milvus Vector Database to Unlock the Collective Power of Retail Investors.png

thumbnail_How Troop Uses Milvus Vector Database to Unlock the Collective Power of Retail Investors.png

How Troop Uses Milvus Vector Database to Unlock the Collective Power of Retail Investors.png

How Troop Uses Milvus Vector Database to Unlock the Collective Power of Retail Investors

Learn how to build a RAG with various configurations and parameters, including index type, embedding model, top k and chunk size.


large_Using Evals to Build Better RAGs TruLens Milvus.png

medium_Using Evals to Build Better RAGs TruLens Milvus.png

small_Using Evals to Build Better RAGs TruLens Milvus.png

thumbnail_Using Evals to Build Better RAGs TruLens Milvus.png

Using Evals to Build Better RAGs TruLens Milvus.png

Evaluations for Retrieval Augmented Generation: TruLens + Milvus

This article explores how to enhance Notion documents with language model interactions using LangChain and Milvus.

large_Retrieval Augmented Generation on Notion Docs via LangChain.png

medium_Retrieval Augmented Generation on Notion Docs via LangChain.png

small_Retrieval Augmented Generation on Notion Docs via LangChain.png

thumbnail_Retrieval Augmented Generation on Notion Docs via LangChain.png

Retrieval Augmented Generation on Notion Docs via LangChain.png

Retrieval Augmented Generation on Notion Docs via LangChain

In this tutorial, we'll dive into DiskANN, a graph-based vector index that enables large-scale storage, indexing, and search of vectors by persisting the bulk of the index on NVMe hard disks. We'll first cover Vamana, the core data structure behind DiskANN, before discussing how the on-disk portion of DiskANN utilizes a Vamana graph to perform queries efficiently. Like previous tutorials, we'll also develop our implementation of the Vamana algorithm in Python.

Vector Database 101

large_Nov 08——DiskANN and the  Vamana Algorithm.png

medium_Nov 08——DiskANN and the  Vamana Algorithm.png

small_Nov 08——DiskANN and the  Vamana Algorithm.png

thumbnail_Nov 08——DiskANN and the  Vamana Algorithm.png

Nov 08——DiskANN and the  Vamana Algorithm.png

DiskANN and the Vamana Algorithm

Explore the intricacies of LLM-driven agents, their components, challenges, and future prospects, reshaping the future of artificial intelligence and revolutionizing how we approach complex tasks.

Exploring LLM-Driven Agents in the Age of AI 

Vector Database Stories

From company news to technical tutorials – explore the most popular content on the Zilliz blog.