Seamless AI Workflows

Content

Start Free, Scale Easily

Start to build your GenAl apps today with Zilliz Cloud Serverless

AI Assistant

Milvus Ambassador Program

Events

Discord Forum

GitHub

Unstructured Data Meetups

Milvus Basics

Slack

Welcome to the community!

Milvus Community

Zilliz hosts Unstructured Data Meetups in various locations around the world with the goal of bringing together developers who are interested in building generative AI applications with unstructured data. As new AI models and platforms are growing at a rapid pace, meetups have become a great forum for developers and engineers curious about or working on GenAI applications to learn and network.

Past Meetups

Don't want to wait? 

Apply to be a speaker or our sponsor in our events!

Want to be a speaker or sponsor?

Upcoming Events

Upcoming Zilliz Unstructured Data Meetups

Why Zilliz Cloud is the Top Chioce for Enterprise-Level Vector Search.

Related Resources

Success Stories

Popular Vector Database Use Cases<0></0>Zilliz Cloud Can Make a Difference 

Saving time and costs when combining Zilliz Cloud with GPTCache

How Zilliz Cloud Augments LLM Applications

RAG for LLMs: Updating and expanding LLMs’ knowledge base for more accurate answers

<0>The CVP stack (ChatGPT/LLMs + a vector database + prompt-as-code)</0> is an increasingly popular AI stack that shows the value of vector databases for LLM enhancement. We can use <1>OSS Chat</1> as an example to demonstrate how the CVP stack works.

OSS Chat is a chatbot that can answer questions about GitHub projects. It collects and stores information from various GitHub repositories and their documentation pages in Zilliz Cloud in the form of embeddings. When a user asks OSS Chat about any open-source project, Zilliz Cloud conducts a similarity search to find the topk most relevant outcomes. Then these results are combined with the original question to create a prompt that gives ChatGPT a broader context, resulting in more accurate answers.

We can also incorporate the GPTCache into the CVP stack to reduce costs and speed up responses.

ChatGPT/LLMs + a vector database + prompt-as-code

The CVP Stack

Retrieval Augmented Generation (RAG)

Milvus Integrations with Popular AI Projects

Lacking domain-specific information

Prone to hallucination 

Costly and slow

Failure to access up-to-date information

Token Limit

Immutable pre-training data

LLM Limitations

LLM Projects Utilizing Milvus & Zilliz Cloud

Vector Database Use Cases: Retrieval Augmented Generation - Zilliz

Share Your Story with Us!

Vector Database Use Cases

Workflows IA fluides

Contenu

Commencez gratuitement, évoluez facilement

Commencez à développer vos applications GenAI dès aujourd'hui avec Zilliz Cloud Serverless

Assistant IA

Programme des ambassadeurs Milvus

Événements

Forum Discord

Rencontres sur les données non structurées

Bases de Milvus

Bienvenue dans la communauté !

Communauté Milvus

Zilliz organise des rencontres sur les données non structurées dans différentes villes du monde avec pour objectif de rassembler les développeurs intéressés par la création d'applications d'IA générative avec des données non structurées. Alors que les nouveaux modèles et plateformes d'IA se développent rapidement, ces rencontres sont devenues un excellent forum pour les développeurs et ingénieurs curieux ou travaillant sur des applications GenAI pour apprendre et réseauter.

Rencontres passées

Vous ne voulez pas attendre ?

Postulez pour être intervenant ou sponsor lors de nos événements !

Vous souhaitez intervenir ou sponsoriser ?

Événements à venir

Prochaines rencontres Zilliz sur les données non structurées

Pourquoi Zilliz Cloud est le Choix Numéro Un pour la Recherche Vectorielle de Niveau Entreprise.

Ressources Associées

Histoires de Succès

Cas d'Utilisation Populaires de la Base de Données Vectorielle<0></0>Zilliz Cloud Peut Faire la Différence

Économiser du temps et des coûts en combinant Zilliz Cloud avec GPTCache

Comment Zilliz Cloud Augmente les Applications LLM

RAG pour LLM : Mise à jour et extension de la base de connaissances des LLM pour des réponses plus précises

<0>La pile CVP (ChatGPT/LLMs + une base de données vectorielle + prompt-as-code)</0> est une pile d'IA de plus en plus populaire qui montre la valeur des bases de données vectorielles pour l'amélioration des LLM. Nous pouvons utiliser <1>OSS Chat</1> comme exemple pour démontrer comment fonctionne la pile CVP.

OSS Chat est un chatbot qui peut répondre à des questions sur les projets GitHub. Il collecte et stocke des informations provenant de divers dépôts GitHub et de leurs pages de documentation dans Zilliz Cloud sous forme d'embeddings. Lorsqu'un utilisateur interroge OSS Chat sur un projet open-source, Zilliz Cloud effectue une recherche de similarité pour trouver les topk résultats les plus pertinents. Ensuite, ces résultats sont combinés avec la question originale pour créer une invite qui donne à ChatGPT un contexte plus large, ce qui permet d'obtenir des réponses plus précises.

Nous pouvons également intégrer GPTCache dans la pile CVP pour réduire les coûts et accélérer les réponses.

ChatGPT/LLMs + une base de données vectorielle + prompt-as-code

La Pile CVP

Génération Augmentée par Récupération (RAG)

Intégrations de Milvus avec des Projets d'IA Populaires

Manque d'informations spécifiques au domaine

Sujet à l'hallucination

Coûteux et lent

Incapacité à accéder à des informations à jour

Limite de Jetons

Données de pré-formation immuables

Limitations des LLM

Projets LLM Utilisant Milvus & Zilliz Cloud

Cas d'Utilisation de la Base de Données Vectorielle : Génération Augmentée par Récupération - Zilliz

Partagez Votre Histoire avec Nous !

Cas d'Utilisation de la Base de Données Vectorielle

Hands-on Tutorial: Building an Agent to Reason about Private Data with Milvus

Combining Lexical and Semantic Search with Milvus 2.5

Bedrock Data Automation (Preview): Simplifying Unstructured Data Processing

Voice-to-Value: LLM-Powered Customer Interaction Analysis

Building the Next-Gen Apps with Multimodal Retrieval using Twelve Labs & Milvus

Bridging Data Pipelines and AI: Powering Insights with Airbyte and Milvus

Building an Accuracy Flywheel for your LLM RAG Apps

Efficient Inference and Information Retrieval for Agents: SambaNova + Milvus

Evaluating RAG pipelines built on unstructured data

Gandalf: Insights from the World's Largest Red Team

Structuring Unstructured Text using generative AI: The key to information extraction

LLM Agent Observability: Lessons Learned from Real-World Applications

Dense Embeddings != Complete Search - a sneak peak of Milvus 2.5

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

Challenges in Structured Document Data Extraction at Scale with LLMs

Multimodal Search with Open-Source Tools


Timeplus: One single binary to tackle streaming and historical analytics


Enhancing Context Provision for LLMs: Beyond RAG and Prompts


Large Language Models ❤️ Knowledge Graphs

RGB-X Model Development: Exploring Four Channel ML Workflows

How Inkeep and Zilliz built an AI Assistant 

Improving RAG with Knowledge Graph + Multi-modality + Milvus

Transformers4rec: Harnessing NLP Advancements for Cutting-Edge Recommender Systems

Small to Slide: RAG using Multimodal LLMs.

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

The Journey of Large Language Models at GetYourGuide

Multi-Agent Systems with Mistral AI, Milvus and llama-agents

Advanced Video Search - Leveraging Twelve Labs and Milvus for Semantic Retrieval

Implement Agentic RAG Using Claude 3.5 Sonnet, LlamaIndex, and Milvus

Modern Analytics & Reporting with Milvus Vector DB and GenAI

Combining Hugging Face Transformer Models and Visual Data with FiftyOne

A Different Angle: Retrieval Optimized Embedding Models

Building the Future of Neural Search: How to Train State-of-the-Art Embeddings

From Dev to Prod: Vector Database Made Easy

Ensuring Secure and Permission-Aware RAG Deployments

How CXAI Toolkit uses RAG for Intelligent Q&A

Docker tools & Open Source libraries for productivity

Scaling Vector Search: How Milvus Handles Billions+

How to Load Test an LLM API using Gatling

Improving Analytics with Time Series and Vector Databases

Garbage In, Garbage Out: Why poor data curation is killing your AI models (and how to fix it)

It's your unstructured data: How to get your GenAI app to production (and speed up your delivery)

How Vector Databases are Revolutionizing Unstructured Data Search in AI Applications


Harnessing the Power of Generative AI with Large Language Models in Human Capital Management

Building an Agentic RAG locally with Ollama and Milvus

Specializing Small Language Models With Less Data

Occiglot - Open Language Models by and for Europe

Building Production Ready Search Pipelines with Spark and Milvus


Challenges associated with using LLM-as-a-judge

Generating privacy-protected synthetic data using Secludy and Milvus

NYC Tech Week - Discussion on Vector Databases, Unstructured Data and AI


Building RAG with self-deployed Milvus vector database and Snowpark Container Services

Infrastructure Challenges in Scaling RAG with Custom AI models

Full RAG: A Modern Architecture for Hyperpersonalization

Introduction to Open Source RAG and RAG Evaluation

Copilot Workspace: What it is, how it works, why it matters

Multilingual narrative tracking in the news - real-time experiments

Exploring Multimodal Embeddings with Milvus

"I see eyes in my soup": How Delivery Hero implemented the safety system for AI-generated images

Processing streaming data in Kafka with Timeplus Proton and Zilliz

Visualizing the Evolution of ML Models: Insights and Tools for Enhanced Understanding

Vector Databases 101 - An introduction to the world of Vector Databases

Fact vs. Fiction: Autodetecting Hallucinations in LLMs

Training state-of-the-art general text embedding

Advanced Retrieval-Augmented Generation apps with LlamaIndex

Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost

Voyage AI: cutting-edge embeddings and rerankers for search and RAG

Chat with your data, privately and locally

Sometimes people worry that if they ask ChatGPT a question, their queries may be used to train the AI model. However, if you use a local application or RAG to search for proprietary documents stored locally on your machine, like patents or personal diaries, the data will be safe. Although this is a good solution, it may slow down the process of running LLMs locally if models with original weights are used. In this talk, Jay proposes a local and optimized RAG pipeline for systems using consumer desktop/laptop NVIDIA GPUs.  We will use Milvus as our vector database for faster vector search, and TensorRT-LLM optimized open-source LLM leveraging local GPU compute.

Introducing Milvus and new features in 2.4 release

The latest version of Milvus introduces sparse vectors to use in your semantic searches. Learn from Yi, Software Engineer at Zilliz, how you can use sparse and dense embeddings to power your RAG apps.


Voyage AI Embedding for your RAG apps 

Voyage AI is a team of leading AI researchers, dedicated to enabling teams to build better RAG applications via quality retrieval. This talk will present the Voyage AI state-of-the-art embedding models and APIs, which outperforms alternatives such as OpenAI v3 text embeddings. These models are a part of the Zilliz Cloud Pipelines.

VectorDB Schema Design 101 - Considerations for Building a Scalable and Performant Vector Search

Approximate Nearest Neighbor Search in Recommender Systems

Path to Production: LLM System Evaluations and Observability

Constructing a Multidimensional Vector Database of Images for Behavioral Science 

Communauté Milvus
Rencontres sur les données non structurées

Rencontres sur les données non structurées

Événements à venir

Seattle

Berlin

New York

San Francisco

South Bay

Tokyo

Vous ne voulez pas attendre ?

Rencontres passées

Hands-on Tutorial: Building an Agent to Reason about Private Data with Milvus

Combining Lexical and Semantic Search with Milvus 2.5

Bedrock Data Automation (Preview): Simplifying Unstructured Data Processing

Voice-to-Value: LLM-Powered Customer Interaction Analysis

Full Text Search with Milvus 2.5

Building the Next-Gen Apps with Multimodal Retrieval using Twelve Labs & Milvus

Bridging Data Pipelines and AI: Powering Insights with Airbyte and Milvus

Building an Accuracy Flywheel for your LLM RAG Apps

Efficient Inference and Information Retrieval for Agents: SambaNova + Milvus

Communauté MilvusRencontres sur les données non structurées

Rencontres sur les données non structurées

Événements à venir

Seattle

Berlin

New York

San Francisco

South Bay

Tokyo

Vous ne voulez pas attendre ?

Rencontres passées

Hands-on Tutorial: Building an Agent to Reason about Private Data with Milvus

Combining Lexical and Semantic Search with Milvus 2.5

Bedrock Data Automation (Preview): Simplifying Unstructured Data Processing

Voice-to-Value: LLM-Powered Customer Interaction Analysis

Full Text Search with Milvus 2.5

Building the Next-Gen Apps with Multimodal Retrieval using Twelve Labs & Milvus

Bridging Data Pipelines and AI: Powering Insights with Airbyte and Milvus

Building an Accuracy Flywheel for your LLM RAG Apps

Efficient Inference and Information Retrieval for Agents: SambaNova + Milvus

Communauté Milvus
Rencontres sur les données non structurées