Milvus vs Weaviate

What is Milvus?

🐦 Milvus is a high-performance vector database built for scale. It powers AI applications by efficiently organizing and searching vast amounts of unstructured data, such as text, images, and multi-modal information.

🧑‍💻 Written in Go and C++, Milvus implements hardware acceleration for CPU/GPU to achieve best-in-class vector search performance. Thanks to its fully-distributed and K8s-native architecture, Milvus can scale horizontally, handle tens of thousands of search queries on billions of vectors, and keep data fresh with real-time streaming updates. Milvus also supports Standalone mode for single machine deployment. Milvus Lite is a lightweight version good for quickstart in python with pip install.

Want to use Milvus with zero setup? Try out Zilliz Cloud ☁️ for free. Milvus is available as a fully managed service on Zilliz Cloud, with Serverless, Dedicated and BYOC options available.

For questions about how to use Milvus, join the community on Discord to get help. For reporting problems, file bugs and feature requests in GitHub Issues or ask in Discussions.

The Milvus open-source project is
under LF AI & Data Foundation, distributed with Apache 2.0 License, with Zilliz as its major contributor.

Quickstart

$ pip install -U pymilvus

This installs pymilvus, the Python SDK for Milvus. Use MilvusClient to create a client:

from pymilvus import MilvusClient

• You can also try Milvus Lite for quickstart by installing pymilvus[milvus-lite]. To create a local vector database, simply instantiate a client with a local file name for persisting data:

  client = MilvusClient("milvus_demo.db")
  

  Copy

• You can also specify the credentials to connect to your deployed Milvus server or Zilliz Cloud:

  client = MilvusClient(
    uri="<endpoint_of_self_hosted_milvus_or_zilliz_cloud>",
    token="<username_and_password_or_zilliz_cloud_api_key>")
  

  Copy

With the client, you can create collection:

client.create_collection(
    collection_name="demo_collection",
    dimension=768,  # The vectors we will use in this demo have 768 dimensions
)

Ingest data:

res = client.insert(collection_name="demo_collection", data=data)

Perform vector search:

query_vectors = embedding_fn.encode_queries(["Who is Alan Turing?", "What is AI?"])
res = client.search(
    collection_name="demo_collection",  # target collection
    data=query_vectors,  # a list of one or more query vectors, supports batch
    limit=2,  # how many results to return (topK)
    output_fields=["vector", "text", "subject"],  # what fields to return
)

Why Milvus

Milvus is designed to handle vector search at scale. It stores vectors, which are learned representations of unstructured data, together with other scalar data types such as integers, strings, and JSON objects. Users can conduct efficient vector search with metadata filtering or hybrid search. Here are why developers choose Milvus as the vector database for AI applications:

High Performance at Scale and High Availability

• Milvus features a distributed architecture that separates compute and storage. Milvus can horizontally scale and adapt to diverse traffic patterns, achieving optimal performance by independently increasing query nodes for read-heavy workload and data node for write-heavy workload. The stateless microservices on K8s allow quick recovery from failure, ensuring high availability. The support for replicas further enhances fault tolerance and throughput by loading data segments on multiple query nodes. See benchmark for performance comparison.

Support for Various Vector Index Types and Hardware Acceleration

• Milvus separates the system and core vector search engine, allowing it to support all major vector index types that are optimized for different scenarios, including HNSW, IVF, FLAT (brute-force), SCANN, and DiskANN, with quantization-based variations and mmap. Milvus optimizes vector search for advanced features such as metadata filtering and range search. Additionally, Milvus implements hardware acceleration to enhance vector search performance and supports GPU indexing, such as NVIDIA's CAGRA.

Flexible Multi-tenancy and Hot/Cold Storage

• Milvus supports multi-tenancy through isolation at database, collection, partition, or partition key level. The flexible strategies allow a single cluster to handle hundreds to millions of tenants, also ensures optimized search performance and flexible access control. Milvus enhances cost-effectiveness with hot/cold storage. Frequently accessed hot data can be stored in memory or on SSDs for better performance, while less-accessed cold data is kept on slower, cost-effective storage. This mechanism can significantly reduce costs while maintaining high performance for critical tasks.

Sparse Vector for Full Text Search and Hybrid Search

• In addition to semantic search through dense vector, Milvus also natively supports full text search with BM25 as well as learned sparse embeddings such as SPLADE and BGE-M3. Users can store sparse vectors and dense vectors in the same collection, and define functions to rerank results from multiple search requests. See examples of Hybrid Search with semantic search + full text search.

Data Security and Fine-grain Access Control

• Milvus ensures data security by implementing mandatory user authentication, TLS encryption, and Role-Based Access Control (RBAC). User authentication ensures that only authorized users with valid credentials can access the database, while TLS encryption secures all communications within the network. Additionally, RBAC allows for fine-grained access control by assigning specific permissions to users based on their roles. These features make Milvus a robust and secure choice for enterprise applications, protecting sensitive data from unauthorized access and potential breaches.

Milvus is trusted by AI developers to build applications such as text and image search, Retrieval-Augmented Generation (RAG), and recommendation systems. Milvus powers many mission-critical businesses for startups and enterprises.

Demos and Tutorials

Here is a selection of demos and tutorials to show how to build various types of AI applications made with Milvus:

You can explore a comprehensive Tutorials Overview covering topics such as Retrieval-Augmented Generation (RAG), Semantic Search, Hybrid Search, Question Answering, Recommendation Systems, and various quick-start guides. These resources are designed to help you get started quickly and efficiently.

Image Search	RAG	Drug Discovery

Ecosystem and Integration

Milvus integrates with a comprehensive suite of AI development tools, such as LangChain, LlamaIndex, OpenAI and HuggingFace, making it an ideal vector store for GenAI applications such as Retrieval-Augmented Generation (RAG). Milvus works with both open-source embedding models and embedding services, in text, image and video modalities. Milvus also provides a convenient utility pymilvus[model], users can use the simple wrapper code to transform unstructured data into vector embeddings and leverage reranking models for optimized search results. The Milvus ecosystem also includes Attu for GUI-based administration, Birdwatcher for system debugging, Prometheus/Grafana for monitoring, Milvus CDC for data synchronization, VTS for data migration and data connectors for Spark, Kafka, Fivetran, and Airbyte to build search pipelines.

Check out https://milvus.io/docs/integrations_overview.md for more details.

Documentation

For guidance on installation, usage, deployment, and administration, check out Milvus Docs. For technical milestones and enhancement proposals, check out issues on GitHub.

Contributing

The Milvus open-source project accepts contributions from everyone. See Guidelines for Contributing for details on submitting patches and the development workflow. See our community repository to learn about project governance and access more community resources.

Build Milvus from Source Code

Requirements:

• Linux systems (Ubuntu 20.04 or later recommended):

  Go: >= 1.21
  CMake: >= 3.26.4 && CMake < 4
  GCC: >= 11
  Python: > 3.8 and  <= 3.11
  

  Copy

• MacOS systems with x86_64 (Big Sur 11.5 or later recommended):

  Go: >= 1.21
  CMake: >= 3.26.4 && CMake < 4
  llvm: >= 15
  Python: > 3.8 and  <= 3.11
  

  Copy

• MacOS systems with Apple Silicon (Monterey 12.0.1 or later recommended):

  Go: >= 1.21 (Arch=ARM64)
  CMake: >= 3.26.4 && CMake < 4
  llvm: >= 15
  Python: > 3.8 and  <= 3.11
  

  Copy

Clone Milvus repo and build.

## Clone github repository.
$ git clone https://github.com/milvus-io/milvus.git

## Install third-party dependencies.
$ cd milvus/
$ ./scripts/install_deps.sh

## Compile Milvus.
$ make

For full instructions, see developer's documentation.

Community

Join the Milvus community on Discord to share your suggestions, advice, and questions with our engineering team.

To learn the latest news about Milvus, follow us on social media:

• X
• LinkedIn
• YouTube
• Medium

You can also check out our FAQ page to discover solutions or answers to your issues or questions, and subscribe to Milvus mailing lists:

• Technical Steering Committee
• Technical Discussions
• Announcement

Reference

Reference to cite when you use Milvus in a research paper:

@inproceedings{2021milvus,
  title={Milvus: A Purpose-Built Vector Data Management System},
  author={Wang, Jianguo and Yi, Xiaomeng and Guo, Rentong and Jin, Hai and Xu, Peng and Li, Shengjun and Wang, Xiangyu and Guo, Xiangzhou and Li, Chengming and Xu, Xiaohai and others},
  booktitle={Proceedings of the 2021 International Conference on Management of Data},
  pages={2614--2627},
  year={2021}
}

@article{2022manu,
  title={Manu: a cloud native vector database management system},
  author={Guo, Rentong and Luan, Xiaofan and Xiang, Long and Yan, Xiao and Yi, Xiaomeng and Luo, Jigao and Cheng, Qianya and Xu, Weizhi and Luo, Jiarui and Liu, Frank and others},
  journal={Proceedings of the VLDB Endowment},
  volume={15},
  number={12},
  pages={3548--3561},
  year={2022},
  publisher={VLDB Endowment}
}

Weaviate

Weaviate is a cloud-native vector database that stores both objects and vectors, enabling semantic search at scale. It combines vector similarity search with keyword filtering, retrieval-augmented generation (RAG), and reranking in a single query interface. Common use cases include RAG systems, semantic and image search, recommendation engines, chatbots, and content classification.

Weaviate supports two approaches to store vectors: automatic vectorization at import using integrated models (OpenAI, Cohere, HuggingFace, and others) or direct import of pre-computed vector embeddings. Production deployments benefit from built-in multi-tenancy, replication, RBAC authorization, and many other features.

To get started quickly, have a look at one of these tutorials:

• Quickstart - Weaviate Cloud
• Quickstart - local Docker instance

Installation

Weaviate offers multiple installation and deployment options:

• Docker
• Kubernetes
• Weaviate Cloud

See the installation docs for more deployment options, such as AWS and GCP.

Getting started

You can easily start Weaviate and a local vector embedding model with Docker.
Create a docker-compose.yml file:

services:
  weaviate:
    image: cr.weaviate.io/semitechnologies/weaviate:1.36.0
    ports:
      - "8080:8080"
      - "50051:50051"
    environment:
      ENABLE_MODULES: text2vec-model2vec
      MODEL2VEC_INFERENCE_API: http://text2vec-model2vec:8080

  # A lightweight embedding model that will generate vectors from objects during import
  text2vec-model2vec:
    image: cr.weaviate.io/semitechnologies/model2vec-inference:minishlab-potion-base-32M

Start Weaviate and the embedding service with:

docker compose up -d

Install the Python client (or use another client library):

pip install -U weaviate-client

The following Python example shows how easy it is to populate a Weaviate database with data, create vector embeddings and perform semantic search:

import weaviate
from weaviate.classes.config import Configure, DataType, Property

## Connect to Weaviate
client = weaviate.connect_to_local()

## Create a collection
client.collections.create(
    name="Article",
    properties=[Property(name="content", data_type=DataType.TEXT)],
    vector_config=Configure.Vectors.text2vec_model2vec(),  # Use a vectorizer to generate embeddings during import
    # vector_config=Configure.Vectors.self_provided()  # If you want to import your own pre-generated embeddings
)

## Insert objects and generate embeddings
articles = client.collections.get("Article")
articles.data.insert_many(
    [
        {"content": "Vector databases enable semantic search"},
        {"content": "Machine learning models generate embeddings"},
        {"content": "Weaviate supports hybrid search capabilities"},
    ]
)

## Perform semantic search
results = articles.query.near_text(query="Search objects by meaning", limit=1)
print(results.objects[0])

client.close()

This example uses the Model2Vec vectorizer, but you can choose any other embedding model provider or bring your own pre-generated vectors.

Client libraries and APIs

Weaviate provides client libraries for several programming languages:

• Python
• JavaScript/TypeScript
• Java
• Go
• C#/.NET

There are also additional community-maintained libraries.

Weaviate exposes REST API, gRPC API, and GraphQL API to communicate with the database server.

Weaviate features

These features enable you to build AI-powered applications:

• ⚡ Fast Search Performance: Perform complex semantic searches over billions of vectors in milliseconds. Weaviate's architecture is built in Go for speed and reliability, ensuring your AI applications are highly responsive even under heavy load. See our ANN benchmarks for more info.

• 🔌 Flexible Vectorization: Seamlessly vectorize data at import time with integrated vectorizers from OpenAI, Cohere, HuggingFace, Google, and more. Or you can import your own vector embeddings.

• 🔍 Advanced Hybrid & Image Search: Combine the power of semantic search with traditional keyword (BM25) search, image search and advanced filtering to get the best results with a single API call.

• 🤖 Integrated RAG & Reranking: Go beyond simple retrieval with built-in generative search (RAG) and reranking capabilities. Power sophisticated Q&A systems, chatbots, and summarizers directly from your database without additional tooling.

• 📈 Production-Ready & Scalable: Weaviate is built for mission-critical applications. Go from rapid prototyping to production at scale with native support for horizontal scaling, multi-tenancy, replication, and fine-grained role-based access control (RBAC).

• 💰 Cost-Efficient Operations: Radically lower resource consumption and operational costs with built-in vector compression. Vector quantization and multi-vector encoding reduce memory usage with minimal impact on search performance.

• ⏱️ Object TTL: Automatically expire and remove stale data with configurable time-to-live settings per collection, with full RBAC and multi-tenancy support.

For a complete list of all functionalities, visit the official Weaviate documentation.

Useful resources

AI Agent Skills

Weaviate Agent Skills is a collection of skills for AI coding agents (Claude Code, Cursor, GitHub Copilot, and others) that enable them to work with Weaviate more accurately and efficiently. Skills cover searching, querying, collection management, data import, and full application blueprints (RAG, agentic RAG, chatbots, and more).

Install with:

npx skills add weaviate/agent-skills

Demo projects & recipes

These demos are working applications that highlight some of Weaviate's capabilities. Their source code is available on GitHub.

• Elysia (GitHub): Elysia is a decision tree based agentic system which intelligently decides what tools to use, what results have been obtained, whether it should continue the process or whether its goal has been completed.
• Verba (GitHub): A community-driven open-source application designed to offer an end-to-end, streamlined, and user-friendly interface for Retrieval-Augmented Generation (RAG) out of the box.
• Healthsearch (GitHub): An open-source project aimed at showcasing the potential of leveraging user-written reviews and queries to retrieve supplement products based on specific health effects.
• Awesome-Moviate (GitHub): A movie search and recommendation engine that allows keyword-based (BM25), semantic, and hybrid searches.

We also maintain extensive repositories of Jupyter Notebooks and TypeScript code snippets that cover how to use Weaviate features and integrations:

• Weaviate Python Recipes
• Weaviate TypeScript Recipes

Blog posts

• What is a Vector Database
• What is Vector Search
• What is Hybrid Search
• How to Choose an Embedding Model
• What is RAG
• RAG Evaluation
• Advanced RAG Techniques
• What is Multimodal RAG
• What is Agentic RAG
• What is Graph RAG
• Overview of Late Interaction Models

Integrations

Weaviate integrates with many external services:

Contributing

We welcome and appreciate contributions! Please see our Contributor guide for the development setup, code style guidelines, testing requirements and the pull request process. If you wish to contribute to our Enterprise Edition, your contributions will be under the BSD license.

Join our Community forum to discuss ideas and get help.

License

This repository contains code in our Community Edition and our Enterprise Edition. Most of this repository is available under the BSD 3-Clause License. Files in our wl/ folder are only available under a commercial license with a license key issued by us. If you are interested in a commercial license, please contact us at http://weaviate.io/enterprise-edition. Our binaries, available for download here, combine these two elements. Enterprise features require a license key.

Please see our licensing FAQ for more information.