{ "componentChunkName": "component---src-templates-issues-tsx", "path": "/issues/599", "result": {"data":{"issuesJson":{"id":"97099e85-3783-5c87-b095-10b045282b6d","title":"weaviate/weaviate: Weaviate是一个开源的向量数据库，可以存储对象和向量，允许将向量搜索与结构化过滤相结合，并具有云原生数据库的容错性和可伸缩性。","number":599,"bodyHTML":"

\n

\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n

Repos	weaviate/weaviate
Views	$\"views\"$
Stars	$\"stars\"$
Forks	$\"forks\"$
License	$\"license\"$
UpdatedAt	$\"last-commit\"$
CreatedAt	$\"create-at\"$

\n\n

\n

\n

\n

Weaviate $\"Weaviate$

\n

$\"Go$
\n $\"Build$
\n $\"Go$
\n $\"Coverage$
\n $\"Slack\"$
\n $\"GitHub$

\n

Overview

\n

Weaviate is a cloud-native, open source vector database that is robust, fast, and scalable.

\n

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

\n

Quickstart tutorial To see Weaviate in action
Contributor guide To contribute to this project

\n

For more details, read through the summary on this page or see the system documentation.

\n

\n

Why Weaviate?

\n

Weaviate uses state-of-the-art machine learning (ML) models to turn your data - text, images, and more - into a searchable vector database.

\n

Here are some highlights.

\n

Speed

\n

Weaviate is fast. The core engine can run a 10-NN nearest neighbor search on millions of objects in milliseconds. See benchmarks.

\n

Flexibility

\n

Weaviate can vectorize your data at import time. Or, if you have already vectorized your data, you can upload your own vectors instead.

\n

Modules give you the flexibility to tune Weaviate for your needs. More than two dozen modules connect you to popular services and model hubs such as OpenAI, Cohere, VoyageAI and HuggingFace. Use custom modules to work with your own models or third party services.

\n

Production-readiness

\n

Weaviate is built with scaling, replication, and security in mind so you can go smoothly from rapid prototyping to production at scale.

\n

Beyond search

\n

Weaviate doesn't just power lightning-fast vector searches. Other superpowers include recommendation, summarization, and integration with neural search frameworks.

\n

Who uses Weaviate?

\n

\n
Software Engineers
\n
- Weaviate is an ML-first database engine
- Out-of-the-box modules for AI-powered searches, automatic classification, and LLM integration
- Full CRUD support
- Cloud-native, distributed system that runs well on Kubernetes
- Scales with your workloads
\n
\n
Data Engineers
\n
- Weaviate is a fast, flexible vector database
- Use your own ML model or third party models
- Run locally or with an inference service
\n
\n
Data Scientists
\n
- Seamless handover of Machine Learning models to engineers and MLOps
- Deploy and maintain your ML models in production reliably and efficiently
- Easily package custom trained models
\n

\n

What can you build with Weaviate?

\n

A Weaviate vector database can search text, images, or a combination of both. Fast vector search provides a foundation for chatbots, recommendation systems, summarizers, and classification systems.

\n

Here are some examples that show how Weaviate integrates with other AI and ML tools:

\n

Use Weaviate with third party embeddings

\n

\n

Use Weaviate as a document store

\n

DocArray
Haystack (blogpost)

\n

Use Weaviate as a memory backend

\n

\n

Demos

\n

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

\n

\n

How can you connect to Weaviate?

\n

Weaviate exposes a GraphQL API and a REST API. Starting in v1.23, a new gRPC API provides even faster access to your data.

\n

Weaviate provides client libraries for several popular languages:

\n

\n

There are also community supported libraries for additional languages.

\n

Where can You learn more?

\n

Free, self-paced courses in Weaviate Academy teach you how to use Weaviate. The Tutorials repo has code for example projects. The Recipes repo has even more project code to get you started.

\n

The Weaviate blog and podcast regularly post stories on Weaviate and AI.

\n

Here are some popular posts:

\n

Blogs

\n

\n

Podcasts

\n

\n

Other reading

\n

\n

Join our community!

\n

At Weaviate, we love to connect with our community. We love helping amazing people build cool things. And, we love to talk with you about you passion for vector databases and AI.

\n

Please reach out, and join our community:

\n

\n

To keep up to date with new releases, meetup news, and more, subscribe to our newsletter

","updatedAt":"2025-05-22T01:52:46Z","upvoteCount":null,"author":{"login":"eryajf","avatarUrl":"https://avatars.githubusercontent.com/u/33259379?u=e4a4090a38ac2473aaed4ef9945233636776c6c3&v=4","url":"https://github.com/eryajf"},"category":null,"labels":{"edges":[{"node":{"name":"更多","color":"25B472"}},{"node":{"name":"vector-database","color":"caa1ca"}},{"node":{"name":"weaviate","color":"ffb0c7"}}]},"comments":{"edges":[]}}},"pageContext":{"number":599,"previous":{"title":"qingwave/weave: 一个基于Go + Vue3实现的Web应用模板，支持前后端，拥有完整的认证、存储、Restful API、应用管理（docker & kubernetes）功能","number":598},"next":{"title":"moreKing/web-firewall: 基于 golang+vue3 开发的 Web Linux 防火墙，可以在 Linux 系统中基于 nfatables 用于替代 firewalld 工具。","number":600}}}, "staticQueryHashes": ["151096407","2861350382"]}