Weaviate

概述

Weaviate is an open-source vector database used for semantic search, retrieval-augmented generation (RAG), and hybrid keyword-plus-vector search. It stores objects with their vector embeddings, integrates with popular model providers for vectorization, and exposes GraphQL and REST APIs. The database is free to self-host under BSD-3-Clause, with a paid managed cloud offering.

主要功能

• Vector, keyword, and hybrid search in one engine
• Built-in vectorizer modules for popular model providers
• GraphQL and REST APIs with client libraries
• Horizontal scaling, replication, and multi-tenancy

适用场景

• Retrieval-augmented generation pipelines for LLM apps
• Semantic search over documents and product catalogs
• Recommendation and similarity-matching systems

定价

Weaviate is free to self-host (BSD-3-Clause); Weaviate Cloud is a paid managed service priced by usage and tier.

常见问题

Is Weaviate free?

Yes, self-hosting Weaviate is free under the BSD-3-Clause license; the managed Weaviate Cloud service is paid.

What is Weaviate used for?

Weaviate stores vector embeddings for semantic search, hybrid search, and retrieval-augmented generation in AI applications.

Does Weaviate create embeddings?

Weaviate can vectorize data through built-in modules that call popular embedding providers, or accept vectors you supply.

同类产品

• Amazon Bedrock — AWS 的托管服务，可通过单一 API 使用来自多家提供商的基础模型构建应用。
• Amazon Nova — AWS 推出的亚马逊自研基础模型与服务组合，覆盖文本、多模态、语音、定制模型构建以及可自动化界面操作的智能体。
• Azure AI Foundry — 微软的平台，可在 Azure 上构建、评估并部署 AI 应用与智能体。
• Baseten — 将机器学习模型部署并作为可扩展 API 提供服务的平台。
• Cerebras — AI 算力公司，其推理云基于晶圆级硬件托管开放语言模型。
• Civitai — 用于分享与发现开放图像生成模型、LoRA 与生成作品的社区平台。

查看Weaviate的全部替代品 → · 查看全部平台与基础设施产品 →

来源

• Official website ↗
• Source code (GitHub) ↗

本记录最近复核于 2026-07-30。

机器可读记录：/api/products/weaviate.json · 发现错误？提交纠错