# 使用 Homebrew, Nix 安装 weaviate 查看 weaviate 的安装路径、可执行文件、元数据以及面向 AI 代理工作流的安全说明。 ## 安装 ```sh sudo av install brew:weaviate ``` 其他安装命令: ### macOS - Homebrew (100%): ```sh brew install weaviate ``` 证据: local Homebrew formula metadata ### Linux - Nix (92%): ```sh nix profile install nixpkgs#weaviate ``` 证据: nixpkgs package indexes: pkgs/by-name/we/weaviate/package.nix from https://api.github.com/repos/NixOS/nixpkgs/git/trees/master?recursive=1 ## 软件包事实 - **软件包键:** brew:weaviate - **软件包管理器:** Homebrew - **版本:** 1.38.8 - **来源摘要:** Open-source vector database that stores both objects and vectors - **主页:** - **仓库:** - **最后更新:** 2026-07-29T18:57:42Z - **已生成:** 2026-08-03T19:37:03+00:00 ## 可执行文件 - weaviate (别名) ## 安装行为 - Bottle: 不可用 ## 版本和新鲜度 - 页面生成时间: 2026-08-03 - 管理器版本: 1.38.8 ## 项目历史与用法 Weaviate is an open-source vector database and semantic search engine built around storing data objects together with vector embeddings. Its package-manager identity sits at the intersection of databases, search engines, and AI infrastructure: developers install it when they want a local or self-hosted service that can combine vector similarity, keyword filtering, retrieval-augmented generation, and reranking. ### 项目历史 The Weaviate idea predates the modern RAG boom. Bob van Luijt's official project history traces an early line from 2017 writing about semantic-web-style 'things' to the end of 2018, when Weaviate entered a Dutch startup accelerator and the startup around it became SeMI Technologies, short for Semantic Machine Insights. The project then narrowed from broad semantic data modeling toward natural-language processing, embeddings, and vector storage. Weaviate's own history describes this shift as the birth of the Weaviate Search Graph: a database/search system meant to make semantic search available as an open-source product rather than as a bespoke machine-learning pipeline. In 2023, SeMI Technologies renamed itself Weaviate, adopting the name of the flagship open-source vector-search engine. The rename reflected the fact that the developer-facing product brand had become better known than the original company name. ### 采用历史 Weaviate's adoption rose with the wider normalization of embeddings in application development. The project describes use cases such as invoice classification, concept-based document search, site search, and product knowledge graphs; its current repository and platform positioning add RAG systems, semantic and image search, recommendation engines, chatbots, and content classification. By July 2026 the public GitHub repository reported more than 16,000 stars and active releases in the 1.3x series, with release notes covering replication, vector-index work, BM25 optimization, and model-provider modules. That release cadence is a useful package-nerd signal: this is not just a research demo, but a packaged server with continuing operational and AI-integration work. ### 使用方式 In local development and self-hosted setups, Weaviate is typically run as a service behind an application, then addressed through client libraries or HTTP/gRPC APIs. The package supplies the server binary for developers who want to test schemas, indexes, vectorizers, hybrid search, and RAG retrieval locally before moving the same workload to containers, Kubernetes, or Weaviate Cloud. The tool is usually selected when a conventional relational database or keyword search engine is not enough: users want nearest-neighbor search over embeddings, metadata filtering, and application-level retrieval in one system. The package is therefore most visible in AI application stacks, search prototypes, and MLOps/data-platform experiments. ### 为什么软件包爱好者会关心 For package nerds, Weaviate is one of the recognizable names in the first wave of vector databases that became ordinary installable infrastructure. Its significance is less the CLI itself than the fact that a vector database moved into the same packaging channels as Redis, PostgreSQL-adjacent tools, and search servers, making semantic search something developers could install and script locally. ### 时间线 - 2017: Bob van Luijt wrote about the overlap between semantic-web objects and internet-of-things 'things', an idea later tied to Weaviate's conceptual roots. - 2018: Weaviate entered a Dutch startup accelerator, where the team and company around the open-source project began to form. - 2019: SeMI Technologies was founded around the Weaviate open-source vector database. - 2023: SeMI Technologies renamed itself Weaviate to match the better-known product brand. - 2026: The GitHub project remained actively released, with v1.37 and v1.38 release trains visible in June 2026. ### Related projects - Weaviate belongs to the vector database and neural-search family alongside systems such as Milvus, Qdrant, Vespa, Elasticsearch/OpenSearch vector search, and managed embedding stores. It is also commonly paired with language-model orchestration frameworks and application code that performs RAG. ### 来源 - - - - - ## 安全说明 没有找到 weaviate 的匹配本地密钥处理 manifest。Nucleus 软件包元数据仍在此发布，以便未来覆盖拥有稳定的软件包 URL。 ## 其他软件包管理器记录 - Nix - weaviate: normalized package name match | nixpkgs package indexes: pkgs/by-name/we/weaviate/package.nix from https://api.github.com/repos/NixOS/nixpkgs/git/trees/master?recursive=1 ## Combined YAML source View the package source record on GitHub. [combined/weaviate.yml](https://github.com/mxcl/pkgdb/blob/main/combined/weaviate.yml) ## 来源 - pkg.so package database - Geiger risk classifier - curated package history - pkgdb category and tag curation - external package-manager database matches - cross-ecosystem install command graph