weaviate/weaviate

Project overview

Weaviate is a cloud-native vector database that unifies vector similarity search, hybrid keyword filtering, and retrieval-augmented generation (RAG) into a single query. It is designed for developers and AI engineers building scalable AI applications without maintaining separate systems for retrieval, vector storage, and generation.

Project type

RAG · AI Search · Vector Database

Use cases

Knowledge Q&A · Search & Research

Deployment

Docker / Docker Compose

License

BSD-3-Clause

Best for

• Developers and AI engineers building scalable search pipelines who need integrated vectorization, API-level interaction, and multi-tenant access controls.

Key capabilities

• Executes semantic search, BM25 keyword search, image search, and advanced filtering in milliseconds over billions of vectors.
• Provides built-in generative search and reranking to support question-answering systems, chatbots, and summarizers directly from the database via a single API call.
• Generates vector embeddings at import time using integrated models from external providers, while also supporting user-provided pre-computed vectors.
• Offers horizontal scaling, replication, multi-tenancy, and role-based access control for production applications.
• Automatically expires and removes stale data through configurable TTL settings assigned at the collection level.

Limitations and risks

• Interaction requires a client library or API calls, as the system does not include a built-in graphical user interface.

Getting started

• Start by creating a docker-compose.yml file and running docker compose up -d. Install the Python client library via pip install -U weaviate-client, then connect to the instance using weaviate.connect_to_local().

Evidence and sources

• README: Weaviate is an open-source, cloud-native vector database that stores both objects and vectors, enabling semantic search at scale. It combines vector similarity search with keyword…
• GitHub project description: Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance a…
• README: You can easily start Weaviate and a local vector embedding model with [Docker](https://docs.docker.com/desktop/). Create a `docker-compose.yml` file:
• README: Install the Python client (or use another [client library](#client-libraries-and-apis)): ```bash pip install -U weaviate-client ```
• README: client = weaviate.connect_to_local()

Reviewed at: 2026-07-17T14:02:31Z