Open-source AI-native vector database for semantic, hybrid, and agentic search
Weaviate documents an open-source vector database at docs.weaviate.io/weaviate for storing objects and vector embeddings with semantic, keyword, and hybrid search, RAG, reranking, and agent workflows. The ecosystem includes self-hosted Docker/Kubernetes installs, Weaviate Cloud (console.weaviate.cloud), Query Agent, and Weaviate Embeddings for managed inference. Client libraries include Python (`weaviate-client` v4, requires Weaviate 1.23.7+), TypeScript, Go, and Java with REST, gRPC, and GraphQL APIs per the official documentation.
Use cases
- Production RAG catalogs with hybrid BM25 + vector retrieval
- Recommendation engines and semantic product search at billion-vector scale
- Agent memory and retrieval layers paired with Weaviate MCP tools
- Multi-tenant SaaS apps isolating customer data per tenant
- Migrating from prototype in-memory stores to cloud-native vector infrastructure
Key features
- Vector, keyword, and hybrid search with filtering in one query interface
- Integrated vectorizers for OpenAI, Cohere, HuggingFace, and other model providers
- Multi-tenancy, replication, RBAC, and quantization options for production
- Weaviate Agents (Query, Transformation, Personalization) on Weaviate Cloud
- Built-in MCP server from v1.37.1 at `/v1/mcp` per docs.weaviate.io/weaviate/mcp/mcp-server
Who Is It For?
- ML engineers building semantic search or RAG backends
- Platform teams operating vector databases with RBAC and replication
- Developers evaluating open-source alternatives to single-vendor vector clouds
Frequently Asked Questions
- Is Weaviate only available as a managed cloud?
- No—Weaviate is open source with Docker/Kubernetes self-hosting plus optional Weaviate Cloud.
- Which Python client version should I use?
- Docs recommend weaviate-client v4 (pip install -U weaviate-client) with Weaviate 1.23.7 or higher.
- How do MCP clients connect?
- From v1.37.1, enable MCP_SERVER_ENABLED=true and point clients to the built-in /v1/mcp endpoint.
Related
Related
3 Indexed items
Milvus
Milvus documents a high-performance vector database at milvus.io/docs for storing, indexing, and searching embedding vectors with metadata filtering and hybrid search. Deployment options include Milvus Lite (`pip install pymilvus` for notebooks/edge), Milvus Standalone (single Docker image), and Milvus Distributed on Kubernetes per milvus.io/docs/v2.6.x/install-overview. Official SDKs include PyMilvus, Go, Java, Node.js, and C#; Zilliz Cloud offers managed Milvus. Architecture separates access, coordinator, worker, and storage layers with object storage backends (MinIO, S3, Azure Blob) per milvus.io/docs/architecture_overview.
Pinecone
Pinecone documents a fully managed vector database at docs.pinecone.io for storing, indexing, and querying high-dimensional embeddings at production scale. Serverless indexes support document schemas mixing dense vectors, sparse vectors, and full-text search fields with metadata filtering per docs.pinecone.io/guides/get-started/concepts. Official SDKs include Python, Node.js, Java, and Go; REST API access uses documented rate limits and plan tiers (Starter, Standard, Enterprise). Pinecone also documents Pinecone Assistant, Dedicated Read Nodes, BYOC, and Nexus offerings on pinecone.io alongside MCP integrations (Pinecone MCP Server and Pinecone Docs MCP Server) for agent workflows.
Qdrant
Qdrant documents an AI-native vector search engine at qdrant.tech/documentation for storing, indexing, and querying high-dimensional vectors with optional payloads, supporting dense, sparse, and multi-vector configurations. Official guides cover Docker/Kubernetes self-hosting, Qdrant Cloud on AWS/GCP/Azure, Hybrid Cloud, Private Cloud, and Qdrant Edge for embedded retrieval. Client libraries include Python (`qdrant-client`), JavaScript/TypeScript (`@qdrant/js-client-rest`), Rust, Go, Java, and .NET with REST and gRPC APIs per the API reference at api.qdrant.tech.