Open-source search engine with vector, semantic, and hybrid retrieval
Typesense documents an open-source search engine at typesense.org/docs for fast typo-tolerant keyword search, faceting, and vector retrieval. Vector search docs at typesense.org/docs/30.2/api/vector-search describe KNN search on imported embeddings or auto-generated embeddings via OpenAI, Google PaLM API, or built-in Hugging Face models in huggingface.co/typesense/models (use the `ts` namespace prefix). Features include semantic search, hybrid search with rank fusion and adjustable `alpha` weighting, similar-document queries by ID, HNSW approximate search with optional `flat_search_cutoff` brute-force mode, and cosine `vector_distance` scoring. Deploy via Typesense Cloud or self-hosted Docker/binaries with REST API and official client libraries.
Use cases
- E-commerce site search with semantic product discovery
- RAG catalogs combining keyword filters and embedding similarity
- Similar-item recommendations via document-ID vector queries
- Notebook-to-production search without separate vector DB
- Agent retrieval prototypes paired with community Typesense MCP servers
Key features
- KNN vector search with imported or auto-generated embeddings
- Hybrid keyword + semantic search via vector_query and alpha weighting
- Built-in ts/* Hugging Face models and remote OpenAI/PaLM embedders
- Typo-tolerant full-text search, faceting, and geo filters
- Self-hosted or Typesense Cloud with multi_search POST API
Who Is It For?
- Developers wanting one engine for keyword and vector search
- Teams self-hosting search before moving to Typesense Cloud
- ML engineers evaluating hybrid rank fusion for RAG quality
Frequently Asked Questions
- Is Typesense only a vector database?
- No—Typesense is a full search engine; vector/semantic/hybrid search extends its core keyword capabilities per typesense.org/docs.
- How are embeddings generated?
- Import your own vectors or enable auto-embedding via OpenAI, PaLM API, or built-in ts/* models documented in vector-search guides.
- Is there an official Typesense MCP?
- Typesense does not document a first-party MCP server; community implementations exist on GitHub for MCP clients.
Related
Related
3 Indexed items
Meilisearch
Meilisearch documents an open-source search engine at meilisearch.com/docs for fast, typo-tolerant full-text search, faceting, filtering, and sorting. Meilisearch Cloud offers hosted deployment; self-hosted options include Docker and native binaries with REST API and official SDKs (JavaScript, Python, Rust, PHP, Java, .NET, Dart, Go). Recent docs and blog posts describe semantic and hybrid search capabilities, AI-powered search experiences, and the official meilisearch-mcp server for LLM clients. Meilisearch positions itself as a developer-friendly alternative focused on sub-50ms search experiences with simple index/document APIs.
Weaviate
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.
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.