Meilisearch
A self-hosted search engine combines keyword and semantic search, with vector storage for RAG and integrations for LangChain and MCP.
Meilisearch is a search engine for developers adding search and AI retrieval to websites, apps, catalogs or internal data. You can host the engine on your own server or use the separate managed Meilisearch Cloud service.
- Hybrid search: Combine keyword matches with semantic relevance, with typo tolerance and synonyms to handle imperfect queries.
- Search interfaces: Show results as people type, then let them narrow matches with filters, facets, sorting or geographic criteria.
- Vector and media retrieval: Store vectors for similarity search and retrieval-augmented generation (RAG), and search images, video and audio through embeddings.
- Connected AI search: Query multiple data sources together, produce conversational answers grounded in results, and connect retrieval to LangChain or MCP tools.
- Access controls: Use granular API permissions and tenant-specific results to serve separate customer groups.
A REST API and SDKs including JavaScript, Python and Swift connect the engine to applications. Meilisearch Cloud adds managed hosting, analytics and monitoring. Enterprise code uses a commercial license or Business Source License 1.1 and requires a commercial agreement for production use. The engine collects anonymized telemetry, which you can disable.
