DigitalOcean Managed OpenSearch for Vector Search
Generated on 13 Jul 2026
DigitalOcean Managed OpenSearch for vector search uses the same managed OpenSearch engine available under Managed Databases. It bundles the k-NN, ML Commons, and Neural Search plugins for vector similarity search, hybrid vector and keyword search, and remote embedding models.
Quickstart guides for using DigitalOcean Managed OpenSearch as a vector database.
How to create OpenSearch vector clusters, build k-NN indexes, run hybrid searches, and register remote embedding models.
Background reading on vector embeddings, HNSW, engines, hybrid search, and where embeddings come from, specific to DigitalOcean Managed OpenSearch.
DigitalOcean Managed OpenSearch for vector search is the same managed OpenSearch engine available under Managed Databases, with built-in support for vector workloads.
OpenSearch 2.19 includes the k-NN, ML Commons, and Neural Search plugins, so you can create vector indexes, run hybrid search, and connect to remote embedding models.
When to Choose OpenSearch
Choose OpenSearch for vector workloads when you need:
- Hybrid search: Combine BM25 keyword scoring with vector similarity, score normalization, and per-query weighting.
- Server-side embeddings: Use ML Commons connectors to call remote embedding providers during ingestion or query workflows.
- Search-first workflows: Store vectors alongside full-text fields in a search engine designed for ranking, filtering, and retrieval.
- Existing OpenSearch workloads: Reuse the same cluster if you already use OpenSearch for logs, metrics, traces, or search.
For pure vector-native workloads, consider Weaviate. For smaller vector datasets stored with relational data, consider PostgreSQL with pgvector.
What Is Included
OpenSearch vector databases include the following capabilities:
- k-NN plugin: Supports HNSW vector indexes.
- Faiss and Lucene engines: Supported for new vector workloads.
- NMSLIB engine: Supported for compatibility, but deprecated upstream.
- Hybrid search: Supported with compound queries and normalization pipelines.
- ML Commons and Neural Search: Included by default.
- Remote model connectors: Supported for providers such as OpenAI, Bedrock, Cohere, SageMaker, Voyage, and custom HTTP endpoints.
- Local in-cluster ML models: Not supported on Basic or General Purpose plans.
Use Existing OpenSearch Clusters
OpenSearch clusters created through Vector Databases and Managed Databases use the same managed OpenSearch engine. If you already have a compatible Managed OpenSearch cluster, enable vector search by creating an index with index.knn enabled and a knn_vector field.
Latest Updates
28 April 2026
-
DigitalOcean Vector Databases is now generally available in Data Services that groups managed engines for vector similarity search. The launch includes:
- Weaviate in private preview for retrieval-augmented generation and semantic search workloads. Available to opted-in customers; preview clusters are not billed.
- OpenSearch with the k-NN, ML Commons, and Neural Search plugins for hybrid (vector plus keyword) search and remote embedding models. Uses the existing Managed Databases OpenSearch engine.
- PostgreSQL with the
vector(pgvector) andvectorscale(pgvectorscale) extensions for vector similarity search alongside relational data.
For an overview and guidance on choosing an engine, see Vector Databases.
17 September 2025
-
Now in public preview, you can now enable storage autoscaling on all Managed Database engines. To enable autoscaling, see our resizing guides for MySQL, PostgreSQL, MongoDB, OpenSearch, and Kafka.
-
Storage autoscaling is now in general availability. Additionally, you can now reduce your cluster’s amount of additional storage, as long as the new storage size is greater than or equal to the latest backup’s size plus any data growth since then and a 25% buffer.
16 May 2025
-
New managed database clusters are now automatically provisioned with default alert policies for CPU, memory, and disk utilization at a 90% threshold. These alerts notify you via email when resource usage is high, so you can investigate your application load or scale your cluster. You can modify or remove the default alerts at any time. For more information, see the following:
For more information, see the full release notes.