For AI agents: The documentation index is at https://docs.digitalocean.com/llms.txt. Markdown versions of pages use the same URL with index.html.md in place of the HTML page (for example, append index.html.md to the directory path instead of opening the HTML document).

How you create your first vector database cluster depends on the engine.

• Weaviate is in private preview and is provisioned through the dedicated Vector Databases API at /v2/vector-databases. The Control Panel and doctl flows are not available during preview. For the end-to-end provisioning walkthrough, see Managed Weaviate.
• OpenSearch and PostgreSQL clusters are created from the DigitalOcean Control Panel, the Managed Databases API, or doctl. The steps below cover the Control Panel flow for these two engines.

To create an OpenSearch or PostgreSQL cluster from the Control Panel, click Data Services in the left menu, then choose Vector Databases. Click Create Database, then choose OpenSearch or PostgreSQL.

1. Pick an engine. Under Supported Vector Database Engines, select one of the following:

   • Weaviate: A dedicated vector database. Use it when vector search is your primary workload, such as retrieval-augmented generation or semantic search. Weaviate is in private preview and uses the API-only flow described above.
   • OpenSearch: A search engine that supports hybrid vector and keyword search. Use it when you need both kinds of search in one query, or when you already run OpenSearch for logging or full-text search.
   • PostgreSQL: A relational database with the pgvector extension. Use it when your data is already in Postgres and vectors are a secondary dataset.

   For a side-by-side comparison, see Choosing Between OpenSearch, Weaviate, and pgvector.

2. Choose a configuration, region, and name. Pick the plan size that matches your expected vector volume, put the cluster in the same region as the application that issues queries, and give the cluster a unique name.

3. Create the cluster. Click Create Vector Database Cluster. Provisioning takes roughly 3 to 5 minutes for smaller plans and up to 15 minutes for larger multi-node plans.

4. Secure the cluster. On the cluster’s Overview tab, add trusted sources (IP addresses, Droplets, App Platform apps, or Kubernetes clusters) under Network Access. Until at least one trusted source is added, the cluster rejects all connections.

5. Run your first vector query. Follow the engine-specific quickstart:

   • Managed Weaviate
   • OpenSearch Vector Search Quickstart
   • PostgreSQL pgvector Quickstart