Elasticsearch Vector Database project overview
The Elasticsearch Vector Database Serverless project type is optimized for vector workloads. Compared with the general-purpose Elasticsearch project type, it uses a vector-tuned default configuration, a hardware profile suited to embeddings, streamlined access to inference, and a pricing model built for vector storage and search.
Vector search uses the same query APIs in both project types.
Use it when embeddings and similarity search are central to your application, for example RAG, recommendations, semantic search, hybrid search, or multimodal search.
A Vector Database project gives you Elastic Cloud Serverless operations with defaults and project settings aimed at embedding storage, inference, and similarity or hybrid search.
Indices in a Vector Database project use the index.mode: vectordb_document vector index mode automatically. It applies storage, indexing, and merge defaults tuned for similarity search on dense vectors, so you get efficient embedding storage and approximate kNN search without configuring each setting yourself. The project hardware profile is also tuned for vector workloads.
On other deployment types, you can set the vector index mode explicitly when you create an index.
The Vector Database project type favors workloads where you ingest and embed data, then serve similarity or hybrid queries repeatedly. Aggressive segment merging improves recall and query speed for relatively stable corpora, which is a common pattern for knowledge bases, product catalogs with semantic search, and RAG document stores.
Vector Database projects are set up for embedding workflows: generate vectors in Elasticsearch with managed models (for example through semantic_text), or store vectors you create yourself and attach the same model at query time. In-product setup guides walk through both paths.
Similar to other Elastic Cloud Serverless projects, Elastic manages the infrastructure, scaling, and upgrades. You create a project, get an endpoint, and start indexing and querying without sizing nodes for vector RAM yourself.
Billing uses storage, search, ingest, and infrastructure, rather than the compute-based VCU model used by Elasticsearch Serverless projects. Refer to Elasticsearch Vector Database billing dimensions for details.
Both the Elasticsearch Vector Database and the Elasticsearch project types support vector search.
Choose Vector Database when embeddings and similarity search are central to the workload. For those projects, generate embeddings with managed models through the Elastic Inference Service or a third-party inference endpoint; you can't deploy custom ML models for in-cluster inference.
Choose the Elasticsearch project type when you need general-purpose data storage and search, including mixed lexical, time series, and analytics workloads, Kibana search tooling such as Query Rules UI and Agent Builder, or the ability to run custom models on ML nodes. You might also prefer the Elasticsearch project type if you are an existing Elasticsearch or OpenSearch user.
| Use case | Fit | Why |
|---|---|---|
| RAG and question answering | Strong | Retrieve passages from documents, wikis, tickets, or knowledge bases and pass them to an LLM. Hybrid search combines semantic similarity with keyword matching when queries mix natural language with exact terms, IDs, or product names |
| Discovery and recommendations | Strong | Find related products, articles, or other items by similarity when keywords alone are not enough. Use hybrid ranking when you also need lexical or attribute matches in the same result set |
| Multimodal search | Strong | Search across images, audio, video, or text with embeddings from a multimodal model |
| Duplicate detection, fraud, and anomaly detection | Strong | Compare embeddings to find near-duplicates, suspicious matches, or unusual patterns at scale |
| Long-term memory for LLMs | Strong | Store facts, chat turns, or summaries so an assistant can retrieve relevant past context by meaning, optionally combined with keyword filters on metadata |
| Full-text or keyword search without vectors | Prefer the Elasticsearch project | General-purpose defaults suit lexical search, filters, and document-centric analytics |
| Log, event, or other time series search | Prefer the Elasticsearch project | General-purpose defaults suit write-heavy, frequently updated time series data |
Vector Database projects use vector index mode only. Time series (tsdb) and LogsDB index modes are not supported; use the Elasticsearch project type for those workloads. Data streams are supported when their backing indices use vector index mode.
Ready to try the Vector Database project type? Follow Get started to create a project, ingest embeddings, and run your first searches.