Vector databases
Stores for embeddings that power semantic search and retrieval-augmented AI (pgvector and dedicated engines).
Where we use it
- Semantic search
- RAG assistants
- Recommendations
Strengths
- Similarity search
Considerations
Trade-offs worth knowing before you choose it.
- Index tuning and embedding model choice affect quality
Vector databases is a trademark of its owner. Listing it describes work we offer and does not imply a partnership or certification.
Services that use Vector databases
AI and machine learning
Classical machine learning, forecasting, classification, recommendation and computer vision — from feasibility to monitored production models.
Generative AI
LLM-powered features: retrieval-augmented assistants, content drafting, summarisation and search over your documents with evaluation and guardrails.
More in databases and storage
- PG
PostgreSQL
A powerful open-source relational database with row-level security, JSONB and rich indexing.
- My
MySQL
The widely deployed open-source relational database.
- Ma
MariaDB
A community-developed MySQL-compatible database.
- MS
Microsoft SQL Server
Microsoft's enterprise relational database.
- Mo
MongoDB
A document database for flexible, evolving data structures.
- Rd
Redis
An in-memory data store for caching, rate limiting, queues and real-time data.
- SL
SQLite
An embedded SQL database in a single file.
- ES
Elasticsearch / OpenSearch
Full-text search and analytics engines.
Have a Vector databases project in mind?
New build, rescue or modernisation — share what you have and where you want to get to.