01
Where this one gets misread
The vector store is one component and rarely the one deciding quality. Chunking, the embedding model and any reranking usually matter more, so a comparison fought on database choice is often the wrong argument.
Glossary
What is a vector database?
A vector database is built to store and search vectors such as embeddings. It is one component of a retrieval architecture rather than the whole of one.
By Marella AI · Updated 21 Aug 2026
02
Questions to ask
Ask for a worked example on your own material, and the evidence needed to reproduce it.
- What does this store add over the alternatives, for your case?
- How does it handle updates and deletions?
- What does a re-index cost in time and money?
- How are permissions applied to vectors?
03
How Marella uses the term
We use “Vector database” only where a product mechanism or an evaluation method backs it up, and we say when the behaviour depends on how a deployment is configured.
- Backed by a product mechanism or an evaluation method
- Deployment differences flagged
Caveats
- B1A definition is not a claim about how the product performs.
- B2Vendor implementations vary.
- B3Test the term against a representative workflow.
Related pages
Test it on your own documents
Pick a real piece of work, agree what a good answer looks like, then go through the results together.