
A vector store houses embedded data in vector format and performs similarity searches.

Every vector store can work with different embedding models. The development framework (e.g., LangChain) dictates what vector stores and embedding models you can integrate based on what it supports.
Embedding similarity may be computed using cosine similarity, Euclidean distance or dot product.
Furthermore, vector stores may optimise search using indexing methods, such as HNSW (Hierarchical Navigable Small World), though specifics vary by vector store.
In addition, you can refine search results by filtering by metadata (e.g., source, date).
Vector Indexing
Vector stores house millions of embeddings, each with hundreds to thousands of dimensions. At this scale, comparing a query vector to every vector in the database is neither efficient nor effective. It would be resource-intensive and result in slow queries.
So, vector indexing is a process that uses Approximate Nearest Neighbour (ANN) algorithms to organise data in a way that enables faster search. Instead of finding the exact closest match, ANN algorithms find vectors that are very likely to be among the closest matches.
Several algorithms perform approximate nearest neighbour search. For example:
- The Hierarchical Navigable Small World (HNSW) algorithm creates multi-layered graphs connecting similar vectors.
- The Inverted File (IVF or IVF_FLAT) index divides the vector space into clusters and searches only the most relevant ones. The term “FLAT” indicates that within each cluster, vectors are stored in their original form (flat structure), without any compression or quantisation, for precise distance computations.
- The FLAT index relies on a brute-force approach. It performs a full scan of the dataset for every query, and each query vector is directly compared to every vector in the dataset, without any preprocessing or data structuring. This approach guarantees accuracy as it provides 100% recall. However, it is an exhaustive search method: it is the slowest indexing option, and it consumes many resources.
The HNSW and IVF_FLAT indexing methods trade some accuracy for a large improvement in search speed.
Typical Use Cases
Below, there is a list of examples of what to use vector stores for:
- Semantic text search – Retrieve documents based on meaning rather than exact keywords.
- Recommendation systems – Find items similar to a user’s past interactions.
- Image/ video similarity – Locate visually similar media assets.
- Anomaly detection – Identify outliers whose embeddings lie far from the bulk of the data.
To sum up, a vector store is what makes large-scale, fast similarity search possible for AI-driven apps.
Vector Database, Vector Store, Vector Search Engine
Most authors consider the terms “vector database”, “vector store” and “vector search engine” as synonyms, including Wikipedia.
However, occasionally, some papers distinguish between a vector store and a vector database. According to those authors, the vector store’s task is to keep data in vector format. The vector database, on the other hand, includes the vector store capabilities plus extended functionality, such as database functionality beyond vectors, integration of vector and relational data, complex query support, flexible data models, and advanced indexing and optimisation.

