Skip to main content
New to vector databases? Vector databases store numerical representations of your data called embeddings, and find results by similarity rather than exact keyword matching. Use one when meaning matters more than exact text: semantic search, RAG pipelines, agent memory.

Architecture

VectorAI DB runs as a single Docker container with no external dependencies. Data is persisted to a volume-mounted directory on the host.
PortProtocolPurpose
6573HTTPREST API
6574gRPCgRPC API (recommended for SDKs)
6575HTTPLocal UI
The Python and JavaScript SDKs communicate over gRPC by default.

Data model

ConceptWhat it is
CollectionsNamed containers for vectors, similar to tables in a relational database. Each collection has a fixed vector dimension and distance metric set at creation time.
PointsThe unit of data in a collection. Each point has a unique ID, a vector embedding, and an optional JSON payload.
VectorsFixed-length arrays of floats that represent your data semantically. Generated by embedding models from text, images, or other content.
PayloadJSON metadata attached to a point. Use payloads to store context and to filter search results.
Distance metricsThe function used to measure similarity between vectors. Supported metrics: Cosine, Euclidean, and Dot Product.

How a search works

1

Generate an embedding

Your application converts a query (text, image, or other data) into a vector using an embedding model.
2

Send a search request

The vector is sent to VectorAI DB over gRPC or REST.
3

HNSW nearest-neighbour search

VectorAI DB traverses the HNSW index to find the closest vectors, applying any payload filters inline.
4

Ranked results returned

Results come back with IDs, similarity scores, and optional payloads. No post-processing needed.
You can build on this foundation with:

Next steps

Installation

Install VectorAI DB with Docker.

Quickstart

Create a collection, insert vectors, and run a search.

Fundamentals

Collections, points, vectors, search, and filtering.

Academy

Hands-on tutorials for semantic search, RAG, and more.