Aquila DB: Index vectors for nearest-neighbor search

Understand the project

Practical overview

Use Aquila DB when an ML application needs vector-based similarity retrieval and you can supply embeddings from your own deployed models.

Machine-learning engineers building retrieval features into applications.
Data scientists searching collections by vector similarity.
Teams working with images and related metadata that need image-similarity search.

Index latent vectors produced by machine-learning models alongside JSON metadata.
Retrieve nearest neighbors for neural information-retrieval applications.
Find similar images using their feature vectors and associated metadata.

Before you choose

The database indexes vectors and JSON metadata; the README says users currently need to deploy their own models to generate vectors.
The project describes its release as alpha.
Docker instructions require Docker; the README also provides a Debian installation command.
Python and Node.js client libraries are described as in progress, rather than finished SDKs.
The project identifies Aquila Port, its peer-to-peer network layer, as work in progress.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Build a documented Aquila DB Docker image and start its container.

Build the lite image using the repository’s Dockerfile and tag it aquiladb:local, or build the big-data image using DockerfileBig and tag it aquiladb:localbg.
Run the chosen image with port 5001 mapped to port 5001; the README gives separate run commands for the lite and big-data images.

Aquila DB runs in a Docker container with port 5001 exposed on the host.

The project describes itself as alpha, and its Python and Node.js client libraries are listed as in progress.

Evidence and transparency

Source record details

Source availability: Active
Sources checked: 18 October 2026
Original website title: Aquila-Network/aquila · Official homepage title · retained in its source language