OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
RAG & Knowledge Systems

Neurondb

NeuronDB is a PostgreSQL extension for vector similarity and k-nearest-neighbor search, embeddings, machine-learning operations in SQL, and hybrid full-text and vector retrieval.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Neurondb — OpenViST project profile in RAG & Knowledge Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use NeuronDB when an application already relies on PostgreSQL and needs vector or hybrid retrieval, or when database-oriented machine-learning operations are part of the workflow.

Who it is for

  • Teams building PostgreSQL-backed knowledge retrieval or RAG systems.
  • Developers who want vector and full-text retrieval alongside PostgreSQL data.
  • Database teams exploring SQL-based embedding and machine-learning workflows.

Documented uses

  • Index embeddings with HNSW or IVF for similarity retrieval.
  • Query nearest neighbors using vector distance metrics.
  • Combine full-text and vector retrieval in SQL.
  • Run documented embedding, inference and machine-learning workflows in the database.
Before you choose

Requirements & limits

  • The README states support for PostgreSQL 16, 17 and 18.
  • The project is a PostgreSQL extension, so its use involves a PostgreSQL environment rather than a standalone search app.
  • The repository labels its license proprietary; public repository visibility does not indicate open-source licensing.

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

Start NeuronDB with Docker Compose

Start the repository's NeuronDB service and create the PostgreSQL extension.

Before you start

  • The NeuronDB repository and its Docker Compose configuration.
  • A PostgreSQL version supported by the project: 16, 17 or 18.

Steps

  1. From the repository root, run the command below.

    Documented command
    docker compose -f docker/docker-compose.yml up -d neurondb

  2. Check the command below and wait until the service is healthy.

    Documented command
    docker compose -f docker/docker-compose.yml ps

  3. Run the command below.

    Documented command
    docker compose -f docker/docker-compose.yml exec neurondb psql -U neurondb -d neurondb -c "CREATE EXTENSION IF NOT EXISTS neurondb; SELECT neurondb.version();"

Expected outcome

The service is started, the extension is created in the configured database, and its version is queried.

Guide limitations

  • The README directs readers to the Simple Start or Quick Start guide for the next stage of running a vector search.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
18 October 2026
Original website title
neurondb/neurondb · Official homepage title · retained in its source language
How we review sourcesSuggest a correction