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

Msvbase

MSVBASE is a PostgreSQL-integrated database system for approximate vector similarity search and relational operations over scalar and vector data. It supports vector indexes and query patterns including nearest-neighbour ranking, scalar filtering, distance thresholds, multi-vector scoring and similarity joins.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Msvbase — 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 MSVBASE when an application needs approximate embedding retrieval together with relational filtering or other database operations in PostgreSQL.

Who it is for

  • Developers building retrieval backends that need embedding search alongside structured database filters.
  • Teams operating PostgreSQL-based systems that want vector indexing and similarity queries within the database query workflow.

Documented uses

  • Retrieve the top-K records nearest to a query vector using L2 distance or inner product.
  • Combine vector ranking with scalar conditions such as a price filter.
  • Find records within a distance threshold or score across multiple vector columns.
  • Join records using vector similarity conditions.
Before you choose

Requirements & limits

The repository is public and lists an MIT license. Its README documents a Docker-based, self-hosted quickstart.

  • MSVBASE is database infrastructure that you build and run; it is not presented as a hosted retrieval application.
  • The README documents L2 and inner-product distance calculations and requires choosing an index algorithm and distance method when creating a vector index.
  • The documented vector storage form is a floating-point array.
  • The README identifies HNSW and SPTAG as supported index options and describes further index integrations as planned.

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 and start MSVBASE with Docker

Follow the repository's documented quickstart to build and run the system.

Before you start

  • A local environment with Git and Docker available; the README uses a Docker build and run script.

Steps

  1. Clone https://github.com/microsoft/MSVBASE.git and enter the MSVBASE directory.

  2. Initialize repository submodules with git submodule update --init --recursive.

  3. Run ./scripts/patch.sh.

  4. Run ./scripts/dockerbuild.sh, then ./scripts/dockerrun.sh.

Expected outcome

The documented quickstart builds and starts the MSVBASE Docker environment.

Guide limitations

  • The README does not specify operating-system or Docker-version requirements.
  • This setup sequence does not configure application data or demonstrate a completed query.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Vector search

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
MsvbaseRetrieve the top-K records nearest to a query vector using L2 distance or inner product.Self-hosted, ServerThe repository is public and lists an MIT license. Its README documents a Docker-based, self-hosted quickstart.
MettisIndex text documents through an HTTP endpoint.Linux, Self-hosted, Server
Evidence and transparency

Sources & review

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