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

Vecstore

VecStore is an embeddable vector database library written in Rust. It stores vectors with metadata, supports similarity queries and metadata filtering, and can persist and reopen a local store. The repository also describes optional Python and WebAssembly interfaces.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Vecstore — 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 VecStore when you want to evaluate embedded vector storage, similarity search, metadata filtering, and local persistence as application infrastructure. The fixed-vector quick start is a scoped first look; integrating generated embeddings or optional components requires additional work.

Who it is for

  • Rust developers adding vector storage and similarity retrieval to an application.
  • Developers evaluating local semantic retrieval with persisted vectors.
  • Python or WebAssembly developers exploring the repository’s optional interfaces.

Documented uses

  • Store vectors alongside metadata within an application.
  • Find similar records and narrow retrieval with metadata filters.
  • Save and reopen a local vector store.
  • Explore a hybrid retrieval example or optional Python and WebAssembly interfaces.
Before you choose

Requirements & limits

The repository is public and identifies the project as MIT-licensed open source. The README specifies Rust 1.92 or later for its quick start.

  • Alpha status: APIs and file formats may change, so the README advises keeping evaluation data regenerable.
  • The quick start uses fixed vectors and does not require a model, service, or API key, but does not cover embedding generation.
  • Optional GPU, server, embedding, and distributed components have separate dependencies and validation needs.
  • Benchmark results should include workload, recall, hardware, and latency details; the repository makes no universal latency claim.

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

Run the fixed-vector quick start

Use the repository example to insert records, search with metadata filters, and save and reopen a temporary store.

Before you start

  • Rust 1.92 or later
  • A fresh checkout of the public repository

Steps

  1. Clone the repository with git clone https://github.com/PhilipJohnBasile/vecstore.git.

  2. Change into the vecstore directory.

  3. Run cargo run --locked --example quickstart.

Expected outcome

The example creates a temporary database, inserts three fixed-vector records, searches with metadata filters, then saves and reopens the store. It reports Store reloaded, count: 3.

Guide limitations

  • This example uses fixed vectors and does not demonstrate generating embeddings.
  • The project is alpha; APIs and file formats may change. The README recommends regenerable data during evaluation.
Documentation 1 ↗
Evidence and transparency

Sources & review

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