OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Developer Tools & SDKs

Vectra

Vectra is an MIT-licensed Ruby client library that gives applications a shared interface for storing and searching vectors in Pinecone, Qdrant, Weaviate and pgvector. It includes direct Ruby calls and a documented Rails ActiveRecord integration.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Vectra — OpenViST project profile in AI Developer Tools & SDKs.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Vectra when a Ruby or Rails application needs vector storage or retrieval through one of its listed providers, particularly when a shared client interface or Rails model integration is useful.

Who it is for

  • Ruby developers adding vector storage and retrieval to an application.
  • Rails developers who want model-level vector declarations and search.
  • Teams evaluating a shared client interface across supported vector database providers.

Documented uses

  • Upsert vectors with IDs and metadata, then query for the closest matches.
  • Use hybrid semantic-and-keyword search on the providers listed as supporting it.
  • Add vector fields and model-level search to a Rails ActiveRecord model.
  • Keep application calls behind a common client interface when selecting among supported providers.
Before you choose

Requirements & limits

The project is published as an MIT-licensed Ruby library. The README lists Ruby 3.2 or later.

  • Provider coverage includes Pinecone, Qdrant, Weaviate and pgvector; Memory is identified as testing-only.
  • Hybrid search is listed for all four database providers, while text-only search is listed for Qdrant, Weaviate and pgvector.
  • The README's Rails integration supports a has_vector declaration and model-level search; its generator creates a pgvector migration only when that provider is selected.
  • Vectra provides the client interface, while vector values and the database connection come from the application's embedding workflow and selected provider.

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

Add vector storage and querying to a Ruby app

Install the Vectra gem, connect a client to a provider, and use the README's example calls to store and query vectors.

Before you start

  • A Ruby application; the README lists Ruby 3.2 or later.
  • A supported provider: Pinecone, Qdrant, Weaviate or pgvector.
  • The provider connection details required for the selected backend.
  • Vector values supplied by the application.

Steps

  1. Add gem 'vectra-client' to the Gemfile and run bundle install.

  2. Require vectra and initialize Vectra::Client with the selected provider and its connection details.

  3. Use client.upsert with vector IDs, values and optional metadata.

  4. Call client.query with a vector and top_k to retrieve matches.

Expected outcome

The Ruby application has a documented client path for storing vectors and requesting the top matching results from its chosen provider.

Guide limitations

  • Provider-specific connection settings vary; the README shows examples for each backend.
  • The README marks Memory as testing-only.
  • The application must obtain or create vector values; Vectra is the client layer, not an embedding model.
Documentation 1 ↗
Evidence and transparency

Sources & review

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