Vectra is an advanced, unified Ruby client designed to facilitate seamless interactions with various vector databases. This library allows for a single codebase, enabling developers to effortlessly switch between different database providers with minimal changes.

Key Features

• Provider Agnostic: Easily shift between different vector database providers with just a single line of code change.
• Production Ready: Compatible with Ruby 3.2+ and boasts over 95% test coverage to ensure reliability.
• Resilient: Implements retry logic with exponential backoff to handle transient errors effectively.
• Observable: Comes with built-in instrumentation for Datadog and New Relic, aiding in performance monitoring and troubleshooting.
• Rails Ready: Integrates smoothly with Ruby on Rails, offering ActiveRecord support through a simple and intuitive DSL.

Supported Providers

Vectra currently supports the following vector database providers:

Quick Start

To use Vectra, simply initialize the client with the desired provider and API key:

require 'vectra'

client = Vectra::Client.new(
  provider: :pinecone,
  api_key: ENV['PINECONE_API_KEY'],
  environment: 'us-west-4'
)

You can then perform operations like inserting, querying, and deleting vectors:

# Upsert vectors
client.upsert(
  vectors: [
    { id: 'doc-1', values: [0.1, 0.2, 0.3], metadata: { title: 'Hello' } },
    { id: 'doc-2', values: [0.4, 0.5, 0.6], metadata: { title: 'World' } }
  ]
)

# Search vectors
results = client.query(vector: [0.1, 0.2, 0.3], top_k: 5)
results.each { |match| puts "#{match.id}: #{match.score}" }

# Delete vectors
client.delete(ids: ['doc-1', 'doc-2'])

Rails Integration

For Ruby on Rails applications, integrate with ActiveRecord for easy embedding management:

class Document < ApplicationRecord
  include Vectra::ActiveRecord

  has_vector :embedding,
    provider: :qdrant,
    index: 'documents',
    dimension: 1536
end

# Auto-indexing on save
Document.create!(title: 'Hello', embedding: [0.1, 0.2, ...])

# Vector search
Document.vector_search(embedding: query_vector, limit: 10)

For comprehensive documentation, refer to the official documentation site. Vectra streamlines interaction with vector databases, enhancing productivity and maintaining flexibility in application development.