pgvector-elixir

pgvector support for Elixir

Supports Ecto and Postgrex

Installation

Add this line to your application’s mix.exs under deps:

{:pgvector, "~> 0.1.0"}

And follow the instructions for your database library:

• Ecto
• Postgrex

Ecto

Create lib/postgrex_types.ex with:

Postgrex.Types.define(MyApp.PostgrexTypes, [Pgvector.Extensions.Vector] ++ Ecto.Adapters.Postgres.extensions(), [])

And add to config/config.exs:

config :my_app, MyApp.Repo, types: MyApp.PostgrexTypes

Create a migration

mix ecto.gen.migration create_vector_extension

with:

defmodule MyApp.Repo.Migrations.CreateVectorExtension do
  use Ecto.Migration

  def up do
    execute "CREATE EXTENSION IF NOT EXISTS vector"
  end

  def down do
    execute "DROP EXTENSION vector"
  end
end

Run the migration

mix ecto.migrate

You can now use the vector type in future migrations

create table(:items) do
  add :factors, :vector, size: 3
end

Update the model

schema "items" do
  field :factors, Pgvector.Ecto.Vector
end

Insert a vector

alias MyApp.{Repo, Item}

Repo.insert(%Item{factors: [1, 2, 3]})

Get the nearest neighbors

import Ecto.Query
import Pgvector.Ecto.Query

Repo.all(from i in Item, order_by: l2_distance(i.factors, [1, 2, 3]), limit: 5)

Also supports max_inner_product and cosine_distance

Add an approximate index in a migration

create index("items", ["factors vector_l2_ops"], using: :ivfflat)

Use vector_ip_ops for inner product and vector_cosine_ops for cosine distance

Postgrex

Register the extension

Postgrex.Types.define(MyApp.PostgrexTypes, [Pgvector.Extensions.Vector], [])

And pass it to start_link

{:ok, pid} = Postgrex.start_link(types: MyApp.PostgrexTypes)

Create a table

Postgrex.query!(pid, "CREATE TABLE items (factors vector(3))", [])

Insert a vector

Postgrex.query!(pid, "INSERT INTO items (factors) VALUES ($1)", [[1, 2, 3]])

Get the nearest neighbors

Postgrex.query!(pid, "SELECT * FROM items ORDER BY factors <-> $1 LIMIT 5", [[1, 2, 3]])

Add an approximate index

Postgrex.query!(pid, "CREATE INDEX my_index ON items USING ivfflat (factors vector_l2_ops)", [])

Use vector_ip_ops for inner product and vector_cosine_ops for cosine distance

History

View the changelog

Contributing

Everyone is encouraged to help improve this project. Here are a few ways you can help:

• Report bugs
• Fix bugs and submit pull requests
• Write, clarify, or fix documentation
• Suggest or add new features

To get started with development:

git clone https://github.com/pgvector/pgvector-elixir.git
cd pgvector-elixir
mix deps.get
createdb pgvector_elixir_test
mix test