pgvector support for Python

Overview

pgvector-python

pgvector support for Python

Great for online recommendations 🎉

Supports Django, SQLAlchemy, Psycopg 2, Psycopg 3, and asyncpg

Build Status

Installation

Run:

pip install pgvector

And follow the instructions for your database library:

Or check out some examples:

Django

Create the extension

from pgvector.django import VectorExtension

class Migration(migrations.Migration):
    operations = [
        VectorExtension()
    ]

Add a vector field

from pgvector.django import VectorField

class Item(models.Model):
    factors = VectorField(dimensions=3)

Insert a vector

item = Item(factors=[1, 2, 3])
item.save()

Get the nearest neighbors to a vector

from pgvector.django import L2Distance

Item.objects.order_by(L2Distance('factors', [3, 1, 2]))[:5]

Also supports MaxInnerProduct and CosineDistance

Add an approximate index

from pgvector.django import IvfflatIndex

class Item(models.Model):
    class Meta:
        indexes = [
            IvfflatIndex(
                name='my_index',
                fields=['factors'],
                lists=100,
                opclasses=['vector_l2_ops']
            )
        ]

Use vector_ip_ops for inner product and vector_cosine_ops for cosine distance

SQLAlchemy

Add a vector column

from pgvector.sqlalchemy import Vector

class Item(Base):
    factors = Column(Vector(3))

Insert a vector

item = Item(factors=[1, 2, 3])
session.add(item)
session.commit()

Get the nearest neighbors to a vector

session.query(Item).order_by(Item.factors.l2_distance([3, 1, 2])).limit(5).all()

Also supports max_inner_product and cosine_distance

Add an approximate index

index = Index('my_index', Item.factors,
    postgresql_using='ivfflat',
    postgresql_with={'lists': 100},
    postgresql_ops={'factors': 'vector_l2_ops'}
)
index.create(engine)

Use vector_ip_ops for inner product and vector_cosine_ops for cosine distance

Psycopg 2

Register the vector type with your connection or cursor

from pgvector.psycopg2 import register_vector

register_vector(conn)

Insert a vector

factors = np.array([1, 2, 3])
cur.execute('INSERT INTO item (factors) VALUES (%s)', (factors,))

Get the nearest neighbors to a vector

cur.execute('SELECT * FROM item ORDER BY factors <-> %s LIMIT 5', (factors,))
cur.fetchall()

Psycopg 3

Register the vector type with your connection or cursor

from pgvector.psycopg3 import register_vector

register_vector(conn)

Insert a vector

factors = np.array([1, 2, 3])
cur.execute('INSERT INTO item (factors) VALUES (%s)', (factors,))

Get the nearest neighbors to a vector

cur.execute('SELECT * FROM item ORDER BY factors <-> %s LIMIT 5', (factors,)).fetchall()

asyncpg

Register the vector type with your connection

from pgvector.asyncpg import register_vector

await register_vector(conn)

Insert a vector

factors = np.array([1, 2, 3])
await conn.execute('INSERT INTO item (factors) VALUES ($1)', factors)

Get the nearest neighbors to a vector

await conn.fetch('SELECT * FROM item ORDER BY factors <-> $1 LIMIT 5', factors)

History

View the changelog

Contributing

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

To get started with development:

git clone https://github.com/ankane/pgvector-python.git
cd pgvector-python
pip install -r requirements.txt
pytest
Owner
Andrew Kane
Andrew Kane
Automatically load and dump your dataclasses 📂🙋

file dataclasses Installation By default, filedataclasses comes with support for JSON files only. To support other formats like YAML and TOML, filedat

Alon 1 Dec 30, 2021
A demo of a data science project using Kedro

iris Overview This is your new Kedro project, which was generated using Kedro 0.17.4. Take a look at the Kedro documentation to get started. Rules and

Khuyen Tran 14 Oct 14, 2022
Grail(TM) is a web browser written in Python

Grail is distributed in source form. It requires that you have a Python interpreter and a Tcl/Tk installation, with the Python interpreter configured for Tcl/Tk support.

22 Oct 18, 2022
Parametric Bottle in CADQuery

Parametric Bottle using CADQuery The proposed code makes it possible to generate different types and sizes of 3D bottles in order to train Pixel2mesh

Ayoub EL HOUDRI 1 May 22, 2022
A new mini-batch framework for optimal transport in deep generative models, deep domain adaptation, approximate Bayesian computation, color transfer, and gradient flow.

BoMb-OT Python3 implementation of the papers On Transportation of Mini-batches: A Hierarchical Approach and Improving Mini-batch Optimal Transport via

Khai Ba Nguyen 18 Nov 14, 2022
An extremely configurable markdown reverser for Python3.

🔄 Unmarkd A markdown reverser. Unmarkd is a BeautifulSoup-powered Markdown reverser written in Python and for Python. Why This is created as a StackS

ThatXliner 5 Jun 27, 2022
Euler 021 Py - Euler Problem 021 solved in Python

Euler_021_Py Euler Problem 021 solved in Python Let d(n) be defined as the sum o

Ariel Tynan 1 Jan 24, 2022
Python Classes Without Boilerplate

attrs is the Python package that will bring back the joy of writing classes by relieving you from the drudgery of implementing object protocols (aka d

The attrs Cabal 4.6k Jan 02, 2023
MIB2 STD ZR Firmware Upgrade

Upgrade MIB2 STD ZR Firmware (without Navigation) About This repository contains some scripts and documentation how to upgrade the MIB2 firmware to a

Fabian 18 Dec 29, 2022
A site that went kinda viral that lets you put Bernie Sanders in places

Bernie In Places An app that accidentally went viral! Read the story in WIRED here Install First, create a python virtual environment, and install all

310 Aug 22, 2022
Object-oriented programming exercise session held in Petnica.

OOP vežba ⚠️ The code in this repo is used for a OOP practice session held in Petnica. All instructions in the README file are written in Serbian. Ops

Pavle Ćirić 1 Jan 30, 2022
This is a Saleae Logic custom high level analyzer that allows you to search and mark specific packets.

SaleaePacketParser This is a Saleae Logic custom high level analyzer that allows you to search and mark specific packets. Field "Search For" is used f

1 Dec 16, 2021
IDA Pro plugin that shows the comments in a database

ShowComments A Simple IDA Pro plugin that shows the comments in a database Installation Copy the file showcomments.py to the plugins folder under IDA

Fernando Mercês 32 Dec 10, 2022
Sentiment Based Product Recommendation System

Sentiment Based Product Recommendation System The e-commerce business is quite p

Sumit Sahay 2 Jan 15, 2022
Pardus-flatpak-gui - A Flatpak GUI for Pardus

Pardus Flatpak GUI A GUI for Flatpak. You can run, install (from FlatHub and fro

Erdem Ersoy 2 Feb 17, 2022
High-level bindings to the Valhalla framework.

Valhalla for Python This spin-off project simply offers improved Python bindings to the fantastic Valhalla project. Installation pip install valhalla

GIS • OPS 20 Dec 13, 2022
An upgraded version of extractJS

extractJS_2.0 An enhanced version of extractJS with even more functionality Features Discover JavaScript files directly from the webpage Customizable

Ali 4 Dec 21, 2022
The next generation Canto RSS daemon

Canto Daemon This is the RSS backend for Canto clients. Canto-curses is the default client at: http://github.com/themoken/canto-curses Requirements De

Jack Miller 155 Dec 28, 2022
A small project of two newbies, who wanted to learn something about Python language programming, via fun way.

HaveFun A small project of two newbies, who wanted to learn something about Python language programming, via fun way. What's this project about? Well.

Patryk Sobczak 2 Nov 24, 2021
People tracker on the Internet: OSINT analysis and research tool by Jose Pino

trape (stable) v2.0 People tracker on the Internet: Learn to track the world, to avoid being traced. Trape is an OSINT analysis and research tool, whi

Jose Pino 7.3k Dec 30, 2022