pgvector support for Python
pgvector support for Python
Supports Django, SQLAlchemy, SQLModel, Psycopg 3, Psycopg 2, asyncpg, and Peewee
Run:
pip install pgvector
And follow the instructions for your database library:
Or check out some examples:
Create a migration to enable the extension
from pgvector.django import VectorExtension
class Migration(migrations.Migration):
operations = [
VectorExtension()
]
Add a vector field to your model
from pgvector.django import VectorField
class Item(models.Model):
embedding = VectorField(dimensions=3)
Insert a vector
item = Item(embedding=[1, 2, 3])
item.save()
Get the nearest neighbors to a vector
from pgvector.django import L2Distance
Item.objects.order_by(L2Distance('embedding', [3, 1, 2]))[:5]
Also supports MaxInnerProduct
and CosineDistance
Get the distance
Item.objects.annotate(distance=L2Distance('embedding', [3, 1, 2]))
Get items within a certain distance
Item.objects.alias(distance=L2Distance('embedding', [3, 1, 2])).filter(distance__lt=5)
Average vectors
from django.db.models import Avg
Item.objects.aggregate(Avg('embedding'))
Also supports Sum
Add an approximate index
from pgvector.django import IvfflatIndex, HnswIndex
class Item(models.Model):
class Meta:
indexes = [
IvfflatIndex(
name='my_index',
fields=['embedding'],
lists=100,
opclasses=['vector_l2_ops']
),
# or
HnswIndex(
name='my_index',
fields=['embedding'],
m=16,
ef_construction=64,
opclasses=['vector_l2_ops']
)
]
Use vector_ip_ops
for inner product and vector_cosine_ops
for cosine distance
Enable the extension
session.execute(text('CREATE EXTENSION IF NOT EXISTS vector'))
Add a vector column
from pgvector.sqlalchemy import Vector
class Item(Base):
embedding = mapped_column(Vector(3))
Insert a vector
item = Item(embedding=[1, 2, 3])
session.add(item)
session.commit()
Get the nearest neighbors to a vector
session.scalars(select(Item).order_by(Item.embedding.l2_distance([3, 1, 2])).limit(5))
Also supports max_inner_product
and cosine_distance
Get the distance
session.scalars(select(Item.embedding.l2_distance([3, 1, 2])))
Get items within a certain distance
session.scalars(select(Item).filter(Item.embedding.l2_distance([3, 1, 2]) < 5))
Average vectors
from sqlalchemy.sql import func
session.scalars(select(func.avg(Item.embedding))).first()
Also supports sum
Add an approximate index
index = Index('my_index', Item.embedding,
postgresql_using='ivfflat',
postgresql_with={'lists': 100},
postgresql_ops={'embedding': 'vector_l2_ops'}
)
# or
index = Index('my_index', Item.embedding,
postgresql_using='hnsw',
postgresql_with={'m': 16, 'ef_construction': 64},
postgresql_ops={'embedding': 'vector_l2_ops'}
)
index.create(engine)
Use vector_ip_ops
for inner product and vector_cosine_ops
for cosine distance
Enable the extension
session.exec(text('CREATE EXTENSION IF NOT EXISTS vector'))
Add a vector column
from pgvector.sqlalchemy import Vector
from sqlalchemy import Column
class Item(SQLModel, table=True):
embedding: List[float] = Field(sa_column=Column(Vector(3)))
Insert a vector
item = Item(embedding=[1, 2, 3])
session.add(item)
session.commit()
Get the nearest neighbors to a vector
session.exec(select(Item).order_by(Item.embedding.l2_distance([3, 1, 2])).limit(5))
Also supports max_inner_product
and cosine_distance
Enable the extension
conn.execute('CREATE EXTENSION IF NOT EXISTS vector')
Register the vector type with your connection
from pgvector.psycopg import register_vector
register_vector(conn)
For async connections, use
from pgvector.psycopg import register_vector_async
await register_vector_async(conn)
Create a table
conn.execute('CREATE TABLE items (id bigserial PRIMARY KEY, embedding vector(3))')
Insert a vector
embedding = np.array([1, 2, 3])
conn.execute('INSERT INTO items (embedding) VALUES (%s)', (embedding,))
Get the nearest neighbors to a vector
conn.execute('SELECT * FROM items ORDER BY embedding <-> %s LIMIT 5', (embedding,)).fetchall()
Enable the extension
cur = conn.cursor()
cur.execute('CREATE EXTENSION IF NOT EXISTS vector')
Register the vector type with your connection or cursor
from pgvector.psycopg2 import register_vector
register_vector(conn)
Create a table
cur.execute('CREATE TABLE items (id bigserial PRIMARY KEY, embedding vector(3))')
Insert a vector
embedding = np.array([1, 2, 3])
cur.execute('INSERT INTO items (embedding) VALUES (%s)', (embedding,))
Get the nearest neighbors to a vector
cur.execute('SELECT * FROM items ORDER BY embedding <-> %s LIMIT 5', (embedding,))
cur.fetchall()
Enable the extension
await conn.execute('CREATE EXTENSION IF NOT EXISTS vector')
Register the vector type with your connection
from pgvector.asyncpg import register_vector
await register_vector(conn)
or your pool
async def init(conn):
await register_vector(conn)
pool = await asyncpg.create_pool(..., init=init)
Create a table
await conn.execute('CREATE TABLE items (id bigserial PRIMARY KEY, embedding vector(3))')
Insert a vector
embedding = np.array([1, 2, 3])
await conn.execute('INSERT INTO items (embedding) VALUES ($1)', embedding)
Get the nearest neighbors to a vector
await conn.fetch('SELECT * FROM items ORDER BY embedding <-> $1 LIMIT 5', embedding)
Add a vector column
from pgvector.peewee import VectorField
class Item(BaseModel):
embedding = VectorField(dimensions=3)
Insert a vector
item = Item.create(embedding=[1, 2, 3])
Get the nearest neighbors to a vector
Item.select().order_by(Item.embedding.l2_distance([3, 1, 2])).limit(5)
Also supports max_inner_product
and cosine_distance
Get the distance
Item.select(Item.embedding.l2_distance([3, 1, 2]).alias('distance'))
Get items within a certain distance
Item.select().where(Item.embedding.l2_distance([3, 1, 2]) < 5)
Average vectors
from peewee import fn
Item.select(fn.avg(Item.embedding)).scalar()
Also supports sum
Add an approximate index
Item.add_index('embedding vector_l2_ops', using='hnsw')
Use vector_ip_ops
for inner product and vector_cosine_ops
for cosine distance
View the changelog
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/pgvector/pgvector-python.git
cd pgvector-python
pip install -r requirements.txt
createdb pgvector_python_test
pytest