pgvector 0.3.5__py3-none-any.whl

pgvector-0.3.5.dist-info/METADATA

@@ -0,0 +1,554 @@
+Metadata-Version: 2.1
+Name: pgvector
+Version: 0.3.5
+Summary: pgvector support for Python
+Author-email: Andrew Kane <andrew@ankane.org>
+License: MIT
+Project-URL: Homepage, https://github.com/pgvector/pgvector-python
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE.txt
+Requires-Dist: numpy
+
+# pgvector-python
+
+[pgvector](https://github.com/pgvector/pgvector) support for Python
+
+Supports [Django](https://github.com/django/django), [SQLAlchemy](https://github.com/sqlalchemy/sqlalchemy), [SQLModel](https://github.com/tiangolo/sqlmodel), [Psycopg 3](https://github.com/psycopg/psycopg), [Psycopg 2](https://github.com/psycopg/psycopg2), [asyncpg](https://github.com/MagicStack/asyncpg), and [Peewee](https://github.com/coleifer/peewee)
+
+[![Build Status](https://github.com/pgvector/pgvector-python/actions/workflows/build.yml/badge.svg)](https://github.com/pgvector/pgvector-python/actions)
+
+## Installation
+
+Run:
+
+```sh
+pip install pgvector
+```
+
+And follow the instructions for your database library:
+
+- [Django](#django)
+- [SQLAlchemy](#sqlalchemy)
+- [SQLModel](#sqlmodel)
+- [Psycopg 3](#psycopg-3)
+- [Psycopg 2](#psycopg-2)
+- [asyncpg](#asyncpg)
+- [Peewee](#peewee)
+
+Or check out some examples:
+
+- [Embeddings](https://github.com/pgvector/pgvector-python/blob/master/examples/openai/example.py) with OpenAI
+- [Binary embeddings](https://github.com/pgvector/pgvector-python/blob/master/examples/cohere/example.py) with Cohere
+- [Sentence embeddings](https://github.com/pgvector/pgvector-python/blob/master/examples/sentence_transformers/example.py) with SentenceTransformers
+- [Hybrid search](https://github.com/pgvector/pgvector-python/blob/master/examples/hybrid_search/rrf.py) with SentenceTransformers (Reciprocal Rank Fusion)
+- [Hybrid search](https://github.com/pgvector/pgvector-python/blob/master/examples/hybrid_search/cross_encoder.py) with SentenceTransformers (cross-encoder)
+- [Sparse search](https://github.com/pgvector/pgvector-python/blob/master/examples/sparse_search/example.py) with Transformers
+- [Late interaction search](https://github.com/pgvector/pgvector-python/blob/master/examples/colbert/exact.py) with ColBERT
+- [Image search](https://github.com/pgvector/pgvector-python/blob/master/examples/image_search/example.py) with PyTorch
+- [Image search](https://github.com/pgvector/pgvector-python/blob/master/examples/imagehash/example.py) with perceptual hashing
+- [Morgan fingerprints](https://github.com/pgvector/pgvector-python/blob/master/examples/rdkit/example.py) with RDKit
+- [Topic modeling](https://github.com/pgvector/pgvector-python/blob/master/examples/gensim/example.py) with Gensim
+- [Implicit feedback recommendations](https://github.com/pgvector/pgvector-python/blob/master/examples/implicit/example.py) with Implicit
+- [Explicit feedback recommendations](https://github.com/pgvector/pgvector-python/blob/master/examples/surprise/example.py) with Surprise
+- [Recommendations](https://github.com/pgvector/pgvector-python/blob/master/examples/lightfm/example.py) with LightFM
+- [Horizontal scaling](https://github.com/pgvector/pgvector-python/blob/master/examples/citus/example.py) with Citus
+- [Bulk loading](https://github.com/pgvector/pgvector-python/blob/master/examples/loading/example.py) with `COPY`
+
+## Django
+
+Create a migration to enable the extension
+
+```python
+from pgvector.django import VectorExtension
+
+class Migration(migrations.Migration):
+    operations = [
+        VectorExtension()
+    ]
+```
+
+Add a vector field to your model
+
+```python
+from pgvector.django import VectorField
+
+class Item(models.Model):
+    embedding = VectorField(dimensions=3)
+```
+
+Also supports `HalfVectorField`, `BitField`, and `SparseVectorField`
+
+Insert a vector
+
+```python
+item = Item(embedding=[1, 2, 3])
+item.save()
+```
+
+Get the nearest neighbors to a vector
+
+```python
+from pgvector.django import L2Distance
+
+Item.objects.order_by(L2Distance('embedding', [3, 1, 2]))[:5]
+```
+
+Also supports `MaxInnerProduct`, `CosineDistance`, `L1Distance`, `HammingDistance`, and `JaccardDistance`
+
+Get the distance
+
+```python
+Item.objects.annotate(distance=L2Distance('embedding', [3, 1, 2]))
+```
+
+Get items within a certain distance
+
+```python
+Item.objects.alias(distance=L2Distance('embedding', [3, 1, 2])).filter(distance__lt=5)
+```
+
+Average vectors
+
+```python
+from django.db.models import Avg
+
+Item.objects.aggregate(Avg('embedding'))
+```
+
+Also supports `Sum`
+
+Add an approximate index
+
+```python
+from pgvector.django import HnswIndex, IvfflatIndex
+
+class Item(models.Model):
+    class Meta:
+        indexes = [
+            HnswIndex(
+                name='my_index',
+                fields=['embedding'],
+                m=16,
+                ef_construction=64,
+                opclasses=['vector_l2_ops']
+            ),
+            # or
+            IvfflatIndex(
+                name='my_index',
+                fields=['embedding'],
+                lists=100,
+                opclasses=['vector_l2_ops']
+            )
+        ]
+```
+
+Use `vector_ip_ops` for inner product and `vector_cosine_ops` for cosine distance
+
+## SQLAlchemy
+
+Enable the extension
+
+```python
+session.execute(text('CREATE EXTENSION IF NOT EXISTS vector'))
+```
+
+Add a vector column
+
+```python
+from pgvector.sqlalchemy import Vector
+
+class Item(Base):
+    embedding = mapped_column(Vector(3))
+```
+
+Also supports `HALFVEC`, `BIT`, and `SPARSEVEC`
+
+Insert a vector
+
+```python
+item = Item(embedding=[1, 2, 3])
+session.add(item)
+session.commit()
+```
+
+Get the nearest neighbors to a vector
+
+```python
+session.scalars(select(Item).order_by(Item.embedding.l2_distance([3, 1, 2])).limit(5))
+```
+
+Also supports `max_inner_product`, `cosine_distance`, `l1_distance`, `hamming_distance`, and `jaccard_distance`
+
+Get the distance
+
+```python
+session.scalars(select(Item.embedding.l2_distance([3, 1, 2])))
+```
+
+Get items within a certain distance
+
+```python
+session.scalars(select(Item).filter(Item.embedding.l2_distance([3, 1, 2]) < 5))
+```
+
+Average vectors
+
+```python
+from pgvector.sqlalchemy import avg
+
+session.scalars(select(func.avg(Item.embedding))).first()
+```
+
+Also supports `sum`
+
+Add an approximate index
+
+```python
+index = Index(
+    'my_index',
+    Item.embedding,
+    postgresql_using='hnsw',
+    postgresql_with={'m': 16, 'ef_construction': 64},
+    postgresql_ops={'embedding': 'vector_l2_ops'}
+)
+# or
+index = Index(
+    'my_index',
+    Item.embedding,
+    postgresql_using='ivfflat',
+    postgresql_with={'lists': 100},
+    postgresql_ops={'embedding': 'vector_l2_ops'}
+)
+
+index.create(engine)
+```
+
+Use `vector_ip_ops` for inner product and `vector_cosine_ops` for cosine distance
+
+## SQLModel
+
+Enable the extension
+
+```python
+session.exec(text('CREATE EXTENSION IF NOT EXISTS vector'))
+```
+
+Add a vector column
+
+```python
+from pgvector.sqlalchemy import Vector
+from sqlalchemy import Column
+
+class Item(SQLModel, table=True):
+    embedding: Any = Field(sa_column=Column(Vector(3)))
+```
+
+Also supports `HALFVEC`, `BIT`, and `SPARSEVEC`
+
+Insert a vector
+
+```python
+item = Item(embedding=[1, 2, 3])
+session.add(item)
+session.commit()
+```
+
+Get the nearest neighbors to a vector
+
+```python
+session.exec(select(Item).order_by(Item.embedding.l2_distance([3, 1, 2])).limit(5))
+```
+
+Also supports `max_inner_product`, `cosine_distance`, `l1_distance`, `hamming_distance`, and `jaccard_distance`
+
+Get the distance
+
+```python
+session.exec(select(Item.embedding.l2_distance([3, 1, 2])))
+```
+
+Get items within a certain distance
+
+```python
+session.exec(select(Item).filter(Item.embedding.l2_distance([3, 1, 2]) < 5))
+```
+
+Average vectors
+
+```python
+from pgvector.sqlalchemy import avg
+
+session.exec(select(func.avg(Item.embedding))).first()
+```
+
+Also supports `sum`
+
+Add an approximate index
+
+```python
+from sqlalchemy import Index
+
+index = Index(
+    'my_index',
+    Item.embedding,
+    postgresql_using='hnsw',
+    postgresql_with={'m': 16, 'ef_construction': 64},
+    postgresql_ops={'embedding': 'vector_l2_ops'}
+)
+# or
+index = Index(
+    'my_index',
+    Item.embedding,
+    postgresql_using='ivfflat',
+    postgresql_with={'lists': 100},
+    postgresql_ops={'embedding': 'vector_l2_ops'}
+)
+
+index.create(engine)
+```
+
+Use `vector_ip_ops` for inner product and `vector_cosine_ops` for cosine distance
+
+## Psycopg 3
+
+Enable the extension
+
+```python
+conn.execute('CREATE EXTENSION IF NOT EXISTS vector')
+```
+
+Register the vector type with your connection
+
+```python
+from pgvector.psycopg import register_vector
+
+register_vector(conn)
+```
+
+For [async connections](https://www.psycopg.org/psycopg3/docs/advanced/async.html), use
+
+```python
+from pgvector.psycopg import register_vector_async
+
+await register_vector_async(conn)
+```
+
+Create a table
+
+```python
+conn.execute('CREATE TABLE items (id bigserial PRIMARY KEY, embedding vector(3))')
+```
+
+Insert a vector
+
+```python
+embedding = np.array([1, 2, 3])
+conn.execute('INSERT INTO items (embedding) VALUES (%s)', (embedding,))
+```
+
+Get the nearest neighbors to a vector
+
+```python
+conn.execute('SELECT * FROM items ORDER BY embedding <-> %s LIMIT 5', (embedding,)).fetchall()
+```
+
+Add an approximate index
+
+```python
+conn.execute('CREATE INDEX ON items USING hnsw (embedding vector_l2_ops)')
+# or
+conn.execute('CREATE INDEX ON items USING ivfflat (embedding vector_l2_ops) WITH (lists = 100)')
+```
+
+Use `vector_ip_ops` for inner product and `vector_cosine_ops` for cosine distance
+
+## Psycopg 2
+
+Enable the extension
+
+```python
+cur = conn.cursor()
+cur.execute('CREATE EXTENSION IF NOT EXISTS vector')
+```
+
+Register the vector type with your connection or cursor
+
+```python
+from pgvector.psycopg2 import register_vector
+
+register_vector(conn)
+```
+
+Create a table
+
+```python
+cur.execute('CREATE TABLE items (id bigserial PRIMARY KEY, embedding vector(3))')
+```
+
+Insert a vector
+
+```python
+embedding = np.array([1, 2, 3])
+cur.execute('INSERT INTO items (embedding) VALUES (%s)', (embedding,))
+```
+
+Get the nearest neighbors to a vector
+
+```python
+cur.execute('SELECT * FROM items ORDER BY embedding <-> %s LIMIT 5', (embedding,))
+cur.fetchall()
+```
+
+Add an approximate index
+
+```python
+cur.execute('CREATE INDEX ON items USING hnsw (embedding vector_l2_ops)')
+# or
+cur.execute('CREATE INDEX ON items USING ivfflat (embedding vector_l2_ops) WITH (lists = 100)')
+```
+
+Use `vector_ip_ops` for inner product and `vector_cosine_ops` for cosine distance
+
+## asyncpg
+
+Enable the extension
+
+```python
+await conn.execute('CREATE EXTENSION IF NOT EXISTS vector')
+```
+
+Register the vector type with your connection
+
+```python
+from pgvector.asyncpg import register_vector
+
+await register_vector(conn)
+```
+
+or your pool
+
+```python
+async def init(conn):
+    await register_vector(conn)
+
+pool = await asyncpg.create_pool(..., init=init)
+```
+
+Create a table
+
+```python
+await conn.execute('CREATE TABLE items (id bigserial PRIMARY KEY, embedding vector(3))')
+```
+
+Insert a vector
+
+```python
+embedding = np.array([1, 2, 3])
+await conn.execute('INSERT INTO items (embedding) VALUES ($1)', embedding)
+```
+
+Get the nearest neighbors to a vector
+
+```python
+await conn.fetch('SELECT * FROM items ORDER BY embedding <-> $1 LIMIT 5', embedding)
+```
+
+Add an approximate index
+
+```python
+await conn.execute('CREATE INDEX ON items USING hnsw (embedding vector_l2_ops)')
+# or
+await conn.execute('CREATE INDEX ON items USING ivfflat (embedding vector_l2_ops) WITH (lists = 100)')
+```
+
+Use `vector_ip_ops` for inner product and `vector_cosine_ops` for cosine distance
+
+## Peewee
+
+Add a vector column
+
+```python
+from pgvector.peewee import VectorField
+
+class Item(BaseModel):
+    embedding = VectorField(dimensions=3)
+```
+
+Also supports `HalfVectorField`, `FixedBitField`, and `SparseVectorField`
+
+Insert a vector
+
+```python
+item = Item.create(embedding=[1, 2, 3])
+```
+
+Get the nearest neighbors to a vector
+
+```python
+Item.select().order_by(Item.embedding.l2_distance([3, 1, 2])).limit(5)
+```
+
+Also supports `max_inner_product`, `cosine_distance`, `l1_distance`, `hamming_distance`, and `jaccard_distance`
+
+Get the distance
+
+```python
+Item.select(Item.embedding.l2_distance([3, 1, 2]).alias('distance'))
+```
+
+Get items within a certain distance
+
+```python
+Item.select().where(Item.embedding.l2_distance([3, 1, 2]) < 5)
+```
+
+Average vectors
+
+```python
+from peewee import fn
+
+Item.select(fn.avg(Item.embedding).coerce(True)).scalar()
+```
+
+Also supports `sum`
+
+Add an approximate index
+
+```python
+Item.add_index('embedding vector_l2_ops', using='hnsw')
+```
+
+Use `vector_ip_ops` for inner product and `vector_cosine_ops` for cosine distance
+
+## History
+
+View the [changelog](https://github.com/pgvector/pgvector-python/blob/master/CHANGELOG.md)
+
+## Contributing
+
+Everyone is encouraged to help improve this project. Here are a few ways you can help:
+
+- [Report bugs](https://github.com/pgvector/pgvector-python/issues)
+- Fix bugs and [submit pull requests](https://github.com/pgvector/pgvector-python/pulls)
+- Write, clarify, or fix documentation
+- Suggest or add new features
+
+To get started with development:
+
+```sh
+git clone https://github.com/pgvector/pgvector-python.git
+cd pgvector-python
+pip install -r requirements.txt
+createdb pgvector_python_test
+pytest
+```
+
+To run an example:
+
+```sh
+cd examples/loading
+pip install -r requirements.txt
+createdb pgvector_example
+python3 example.py
+```

pgvector-0.3.5.dist-info/RECORD

@@ -0,0 +1,42 @@
+pgvector/asyncpg/__init__.py,sha256=nPEfolmn6hf2gmonE1sCne051hd28biWhlSRimDy0AI,180
+pgvector/asyncpg/register.py,sha256=33xZD3SZjkDUFcEuVvVVQPZLEkpBVZZE2iZeWbLa1lc,835
+pgvector/django/__init__.py,sha256=omSXhf85Nazw2e1h2HzgxphL-MNTZUg7A_hwQ6nXBCo,701
+pgvector/django/bit.py,sha256=QjWHD4FhsveLQ8r3Q8SYDoe-zIYnhHR0W7HDLGx87Dc,935
+pgvector/django/extensions.py,sha256=JAtn_FCIST0DWJtDPZAQ-MygbAkKEiL0ZsA2QbYITRo,158
+pgvector/django/functions.py,sha256=QC6tiWErauN7EtbYqISiwJcpSGnxEW9qOhUBmwmGeoY,1364
+pgvector/django/halfvec.py,sha256=XNr54sddUquK3yDOfJT8BJHbRrEGjN7bwAnRKi_rOgM,1825
+pgvector/django/indexes.py,sha256=purT3nhq_CjHWUe-c3loCyK1XrWtZJ8pIq2wl975aSY,1440
+pgvector/django/sparsevec.py,sha256=KJlGF_VAxSV1eSOHPzfT4uNhCGDMBqjjANJPq2E7osE,1675
+pgvector/django/vector.py,sha256=xASXG7KGr65HsvsLYYrJfwv6azbDOdPcdmw9QLOHayA,2215
+pgvector/peewee/__init__.py,sha256=tANx57_gHFXgJLnr7GhD5j_xhsCosZ4GWBpdG76FNnY,326
+pgvector/peewee/bit.py,sha256=ZK6_RDDj46aAfYyxgXrwXYmHfPZpp5P5aA-CLt0M61Q,619
+pgvector/peewee/halfvec.py,sha256=NY3Wz79QbkKJdmQ_ZrkAqayQutQaO3iR5JBZ00sbMAE,969
+pgvector/peewee/sparsevec.py,sha256=SRDkw1_aWTVHOAXz3LYPMtDvIVlk5ByPcbDKkg1kR_0,981
+pgvector/peewee/vector.py,sha256=HXPj77K70jU7Vk33TVQLkDrp3995a_wygXkjyszDzTM,948
+pgvector/psycopg/__init__.py,sha256=ggPIFt-dlT9T4vCbzLfxReYqdUyFUx2n3J0p2kRZvek,248
+pgvector/psycopg/bit.py,sha256=ad9XneEmlCMEZi-1HN41mrTGogJmINtS7fy_I9Dbem8,712
+pgvector/psycopg/halfvec.py,sha256=A_uVQhXzcDsiK41rB5gmxwqLp7Fjpw-YJYPTED5Va5M,1354
+pgvector/psycopg/register.py,sha256=Ueuc9YKdhSI8Hd2JZIBrGHqp2i5sVW9DIKgS-Xo7Yyk,1107
+pgvector/psycopg/sparsevec.py,sha256=jaOEpcMPknCONMDNmWkQDLcvttemS8aNZGwfbEqHxPQ,1390
+pgvector/psycopg/vector.py,sha256=rUTcBJmyEtcideZ711H8kjVFfFRXLETmRMlGpOCALkA,1521
+pgvector/psycopg2/__init__.py,sha256=ThM3WfiOQfXHv-EY1DbOUNLJkR2RsXmxQzJNoynT4dw,158
+pgvector/psycopg2/halfvec.py,sha256=7JCYfpgflVq-kg4abzPZStxqb4d7u19gd2_X0ZmdGz8,536
+pgvector/psycopg2/register.py,sha256=BLGd6_xZgHGL6T8-lxDC03qkvUCI_HbpiYk46joLoRo,1107
+pgvector/psycopg2/sparsevec.py,sha256=fsIyviFoLIOc1jlMi6R5xWc9NNoKXgNcUKOaOrKlx38,560
+pgvector/psycopg2/vector.py,sha256=v3cwgISpStIS6zJqKcB78xqG0pQq4qCoa9Lbj1o8mCQ,535
+pgvector/sqlalchemy/__init__.py,sha256=CDMSwvIt4mwpuuSMduq3IyvgEp6RLToQClkqOElFY7o,369
+pgvector/sqlalchemy/bit.py,sha256=a-I24dwAR-Uc_vxj32MahDezjQVtUvIoMdPuYpztLIA,722
+pgvector/sqlalchemy/functions.py,sha256=LCxFWiTH-pM4XE2R5QRUg3vJxsxB-LNCGkqCEU6JOfk,272
+pgvector/sqlalchemy/halfvec.py,sha256=jlg3BuwvMrqSuDYJV0sjECEq_tq2n0IjgwtMz-grDak,1538
+pgvector/sqlalchemy/sparsevec.py,sha256=SJPSs0G07Bo8JTzmlO3a0LsYimyYmONynlRQ5Nndxss,1556
+pgvector/sqlalchemy/vector.py,sha256=dw7znnHjIQPblCzWD-uJmVY3HBGDOmw98uB1qkFBmTo,1517
+pgvector/utils/__init__.py,sha256=2qAb4VM3LcsnWwhFvRosnI4QS0KJnTDrY0aoRSXXIcg,193
+pgvector/utils/bit.py,sha256=YMcmqSjdZEhxC4HhSpkCgyYG26WUjM2Qv8JjI2Wu_Ts,1711
+pgvector/utils/halfvec.py,sha256=1yAmQ174UGFIWijfvegVWrr5sjltRAxMUMLmis-9BGc,2013
+pgvector/utils/sparsevec.py,sha256=uo1YfKx35iYuBPC9V3dDHWoAin042q6klOWBgY_Cnhc,4622
+pgvector/utils/vector.py,sha256=upyEMEEJF-o995GAk3UGhDPF9B0Ouv3zHWVZK54M4q8,2079
+pgvector-0.3.5.dist-info/LICENSE.txt,sha256=kzzb1DKtBwp3Pn5-R7YEUm8uH1qHA-D2tjT67Bn_b6M,1083
+pgvector-0.3.5.dist-info/METADATA,sha256=J5ZibepgmNk94dtOOYnO0ZiRyqhz7YSfvs1w98xoc6E,13231
+pgvector-0.3.5.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
+pgvector-0.3.5.dist-info/top_level.txt,sha256=xGGaXFRcSRHEhn0HS1FN_UjCWr1G-WSPgxx4a0NJc0M,9
+pgvector-0.3.5.dist-info/RECORD,,

pgvector-0.3.5.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (75.1.0)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

pgvector-0.3.5.dist-info/top_level.txt

@@ -0,0 +1 @@
+pgvector