https://github.com/supabase/vecs

Postgres/pgvector Python Client
https://github.com/supabase/vecs

ai embeddings pgvector postgres vectors

Last synced: 27 days ago
JSON representation

Postgres/pgvector Python Client

• Host: GitHub
• URL: https://github.com/supabase/vecs
• Owner: supabase
• License: apache-2.0
• Created: 2023-05-19T14:52:11.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2024-02-28T17:58:42.000Z (8 months ago)
• Last Synced: 2024-04-13T21:54:17.393Z (7 months ago)
• Topics: ai, embeddings, pgvector, postgres, vectors
• Language: Python
• Homepage: https://supabase.github.io/vecs/latest
• Size: 6.54 MB
• Stars: 190
• Watchers: 16
• Forks: 30
• Open Issues: 8
• Metadata Files:
  • Readme: README.md
  • License: LICENSE
  • Support: docs/support_changelog.md

Awesome Lists containing this project

README

        
# vecs



    

    

        

    

    

        

    





    

    

    



---

**Documentation**: https://supabase.github.io/vecs/latest/

**Source Code**: https://github.com/supabase/vecs

---

`vecs` is a python client for managing and querying vector stores in PostgreSQL with the [pgvector extension](https://github.com/pgvector/pgvector). This guide will help you get started with using vecs.

If you don't have a Postgres database with the pgvector ready, see [hosting](https://supabase.github.io/vecs/hosting/) for easy options.

## Installation

Requires:

- Python 3.7+

You can install vecs using pip:

```sh

pip install vecs

```

## Usage

Visit the [quickstart guide](https://supabase.github.io/vecs/latest/api) for more complete info.

```python

import vecs

DB_CONNECTION = "postgresql://:@:/"

# create vector store client

vx = vecs.create_client(DB_CONNECTION)

# create a collection of vectors with 3 dimensions

docs = vx.get_or_create_collection(name="docs", dimension=3)

# add records to the *docs* collection

docs.upsert(

    records=[

        (

         "vec0",           # the vector's identifier

         [0.1, 0.2, 0.3],  # the vector. list or np.array

         {"year": 1973}    # associated  metadata

        ),

        (

         "vec1",

         [0.7, 0.8, 0.9],

         {"year": 2012}

        )

    ]

)

# index the collection for fast search performance

docs.create_index()

# query the collection filtering metadata for "year" = 2012

docs.query(

    data=[0.4,0.5,0.6],              # required

    limit=1,                         # number of records to return

    filters={"year": {"$eq": 2012}}, # metadata filters

)

# Returns: ["vec1"]

```