nnext 0.0.43

Client library for the NNext Neural search engine

About

The NNext Python Client.

NNext is a

• ⚡ blazingly fast
• 🔍 nearest-neighbors vector search engine

Installation | Quick Start | Documentation

Installation

To install the pynnext client, activate a virtual environment, and install via pip:

Supported Python Versions

Python >= 3.7, < 3.11

Mac/Linux

pip install virtualenv
virtualenv <your-env>
source <your-env>/bin/activate
<your-env>/bin/pip install nnext

Windows

pip install virtualenv
virtualenv <your-env>
<your-env>\Scripts\activate
<your-env>\Scripts\pip.exe install nnext

Quick Start

In order start interacting with NNext, you need to obtain a client here https://console.nnext.ai/.

Here's a quick example showcasing how you can create an index, insert vectors/documents and search among them via NNext.

Let's begin by installing the Connecting to NNext.

SELECT images.uid,
       images.name,
       images.vector < - > 'VECTOR(0.19, 0.81, 0.75, 0.11)'::vector AS dist
FROM nnext-public-data.images.laion
ORDER BY
    dist
    LIMIT 100

import nnext

nnclient = nnext.NNextClient(api_key="NNEXT_API_KEY")

# Perform a query.
QUERY = """
        SELECT images.uid, images.name,
          images.vector <-> 'VECTOR(0.19, 0.81, 0.75, 0.11)'::vector AS dist
        FROM nnext-public-data.images.laion
        ORDER BY
            dist
        LIMIT 100;
    """
query_job = nnclient.query(QUERY)  # API request
rows = query_job.result()  # Waits for query to finish

for row in rows:
    print(row.name)

Documentation

More documentation is available here here https://nnext.ai/docs.: