Metadata-Version: 2.1
Name: vector_db_benchmark
Version: 1.0.0
Summary: Benchmarking tool for vector databases
Home-page: https://github.com/frozenparadox/vector_db_benchmark
Author: Sushant Lenka
Author-email: frostbitecryengine300@gmail.com
Keywords: vector database benchmark milvus numpy
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.6
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: numpy>=1.18.0
Requires-Dist: psutil>=5.7.0
Requires-Dist: matplotlib>=3.2.0

# Vector DB Benchmark

`vector_db_benchmark` is a Python package that allows you to benchmark vector databases. It enables you to run benchmarks on different vector database implementations under identical conditions, ensuring replicable and fair comparisons.

## Features

- **Benchmark any vector database implementation** that provides the required methods.
- **Replicable benchmarking configurations** using a fixed random seed.
- **Supports both on-disk and in-memory vector databases**.
- **Generates metrics and graphs** for ingestion time, search times, and memory usage.
- **Easy to use** with simple API and command-line interface.

## Installation

Install the package using `pip`:

```bash
pip install vector_db_benchmark
```
