VectorDBBench
The open‑source repository containing the implementation, configuration, and scripts of VectorDBBench, enabling users to run standardized benchmarks across multiple vector database systems locally or in CI.
About this tool
title: VectorDBBench slug: vectordbbench url: https://github.com/zilliztech/VectorDBBench category: benchmarks-evaluation brand: zilliz brand_logo: https://avatars.githubusercontent.com/u/67472536?s=200&v=4 source_url: https://github.com/zilliztech/VectorDBBench images:
- https://opengraph.githubassets.com/1/zilliztech/VectorDBBench tags:
- benchmark
- evaluation
- vector-databases license: MIT featured: false
Overview
VectorDBBench is an open‑source benchmarking toolkit for vector databases. It provides implementation code, configuration, and scripts to run standardized benchmarks across multiple vector database systems locally or in CI environments.
Features
- Standardized benchmarking framework for evaluating vector databases under a common setup.
- Multi‑database support through pluggable implementations in the
vectordb_benchmodule. - Configurable benchmark runs via configuration files and environment variables (example in
.env.example). - Containerized environment using the provided
Dockerfileand.devcontainersetup for reproducible runs. - CI integration enabled by GitHub workflow definitions in
.github/workflows. - Automated tests in the
testsdirectory to validate benchmark logic and integrations. - Scripted installation and setup with resources under the
installdirectory andMakefiletargets. - Open‑source, extensible design under the MIT license, allowing customization and contribution.
Pricing
VectorDBBench is open source and available free of charge under the MIT license.
Loading more......
Information
Categories
Tags
Similar Products
6 result(s)An annual competition focused on similarity search and indexing algorithms, including approximate nearest neighbor methods and high-dimensional vector indexing, providing benchmarks and results relevant to vector database research.
BEIR (Benchmarking IR) is a benchmark suite for evaluating information retrieval and vector search systems across multiple tasks and datasets. Useful for comparing vector database performance.
ANN-Benchmarks is a benchmarking platform specifically for evaluating the performance of approximate nearest neighbor (ANN) search algorithms, which are foundational to vector database evaluation and comparison.
Benchmark results and tools by MyScale aimed at measuring the performance of vector databases in various search and retrieval tasks.
A set of benchmarks provided by Qdrant for evaluating vector databases, focusing on speed, scalability, and accuracy of vector search operations.
A massive text embedding benchmark for evaluating the quality of text embedding models, crucial for vector database applications.