vector-index-bench/vibe
Vector Index Benchmark for Embeddings (VIBE) is an extensible benchmark for approximate nearest neighbor search methods, or vector indexes, using modern embedding datasets.
This tool helps machine learning engineers and researchers rigorously compare the performance of different approximate nearest neighbor (ANN) search methods, often called vector indexes. You provide datasets of high-dimensional embeddings and receive detailed benchmark results, including recall, queries per second, and memory usage. It's designed for individuals developing or selecting vector search algorithms for large-scale applications.
Use this if you need to objectively evaluate and select the best vector indexing algorithm for your specific embedding data and performance requirements.
Not ideal if you are looking for an off-the-shelf vector search solution or a simple tool for basic similarity search without detailed benchmarking.
Stars
36
Forks
6
Language
Python
License
MIT
Category
Last pushed
Mar 04, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/vector-index-bench/vibe"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
lancedb/lancedb
Developer-friendly OSS embedded retrieval library for multimodal AI. Search More; Manage Less.
zilliztech/VectorDBBench
Benchmark for vector databases.
qdrant/vector-db-benchmark
Framework for benchmarking vector search engines
prrao87/lancedb-study
Comparing LanceDB and Elasticsearch for full-text search and vector search performance
myscale/vector-db-benchmark
Framework for benchmarking fully-managed vector databases