DEV Community

Engin EROL
Engin EROL

Posted on

hi everyone!

Hi everyone! ๐Ÿ‘‹

Iโ€™m excited to write my first post on this platform, and Iโ€™m very happy to be part of this amazing developer community. ๐Ÿš€


๐Ÿš€ FAISS HNSW-based Vector Database for Node.js is Here!

Iโ€™ve been working on a high-performance FAISS-based vector database for Node.js, and Iโ€™m excited to finally share it with you all! ๐ŸŽ‰

๐Ÿ’ก eada-cpu is optimized for FAISS HNSW (Hierarchical Navigable Small World) indexing, allowing efficient KNN searches directly in Node.jsโ€”without needing Python dependencies.


๐Ÿ”ฅ Benchmark Results

Metric Value
Vector Dimension 128
Number of Vectors 7,000,000+
KNN Search Time 4.05 ms ๐Ÿš€
Performance vs FAISS-Python 10% - 15% faster
Dataset Size ~5GB
Indexing Time 1 hour 36 minutes

๐Ÿ’ก Fully Optimized for CPU!

This benchmark was run entirely on CPU, making it ideal for standard servers without requiring GPU acceleration.

This enables LLM RAG applications, recommendation engines, and vector searches to run efficiently and cost-effectively in Node.js.


๐ŸŽฏ Key Features

โœ… FAISS HNSW support โ†’ High-speed, accurate KNN search

โœ… Pure Node.js โ†’ No Python dependencies required

โœ… Compatible with Windows / Linux / macOS (Intel & ARM64)

โœ… CMake-based build system for easy cross-platform support

โœ… N-API & Prebuilt support โ†’ Install easily with:


bash
npm i eada-cpu


Enter fullscreen mode Exit fullscreen mode

Top comments (0)