Skip to content

Releases: sauravniraula/fastembed-vectorstore

v0.5.2

Choose a tag to compare

@sauravniraula sauravniraula released this 17 Feb 16:51
ee693fb

Full Changelog: v0.4.2...v0.5.2

v0.2.0

Choose a tag to compare

@sauravniraula sauravniraula released this 16 Aug 18:23
b323ce4

Fastembed Vectorstore 0.2.0 🚀

This release includes support for multiple OS and Architecture and improves performance using multiple threads.

What's Changed

Full Changelog: v0.1.5...v0.2.0

v0.1.5

Choose a tag to compare

@sauravniraula sauravniraula released this 28 Jun 22:13
62763d2

🚀 Release: v0.1.5 – Initial Public Release

📦 FastEmbed VectorStore
A high-performance, Rust-based in-memory vector store with seamless Python integration via FastEmbed.

🔗 [📄 View on PyPI](https://pypi.org/project/fastembed-vectorstore/0.1.5)
🔗 [📂 Source on GitHub](https://github.com/sauravniraula/fastembed_vectorstore/commits/v0.1.5)

🌟 Highlights

  • Rust-based core with blazing-fast performance and minimal memory overhead
  • Python bindings via PyO3 for easy integration with your Python applications
  • Supports 30+ Embedding Models including BGE, GTE, Nomic, Multilingual E5, and more
  • In-memory vector store with JSON-based persistence and restore
  • Cosine similarity search with ranked results

🔧 Features

  • 🧠 Embedding Model Support: Choose from a wide range of pre-trained models including quantized variants
  • 💾 Persistence: Save and load vector stores to/from disk (.json)
  • 🔍 Search: Cosine similarity-based nearest neighbor search
  • ⚙️ Simple API:

📄 License

Licensed under Apache 2.0
Author: Saurav Niraula (📧 [developmentsaurav@gmail.com](mailto:developmentsaurav@gmail.com))