helix-db  by HelixDB

Graph-vector database for RAG and AI applications

Created 11 months ago
2,956 stars

Top 16.0% on SourcePulse

GitHubView on GitHub
Project Summary

HelixDB is an open-source graph-vector database built in Rust, designed for high-performance intelligent data storage, particularly for RAG and AI applications. It targets developers seeking a reliable, fast, and user-friendly database solution for AI-driven workloads.

How It Works

HelixDB leverages Rust for performance and utilizes LMDB via the Heed wrapper for its storage engine. This combination provides fast startup times and millisecond query latency. Its vector-first design natively supports vector data types, making it suitable for AI and RAG, while its intuitive query language and built-in type checking enhance developer experience.

Quick Start & Requirements

  • Install CLI: curl -sSL "https://install.helix-db.com" | bash
  • Install Helix: helix install
  • Setup: helix init --path <path-to-create-files-at>
  • Check queries: helix check
  • Deploy locally: helix deploy --local
  • Additional commands: helix instances, helix stop <instance-id>, helix start <instance-id>
  • Prerequisites: Rust, LMDB (managed by Heed).

Highlighted Details

  • Built in Rust for performance and reliability.
  • Native vector data type support for AI/RAG.
  • Powered by LMDB via Heed for efficient storage.
  • ACID compliant.
  • Offers a managed cloud service.

Maintenance & Community

The project is actively developed with a focus on expanding vector capabilities, enhancing the query language, improving build tools, and optimizing performance. Community and support channels are not explicitly detailed in the README.

Licensing & Compatibility

Licensed under GNU General Public License v3.0 (GPL-3.0). This copyleft license may have implications for commercial or closed-source integrations. Commercial support and managed services are available.

Limitations & Caveats

The GPL-3.0 license may restrict its use in certain commercial or proprietary applications without adherence to its terms. Specific details on community engagement or support channels are not provided.

Health Check
Last Commit

18 hours ago

Responsiveness

1 day

Pull Requests (30d)
24
Issues (30d)
9
Star History
227 stars in the last 30 days

Explore Similar Projects

Starred by Chang She Chang She(Cofounder of LanceDB), Carol Willing Carol Willing(Core Contributor to CPython, Jupyter), and
11 more.

lancedb by lancedb

0.7%
8k
Embedded retrieval engine for multimodal AI
Created 2 years ago
Updated 4 days ago
Feedback? Help us improve.