rill-flow  by weibocom

Workflow orchestration engine for distributed workloads and LLMs

created 1 year ago
397 stars

Top 73.8% on sourcepulse

GitHubView on GitHub
Project Summary

Rill Flow is a distributed workflow orchestration engine designed for high-performance, scalable execution of complex workloads, particularly those involving LLMs. It targets developers and organizations needing to manage and automate distributed tasks, offering a cloud-native approach with visual process orchestration and easy integration capabilities.

How It Works

Rill Flow utilizes a distributed architecture to orchestrate tasks across heterogeneous systems. It emphasizes high performance, claiming task execution latency under 100ms and the ability to handle tens of millions of tasks daily. The system supports cloud-native deployment via Docker and orchestration of containerized functions, enabling flexible and scalable execution environments.

Quick Start & Requirements

  • Install: Clone the repository and use docker-compose up -d (or docker compose up -d for V2).
  • Prerequisites: OSX/Linux environment, Docker, Docker-Compose.
  • Verification: Run docker-compose ps to check service status.
  • Access: The UI is available at http://localhost (admin/admin).
  • Docs: Live Demo, Execution Status Document

Highlighted Details

  • High performance: <100ms task latency, millions of tasks/day.
  • Distributed orchestration for heterogeneous systems.
  • Visual process orchestration and plug-in access.
  • Cloud-native deployment and function orchestration.
  • AIGC support for LLM model service integration.

Maintenance & Community

The project lists several maintainers and contributors. Community links are not explicitly provided in the README.

Licensing & Compatibility

Rill Flow is licensed under the Apache License 2.0, which is permissive and generally compatible with commercial and closed-source applications.

Limitations & Caveats

The README focuses on setup and basic usage, with limited information on advanced configurations, error handling, or specific LLM integration patterns beyond general support.

Health Check
Last commit

5 months ago

Responsiveness

1 day

Pull Requests (30d)
0
Issues (30d)
2
Star History
13 stars in the last 90 days

Explore Similar Projects

Starred by Elie Bursztein Elie Bursztein(Cybersecurity Lead at Google DeepMind), Tim J. Baek Tim J. Baek(Founder of Open WebUI), and
1 more.

harbor by av

0.3%
2k
CLI tool for local LLM stack orchestration
created 1 year ago
updated 3 weeks ago
Feedback? Help us improve.