Skip to main content

Lightweight orchestrator with in-process gatekeeper + micro-batching for multi-agent RAG.

Project description

Krionis Orchestrator

A lightweight orchestration runtime built on top of Krionis Pipeline.
It enables batching, multi-agent workflows, and coordination for low-latency, multi-user RAG systems.


🤖 Key Features

Batching & Microbatching

  • Queueing + scheduling for efficient parallel queries
  • Smooth multi-user handling (no “stuck at starting”)

🕹 Agent Runtime

  • Built-in agents: Retriever, Compressor, Reranker, Drafting, Validator, Dialogue, Coordinator
  • Agents communicate, self-optimize, and hand off state until human approval

🔗 Provider Plug-ins

  • Pluggable backends (local LLMs, APIs, hybrid deployments)
  • Bridges directly to krionis-pipeline

🌐 API + Web Interface

  • REST endpoints for orchestration and multi-agent queries
  • Minimal HTML UI for monitoring and interaction

🛡 Resilient Runtime

  • Timeouts, retries, and cancellation built in
  • Lightweight, works offline and in low-compute setups

🚀 Quickstart

Install:

pip install krionis-orchestrator

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

rag_orchestrator-0.1.1.tar.gz (2.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

rag_orchestrator-0.1.1-py3-none-any.whl (2.3 kB view details)

Uploaded Python 3

File details

Details for the file rag_orchestrator-0.1.1.tar.gz.

File metadata

  • Download URL: rag_orchestrator-0.1.1.tar.gz
  • Upload date:
  • Size: 2.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.10.18

File hashes

Hashes for rag_orchestrator-0.1.1.tar.gz
Algorithm Hash digest
SHA256 bd8c29127e3edd0429b824c0c2bc86949593e7aa9748a3b6bef7008388500aa9
MD5 fb3190d292bc4ab0b505f954d4b4ee22
BLAKE2b-256 4a11a819c62ab5aa52042dc2d10d67b859591db871de094ee6052b16606d5a7f

See more details on using hashes here.

File details

Details for the file rag_orchestrator-0.1.1-py3-none-any.whl.

File metadata

File hashes

Hashes for rag_orchestrator-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 46ca54ccd2ac292175a87ac90741d725921d3f61234957fd90cef08fc9dd5a3a
MD5 28a8ec5d292f7a8b3b65fbc012049e2b
BLAKE2b-256 8de35e9005eb3d9ce0ed0af26037fd02ef6d71c661acc696ced427959a0161ce

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page