Skip to main content

Runnable Hub is a middleware for large models, enabling management and execution of complex inference tasks with a flexible architecture and support for multiple task types.

Project description

Runnable Hub

Runnable Hub 是大模型中间件,可以用于管理和执行大模型相关的任务。它提供了一个灵活的架构,允许用户定义和执行复杂的大模型推理任务,并支持多种任务类型的扩展。

flowchart TD
    bizApp1(AI业务应用) -->|SDK| sub
    bizApp2(AI业务应用2) -->|SDK| sub
    sub[("`
    文件存储(本地|OSS|S3 ...)
    消息队列(Redis ...)
    `")] --> hub1[["`
    RunnableHub
    Python`"]]
    sub --> hub2[["`
    RunnableHub
    Java`"]]

    hub1 --> LLM_WORKER & PROCESS_WOKRER & API_WORKER & CHAIN_WORKER
    hub2 --> AGENT_WORKER & TOOL_WORKTER

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

runnable_hub-0.2.tar.gz (4.8 kB view details)

Uploaded Source

Built Distribution

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

runnable_hub-0.2-py3-none-any.whl (5.8 kB view details)

Uploaded Python 3

File details

Details for the file runnable_hub-0.2.tar.gz.

File metadata

  • Download URL: runnable_hub-0.2.tar.gz
  • Upload date:
  • Size: 4.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.1

File hashes

Hashes for runnable_hub-0.2.tar.gz
Algorithm Hash digest
SHA256 75deba54d589a3a24f591560c52d32e990a814c644141fb9ecd3e515017c5136
MD5 7ad941800b5a78098a024f11b6561b56
BLAKE2b-256 7dcae9392df19fd272456c648c5017891c38bcfbdd3b159591130d6b5106696e

See more details on using hashes here.

File details

Details for the file runnable_hub-0.2-py3-none-any.whl.

File metadata

  • Download URL: runnable_hub-0.2-py3-none-any.whl
  • Upload date:
  • Size: 5.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.1

File hashes

Hashes for runnable_hub-0.2-py3-none-any.whl
Algorithm Hash digest
SHA256 23b21e31fea18d8d4de364ec84bf750d96af477a1e7708cad25d09e6149d1660
MD5 1fcc1e9db32165f1e988f7ce6c199954
BLAKE2b-256 28b9653baaef932ab07c88229cbd0679e7cefb35730f33ea02f17a55b8300ccc

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