Skip to main content

Unix pipes for AI workflows. Define tasks and pipelines in YAML; execute with a single Go binary auto-downloaded on first run.

Project description

orcha

Unix pipes for AI workflows. Define reusable tasks and linear pipelines in orcha.yaml; run them from Python with a single line.

from orcha import Orcha

o = Orcha("./orcha.yaml")
for event in o.run("summarize-and-translate", "./article.txt"):
    print(event)

The package ships a tiny Python wrapper; the actual engine is a Go binary that's auto-downloaded to ~/.orcha/bin/ on first use.

Project details


Download files

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

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

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

orcha_dev-0.1.0-py3-none-any.whl (9.6 kB view details)

Uploaded Python 3

File details

Details for the file orcha_dev-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: orcha_dev-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 9.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.11

File hashes

Hashes for orcha_dev-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 ebc9ab8e8612b0d7d70a3c459aa7cc61a7e12e4fff200550b00be6af11142a22
MD5 c9872c04ce271c571d69766bb9342f65
BLAKE2b-256 ad3c63f69111e21dab23a915a94983b3a954569c3997a344610bf34af3c27b74

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