Skip to main content

Business process automation for the Ratchet framework

Project description

ratchet-ops

Business process automation for the Ratchet framework.

Install

pip install ratchet-ops

What it does

  • Invoicing — Parse invoices from text with rule-based extraction, duplicate detection, and status tracking
  • Expenses — Track spending by category and vendor, with period summaries and recurring expense support
  • Cost routing — Route LLM tasks to the cheapest capable model (Haiku/Sonnet/Opus), log costs, project budgets
from ratchet.ops import OpsModule

agent.register(OpsModule())

# Or use components directly
from ratchet.ops import select_model, calculate_cost

model = select_model("extract facts from this transcript")  # → claude-haiku-4-5
cost = calculate_cost(model, input_tokens=5000, output_tokens=500)

License

MIT

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

ratchet_ops-0.1.0.tar.gz (7.4 kB view details)

Uploaded Source

Built Distribution

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

ratchet_ops-0.1.0-py3-none-any.whl (10.2 kB view details)

Uploaded Python 3

File details

Details for the file ratchet_ops-0.1.0.tar.gz.

File metadata

  • Download URL: ratchet_ops-0.1.0.tar.gz
  • Upload date:
  • Size: 7.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.9

File hashes

Hashes for ratchet_ops-0.1.0.tar.gz
Algorithm Hash digest
SHA256 03d0e47c99b412f84f9141c7ed552da19a9d07d520b0532ad79d021c9fa0160a
MD5 6110b0fb7447fb4863dd980c84983da7
BLAKE2b-256 522db6ce3d8921740f699785d32357ef129eaa42d46bcb2e185578f082370206

See more details on using hashes here.

File details

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

File metadata

  • Download URL: ratchet_ops-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 10.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.9

File hashes

Hashes for ratchet_ops-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 89c9becc45fa1b6bc3e1c145a9255a9735178ad88507d5401eba3b4b7d4493b4
MD5 a9b9c3f4bda46b29316ac8fb4d21ce25
BLAKE2b-256 4908a09dd29ccd6e000ea53710f09283851a9bd184a2d67fe72739cf85004ba3

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