Tanuki/tanuki.py

Prompt engineering for developers

51
/ 100
Established

Enforces typed outputs through Python type hints and Pydantic schemas to constrain LLM responses, then automatically distills smaller, cheaper models from execution data as usage scales. Uses n-shot prompting with cached alignment examples from test assertions, and integrates with OpenAI, Amazon Bedrock, and Together AI backends. Includes built-in RAG support with embedding generation for retrieval-augmented generation workflows.

695 stars and 55 monthly downloads. No commits in the last 6 months. Available on PyPI.

Stale 6m
Maintenance 0 / 25
Adoption 14 / 25
Maturity 25 / 25
Community 12 / 25

How are scores calculated?

Stars

695

Forks

27

Language

Python

License

MIT

Last pushed

Feb 13, 2024

Monthly downloads

55

Commits (30d)

0

Dependencies

7

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/Tanuki/tanuki.py"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.