sutro-sh/sutro

Analyze and generate unstructured data using LLMs, from quick experiments to billion token jobs.

40
/ 100
Emerging

This project helps data scientists and analysts quickly process large volumes of unstructured text, like customer reviews or product descriptions, using AI models. You feed in your raw text data, and it delivers structured outputs such as sentiment classifications, extracted key information, or newly generated synthetic data. It’s ideal for anyone needing to derive insights or create new datasets from text at scale.

Use this if you need to rapidly analyze, classify, or generate text data using AI models without managing complex infrastructure or incurring high costs for large-scale operations.

Not ideal if your primary need is real-time, low-latency AI inference for single queries rather than high-throughput batch processing of large datasets.

unstructured-data-analysis text-classification sentiment-analysis synthetic-data-generation data-labeling
No Package No Dependents
Maintenance 13 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 6 / 25

How are scores calculated?

Stars

12

Forks

1

Language

Python

License

Apache-2.0

Category

mlops-end-to-end

Last pushed

Mar 17, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/mlops/sutro-sh/sutro"

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