lotus-data/lotus

AI-Powered Data Processing: Use LOTUS to process all of your datasets with LLMs and embeddings. Enjoy up to 1000x speedups with fast, accurate query processing, that's as simple as writing Pandas code

51
/ 100
Established

Based on the README, here's a technical summary: Introduces **semantic operators**—declarative transformations parameterized by natural language expressions that extend relational algebra to unstructured data, enabling operations like filtering and extraction on text/images without explicit code. Implements optimization algorithms that reduce LLM API calls through intelligent batching and caching strategies, delivering the claimed speedups while maintaining accuracy guarantees against reference implementations. Built on a Pandas-compatible API that integrates with standard Python data workflows and supports multiple LLM backends and embedding models via a configurable model abstraction layer.

1,561 stars. Actively maintained with 3 commits in the last 30 days.

No Package No Dependents
Maintenance 13 / 25
Adoption 10 / 25
Maturity 9 / 25
Community 19 / 25

How are scores calculated?

Stars

1,561

Forks

139

Language

Python

License

Apache-2.0

Last pushed

Feb 19, 2026

Commits (30d)

3

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/lotus-data/lotus"

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