Jev in production › SQL and data pipelines

jevframe

Python library adds a .jev accessor to pandas and Polars DataFrames that sends each row as state with typed questions to Jev and returns labels, scores and full probability distributions as columns.

Open on GitHub ↗

The source publishes no measured number.
Use
SQL and data pipelines
Industry
Data and analytics
Form
Open-source tool
Stage
In production
Plugs into
pandas, Polars
Listed
2026-09-22
Found via
github
Repository
ktaletsk/jevframe
Stars
21
Forks
1
Last push
2026-09-24
Language
Python
License
MIT
jevframe screenshot
assets/jevframe/preview.png in the ktaletsk/jevframe README, MIT; shown from GitHub.

The README opens with

jevframe is a Python library for AI text classification, sentiment analysis, and scoring in pandas and Polars DataFrames. Ask natural-language questions about each row using TypeSafe Jev and get structured results with complete probability distributions.

Label customer reviews, categorize support tickets, flag urgent messages, or grade answers against a rubric. Results are ordinary Series and DataFrames, with preserved row order and pandas indexes. Evaluate several questions together per row, with bounded async concurrency and optional caching.

Badge

For the project's own README, linking back here:

Listed in Jev in production

Also used for sql and data pipelines