What it is
jevframe is a Python library for AI text classification, sentiment analysis, and scoring in pandas and Polars DataFrames. It lets users ask natural-language questions about each row and get structured results with complete probability distributions.
How it uses Jev
Jev evaluates typed questions (Choice, Score, Noul) on a state built from selected row context. Results are returned as ordinary Series/DataFrames with preserved row order and indexes. Multiple questions per row share one request; bounded async concurrency and optional caching are supported.
Primitives:choicescorenoul
Technique worth stealing
Evaluate several questions together per row with bounded async concurrency and optional memory caching.
Try it
uv add 'jevframe[pandas]==0.1.0' and set TYPESAFE_API_KEY, or run the marimo demo without a key.
Evidence
Each line is one question put to Jev about the README. ≥ 0.60 reads as yes, ≤ 0.40 as no; in between Jev is not making a call.
- Jev-centricyes0.94
- Shows a System One patternyes0.69
- Handles uncertaintyno0.06
- Measuredno0.06
- Runnableyes0.95
- Worth recommendingunclear0.45
- Model replicano0.05
- Problem scopescore on a 0–2 scale1.39
- About Jevyes0.98
Signals by Jev jev-1.13.0, card written by DeepSeek V4.1 Flash from the README on 21 Sept 2026.