Jev in production › Document and record classification

LatteReview

LatteReview v1.3.0 adds Jev as a reviewer that answers typed screening questions with probabilities to classify articles, taking about 0.2s per article (author).

Open on GitHub ↗

0.2smeasured, as published by the source
Use
Document and record classification
Industry
Education and research
Form
Open-source tool
Stage
In production
Listed
2026-09-28
Found via
github
Repository
PouriaRouzrokh/LatteReview
Stars
122
Forks
12
Last push
2026-10-09
Language
Jupyter Notebook
License
none stated

The README opens with

🚨 NEW in v1.4.0: Decision reviewers now also run on Perplexity's pplx-decider and OpenAI's gpt-6-luna through their new Decisions APIs, next to TypeSafe's Jev. In our evaluation on 11,793 articles, pplx-decider ranked articles best, for about $0.05 per 1,000 abstracts. Perplexity's Sonar works as an LLM reviewer too. See What's New and Decision models vs LLM reviewers.

LatteReview is a powerful Python package designed to automate academic literature review processes through AI-powered agents. Just like enjoying a cup of latte ☕, reviewing numerous research articles should be a pleasant, efficient experience that doesn't consume your entire day!

Badge

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

Listed in Jev in production

Also used for document and record classification