Jev directory
CommunityJev Repos & SDKs
JEV YouTube URL Classification
Python pipeline that extracts YouTube video and Shorts metadata with yt-dlp and classifies topics, content formats, and educational value using TypeSafe AI's Jev decision model. Packaged and managed with Astral's uv; requires a TYPESAFE_API_KEY.
- Stars
- 2
- Reading time
- 2 min
- Published by
- Community
- Added
- Oct 2026
Highlights
- Extracts YouTube video and Shorts metadata with yt-dlp before classification.
- Classifies topics, content formats, and educational value with Jev.
- Dependencies include typesafe-sdk, yt-dlp, pandas, and python-dotenv.
- Documented run command: uv run --env-file .env python jev_classify.py
- uv sync --frozen --no-dev installs the locked environment without re-resolving.
Questions about this entry
Short answers drawn from the linked project or page.
Initialize the project with uv init, add the dependencies (typesafe-sdk, yt-dlp, pandas, python-dotenv), then launch it with uv run --env-file .env python jev_classify.py.
It needs TYPESAFE_API_KEY available in the environment. The documented run command passes --env-file .env so the key is present in os.environ even before load_dotenv() executes.
It extracts YouTube video metadata via yt-dlp and categorizes topics, content formats, and educational value using TypeSafe AI's calibrated Jev decision model.
Yes. uv.lock pins every sub-dependency to exact versions, hashes, and platform markers, and uv sync --frozen --no-dev installs those pinned versions without re-resolving or modifying the lockfile.
Yes. The digest documents uv venv followed by uv pip install -r requirements.txt, and uv run --env-file .env to load environment variables without activating the virtual environment.
The provided material does not state a license. Check the repository for its terms before redistributing or deploying the code.
It depends on yt-dlp metadata extraction and a TypeSafe API key, so it is not suited to offline use or to sources other than YouTube videos and Shorts.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
YouTube: Building a contextual brand-safety scorer on Jev from scratch.
YouTube: Kubernetes admission control with a decision model, fail-closed.
YouTube: Jev explained for routing and judging, with a comparison against LLMs.
YouTube: The AI Daily Brief maps six categories of real Jev use ten days after launch.
More Jev resources like this
A zero-dependency, copy-anywhere Python service that implements the quick-coarse-verdict-first idea: a deterministic lexicon plus heuristics turn text and structured questions into labels on a controlled vocabulary in micro-to-millisecond time.
Jev Repos & SDKs#community#github#python
Community
junnyofficial/nano_jevPython
junnyofficial/nano_jevPythonChinese-language GitHub project that wraps Jev's /predict endpoint behind a CLOUDSOA-HMAC-SHA256 gateway signature. Ships jev_predict_common.py for signed requests and jev_client.py, a CLI with weather and web rerank examples.
Jev Repos & SDKs#github#python#sdk
Communitydulin20240919-dot/jev
Open multilingual System 1 decision models with published checkpoints for choice, score and noul questions, plus a router that dispatches each request to the right checkpoint in one forward pass.
Jev Repos & SDKs#community#python#open-models
Community
NandhaKishorM/layaPython
NandhaKishorM/layaPythonA System One layout optimizer for decision-model workloads: it reorders rows and fields so a prefix-caching backend reuses input computation, then returns per-record decisions in original order. Its bundled backend serves AutoTrust JEV-9B through vLLM.
Jev Repos & SDKs#community#github#python
Community
0814wdwd/solo_jevPython
0814wdwd/solo_jevPythonA local server and Python package that runs open models with Hugging Face Transformers or PyTorch and returns Choice, Score, and Noul answers read from next-token logits instead of generated JSON.
Jev Repos & SDKs#community#python#open-models
Community
featherless-ai/simple-jevPython
featherless-ai/simple-jevPythonAn open, non-autoregressive System One model with published weights and a TypeSafe-compatible /v1/systemone API; the 395M-parameter OptionMarker checkpoint scores discrete and ordinal questions locally.
Jev Repos & SDKs#community#python#open-models
Community
wfzyx/vonPython
wfzyx/vonPythonFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.