User repository on GitHub
- Forks
- 0
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Tools & CLIs
Jev Context Selector
A local experiment bench that uploads PDFs, extracts and chunks their text, then generates Full, Jev and RAG comparison records for consecutive questions, storing workspaces, chunk rules and answer history in a SQLite file at .runtime/jev_context.sqlite3.
- Stars
- 0
- Language
- Python
- Reading time
- 2 min
- Published by
- Community
- Author
- wdwd200
- Last verified
- Oct 2026
- Languages
- Python
- Capabilities
- Open sourceRuns locally
Highlights
- Upload PDFs into reusable workspaces; chunking rules, counting scope and config fingerprint are snapshotted per workspace.
- Questions run in modes jev, full, rag or all, producing Full, Jev and explicitly-unconfigured RAG comparison records.
- SQLite state defaults to .runtime/jev_context.sqlite3; answers keep the selection made at the time, even after rechunking.
- API covers workspaces, per-document add and delete, rechunk, question runs, run history and retries of selection or generation.
- Deployment ships deploy/Caddyfile and deploy/jev.service; the app listens only on localhost 8001 and is exposed on port 8081.
Quickstart
bash
python -m pip install -r requirements.txt
python -m uvicorn app.main:app --reloadWatch out
README reviewed 2026-10-17; it is written in Chinese and its setup assumes a Windows shell (copy instead of cp). The digest cuts off inside the API list, so response schemas, environment variables and licensing are not documented; 0 stars.
Questions about this entry
Short answers drawn from the linked project or page.
A local experiment bench: upload PDFs, extract and chunk their text, then generate Full, Jev and explicitly-unconfigured RAG comparison records for consecutive questions.
Questions run in modes jev, full, rag or all; the Jev runs use the decision model's passage selection over the current active chunk set.
Install requirements with pip, copy .env.example to .env, then start python -m uvicorn app.main:app --reload; the app listens only on localhost port 8001.
In SQLite by default at .runtime/jev_context.sqlite3, holding workspaces, chunk rules, questions, runs, selections and answer history.
Old chunks and old selections are preserved; adding beyond the limit is rejected without truncation, and selections made before a rechunk can no longer answer.
Workspaces with per-document add and delete, rechunk, questions, run history, and retries that either reuse the selection or re-select first; the captured list cuts off mid-entry.
The repo ships deploy/Caddyfile and deploy/jev.service; the app stays on localhost 8001 and is exposed on port 8081, which both cloud and system firewalls must allow.
More Jev resources like this
A local deep-research tool that turns your own PDF, DOCX, PPTX, image, TXT, or Markdown files into a structured report, using TypeSafe's Jev to rerank Qdrant chunks and verify evidence coverage while an LLM plans and writes.
Jev Tools & CLIs#community#github#python
Community
oqura-ai/deepdocPython
oqura-ai/deepdocPythonA local workbench that pairs OpenCV vision with Laya or Jev decision models: images are segmented and measured, hard rules settle the numbers, and the model gives the verdict — with one-click installers and an "open-source JEV" training path served at /v1/systemone.
Jev Tools & CLIs#community#github#python
Community
uu889/laya-opencvPython
uu889/laya-opencvPythonA proof-of-concept HTTP service for constrained decisions with a local MLX model: send text or JSON plus typed choice, score, or noul questions and it returns probabilities over the answers you declared — no generated text, no parsed model JSON.
Jev Tools & CLIs#community#github#python
Community
snellingio/system-onePython
snellingio/system-onePythonFills job applications page by page in a browser from a JSON profile, with plain rules answering common fields, a local decision model choosing among your own facts, and submit gated until you opt in.
Jev Tools & CLIs#community#github#job-applications
Community
Noface07/SystemOne-ApplyPython
Noface07/SystemOne-ApplyPythonA technical knowledge assistant that runs adaptive RAG over 11 technical books (2,810 chunks) with hybrid dense and BM25 search, reciprocal rank fusion and a JEV System-1 decision engine over a local vector database.
Jev Tools & CLIs#community#github#rag
Community
rudra-p11/techbook-ragHTML
rudra-p11/techbook-ragHTMLA local workbench for System One-style models on Apple Silicon Macs: it serves Laya through MLX or Core ML behind a Jev-compatible /v1/systemone endpoint, proxies other Jev-compatible servers like Jeff and Kev, recommends models and evaluates them on Japanese data.
Jev Tools & CLIs#community#github#python
Community
katya4oyu/systemone-workbenchPython
katya4oyu/systemone-workbenchPythonFrom 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.