User repository on GitHub
A production-grade RAG system with optimised latency and local vector database.
- Forks
- 0
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.Homepage
Jev directory
CommunityJev Tools & CLIs
TechBook RAG
A 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.
- Stars
- 0
- Language
- HTML
- Reading time
- 2 min
- Published by
- Community
- Author
- Rudra-P11
- Last verified
- Oct 2026
Highlights
- Covers 11 technical books split into 2,810 chunks with adaptive RAG, hybrid dense and BM25 search and reciprocal rank fusion.
- A JEV System-1 decision engine sits in app/decision/jev_engine.py behind the retrieval pipeline.
- Stack badges list Python 3.11+, FastAPI 0.109+, Qdrant, BGE-small 384-dimension embeddings and gpt-4o-mini.
- The README links a live architecture showcase and an RRF k=60 forensic case study on rudra-p11.github.io.
- GitHub topics include jev, jev-model, rag-evaluation, llm-optimization and voice-ai; the repo has 0 stars and no license.
Watch out
README and GitHub metadata reviewed 2026-10-17; the excerpt stops after the quick links, so the adaptive retrieval logic, the JEV decision steps, setup instructions and any results are not visible, and no license or benchmarks are listed.
Questions about this entry
Short answers drawn from the linked project or page.
A technical knowledge assistant that runs adaptive RAG over 11 technical books, or 2,810 chunks, pairing hybrid dense and BM25 search with a JEV System-1 decision engine.
The README badge labels the decision model JEV System 1 and links to app/decision/jev_engine.py; the captured text does not show how that engine queries the model, so the integration is unverified.
It combines hybrid dense and BM25 search with reciprocal rank fusion, grouped in the description under Joint Evidential Valuation, and a case study documents the fusion with k=60.
Badges list Qdrant as the vector database, BGE-small 384-dimension embeddings, gpt-4o-mini as the language model and FastAPI 0.109+ running on Python 3.11 or newer.
Yes, the README links a live interactive architecture showcase and an RRF k=60 forensic case study, both hosted on rudra-p11.github.io rather than in the repository itself.
GitHub metadata lists an HTML repository with 0 stars and 0 forks, created and last pushed 2026-10-09, with no license recorded in the digest.
The excerpt ends right after the quick links, so architecture details, evaluation numbers, installation steps and any screenshots are not available to review here.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
X: A RAG loop where Jev decides what is real
X: Measuring what Jev does in a RAG pipeline
X: Jev-powered reranking for RAG. Likitd_’s jev-ranker uses Jev to rerank results in a RAG pipeline.
X: Coverage is not product value
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/deepdocPythonAn open-source platform for creating, distributing, and running sovereign EU-compliant LLMs: one Rust binary with OpenAI- and Ollama-compatible APIs, decisions answered as probabilities in milliseconds, and an audit trail designed for the EU AI Act.
Jev Tools & CLIs#community#github#local-llm
Community
eullm/eullmPython
eullm/eullmPythonA 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 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-workbenchPythonA 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.
Jev Tools & CLIs#community#github#python
Community
wdwd200/jevPython
wdwd200/jevPythonA desktop app for dictation, audio-file transcription and meeting notes on Windows, macOS and Linux, using local Whisper models or the OpenAI API, with an opt-in MCP server and local history API so agents can search saved transcripts.
Jev Tools & CLIs#community#catalog-import#logicrw
Community
knuckles92/openwhisperPython
knuckles92/openwhisperPythonFrom 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.