User repository on GitHub
Utility library to help process large context inputs in limited context window scenarios
- Forks
- 1
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Repos & SDKs
Context Atlas
A PHP library that structures a document section by section by the kind of text each part is, then, given a question, gathers the few hundred tokens that answer it instead of the whole document, aimed at improving RAG chunking. Powered by Jev.
- Stars
- 0
- Language
- PHP
- License
- MIT
- Reading time
- 2 min
- Published by
- Community
- Author
- Fox-Islam
- Last verified
- Oct 2026
- Languages
- PHP
- Capabilities
- Open sourceRequires API key
Highlights
- Structures each document section by text kind, then answers questions from the few hundred relevant tokens rather than the whole document.
- Targets the chunk-size problem where chunks mix unrelated paragraphs, split sentences or drag in the next section's heading.
- Positioned as a layer that improves RAG implementations; the README keeps the vector store in the loop.
- Powered by Jev, with the README linking the TypeSafe docs.
- MIT-licensed PHP library; the repository had gained one fork by 2026-10-16.
Watch out
README reviewed 2026-10-17; the captured text stops mid-sentence, gives no benchmarks or accuracy numbers, and does not spell out how it calls Jev or what a run costs, so the RAG-improvement claim is the author's framing.
Questions about this entry
Short answers drawn from the linked project or page.
A PHP utility library for large inputs in limited context windows. It structures a document section by section by text kind and, given a question, gathers the few hundred tokens that answer it instead of sending the whole document.
The README says the library is powered by Jev and links to the TypeSafe documentation. The captured text does not detail the request shape or how many decisions it makes per document.
No. The README asks the question itself and answers that it exists to improve RAG implementations by handling the processing that makes RAG work well, keeping your vector store in the loop.
Chunk management: a chunk holding two unrelated paragraphs, cutting a sentence in half, or carrying the next section's heading. Bigger chunks repeat the same problems in new places, and too-big chunks defeat the purpose.
PHP, per the repository's language metadata, and the ability to call Jev; the captured README does not spell out key setup, dependencies or install commands, so check the repository before adopting it.
No benchmarks, accuracy figures or pricing appear in the captured text, so the value over plain chunking is not quantified anywhere in the digest.
It is Fox-Islam's MIT-licensed PHP repository, created 2026-10-11 and last pushed 2026-10-16, with zero stars and one fork; the README documents the library's purpose but not benchmarks.
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 Python library shaped like the re module that finds, replaces, splits and extracts text by meaning: loose finders propose spans and Jev judges each one with a probability. Every match stays a verbatim slice of the input with its offsets, so it can be wrong but never invented.
Jev Repos & SDKs#community#github#python
Community
nothans/ex-regexPython
nothans/ex-regexPythonA PHP monorepo that adds typed decision APIs on top of structured output, unified inference, retrieval and an agent SDK: the Polyglot Decision API can call the TypeSafe provider and return probabilities for noul questions, alongside OpenAI, Anthropic, Gemini and Ollama drivers.
Jev Repos & SDKs#community#catalog-import#logicrw
Community
cognesy/instructor-phpPHP
cognesy/instructor-phpPHPA Python retrieval framework that wraps an existing base retriever and asks TypeSafe Jev after each pass whether the accumulated evidence is sufficient or another retrieval round is useful. Jev judges sufficiency, coverage, relevance, redundancy and missing information.
Jev Repos & SDKs#community#github#python
Community
Aditya-on/JevRetrieverPython
Aditya-on/JevRetrieverPythonA Laravel-ready PHP SDK for Laya, a self-hosted multilingual decision engine described as a Jev AI alternative: classify text in 100+ languages and get typed enums, ints and bools back without paying per-token fees.
Jev Repos & SDKs#community#github#php
Community
marcreichel/laya-phpPHP
marcreichel/laya-phpPHPA Python batching proxy for Jev that returns Apache Arrow streams, with Python and JavaScript SDKs. It packs many independent states and questions into each TypeSafe API call or runs them concurrently, then emits the answers as an ordered Arrow IPC stream with the schema first.
Jev Repos & SDKs#community#github#python
Community
columnar-tech/jevaroPython
columnar-tech/jevaroPythonLocal-first knowledge search with seven selectable pipelines: BM25 plus Jev reranking is the default vector-free path, plus agentic, embedding-hybrid, taxonomy, gate and line-search modes. Reranks up to 30 candidates in one batched set of Jev Noul relevance questions and streams cited answers from a configurable model.
Jev Integrations & Adapters#community#rag#retrieval
Community
aifabrice/jev-ragPython
aifabrice/jev-ragPythonFrom 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.