jev-doc-search

Jev Search is a web search application built by Search1API that uses TypeSafe's Jev to interpret plain-language requests, select search terms, sources, and time ranges, and rank results. It queries general and vertical search engines concurrently, merges results by URL, engine agreement, original rank, and Jev relevance scores, and returns links and snippets with editable filters rather than generated answers. The application streams results as search lanes finish, reports failed sources separately, and can be installed as a browser app; it requires a network connection for searches. The open-source application is MIT licensed and can be self-hosted on Cloudflare Workers with Search1API and a Jev provider such as TypeSafe, Vercel AI Gateway, or Cloudflare Workers AI.

Jevbox is a self-hostable, permission-aware document library from Extend for uploading, visually browsing, and inspecting parsed documents. It uses Extend for document parsing and stores parsed structures, heading outlines, source passages, and original files; supported viewers include PDF, DOCX, XLSX, PPTX, Markdown, code, JSON, CSV/TSV, images, archives, audio, and video, with a safe download fallback for unknown formats. Its JEV retrieval system performs permission-filtered hierarchical beam search across categories, documents, and sections, followed by usefulness scoring of source passages. Users can ask questions through the AI SDK or web chat, view inline citations and source previews, attach accessible documents to scope an answer, and connect through REST and MCP APIs. Uploads can be automatically filed by walking existing folders and validating model-proposed branches, while organization permissions are evaluated through SpiceDB. The repository supports local operation with Node, pnpm, Docker Compose, PostgreSQL, and SpiceDB, and provides Docker, Render, Helm, and AWS/EKS deployment options. It includes organization accounts, invitations, role-based sharing, durable background jobs, queued chat processing, and configurable model providers. Jevbox's original code is licensed under the MIT License; third-party code and assets retain their own licenses.

DocJev is an open-source Python library, CLI, and local app for classifying and splitting PDF, DOCX, and PPTX files with user-written natural-language rules. LiteParse extracts page text locally, then the hosted Jev decision engine assigns document categories or identifies boundaries between component documents; optional LlamaParse tiers provide cloud OCR for difficult inputs. Classification returns a category, probabilities, and review flags. Splitting returns ordered categories and contiguous page ranges, with optional export of each segment as a PDF and review reasons for uncertain boundaries. DOCX and PPTX processing requires LibreOffice, and inference is not offline because Jev is a hosted service. The project is distributed under the Apache-2.0 license.

Jevlike is an open-source research starter for training small models that choose among a variable list of text options. Given a context and an option list, it represents each option as a query, attends to the context tokens to produce an option-specific context vector, applies a shared dot product, and runs a softmax across the options to return probabilities in one pass rather than generating an answer token by token. It provides a trainable byte-level encoder and an optional frozen Hugging Face encoder, with command-line tools for generating synthetic data, training, evaluation, and prediction from JSONL records. The repository also includes a visual option scorer used by Doom and chess controller examples. Training supports CPU, Apple MPS, and CUDA; the default encoder truncates contexts to 192 bytes and options to 32 bytes, and the project requires the complete option list at prediction time. Jevlike is an independent implementation rather than a copy of TypeSafe's commercial Jev model, and its code is released under the MIT License.

kev is an open-source, local Jev-inspired decision model from Jared Palmer. It runs on a laptop and accepts a document or other state plus typed questions, returning calibrated probabilities rather than generated text. It supports yes/no (noul), multiple-choice, and ordered-score questions. The model uses a LoRA adapter and a readout head on a Qwen base model. It packs the state and all questions into one sequence, applies a block-causal mask so each question can see the state but not sibling questions, and performs one prefill pass without decoding. A pointer head scores each option against the question's decision token and applies softmax; the head is trained with cross-entropy on labelled outcomes. The local server exposes a TypeSafe System One-compatible API at POST /v1/systemone, allowing the official TypeSafe SDK to connect by changing its base URL. It also provides model information, option-order permutation, and separate-pass comparison endpoints, plus a local playground. The repository includes 0.5B, 0.6B, 4B, and 8B model checkpoints and recipes for local or Modal-based training and evaluation. Serving is tested on Apple Silicon, with larger checkpoints requiring bf16 on a 32 GB Mac. The server has no authentication and is intended for local use. The project is licensed under Apache-2.0; base models and datasets have separate licenses.