Projects with this topic
-
PaveDB is an inspectable retrieval database for AI applications: text-backed vector search with source provenance and query replay, embedded or over HTTP.
Website: https://pavedb.org/
Updated -
A robust CLI that turns recordings and PDFs into clean, structured Markdown notes end-to-end.
Audio — chunks with configurable length and overlap, transcribes via a dedicated Whisper STT endpoint or cascades to OpenAI-compatible multimodal and Native Ollama backends.
PDF — text PDFs pass through pdftotext straight to refinement; scanned PDFs are auto-detected by character count, rendered to page images, and read by a vision model (or tesseract via an explicit --ocr escape, never silently).
LLM refinement — dedupes overlapping boundaries and formats the raw transcript into clean notes.
Resumable content-addressed cache — keyed by input hash with per-chunk/page signatures; a changed parameter invalidates only what depends on it.
Config resolves CLI > env var > settings file > defaults, including persistent chunk sizes. Python 3.12, built with uv, 147 tests at 100% coverage. Architecture is protocol-based and documented via TIPs (docs/).
Updated -
Advanced enterprise Free Open Source DMS (document management system).
Updated -
-
-
Euro-Office (OnlyOffice) CLI-Wrapper – Office-to-PDF or any-to-any conversion and document building on Linux.
Updated -
Self-hosted, API-first reporting server for managing and rendering JasperReports templates.
Updated -
Diff two versions of a text-layer PDF; produce a redlined output PDF plus a structured change report
Updated -
-
Create PDF and SVG animations from graphics files and inline graphics using LaTeX
Updated -
A sleek really small GTK4/Python GUI tool that instantly converts Unicode emojis into perfectly cropped vector PDF graphics, enabling native and hassle-free emoji usage in standard LaTeX documents.
Updated -
-
High-fidelity command-line PDF conversion using Microsoft Office on Windows. (proof of concept; development has been discontinued)
Updated -
A CLI text-to-speech tool using the Kokoro model, supporting multiple languages, voices (with blending), and various input formats including EPUB books and PDF documents.
Updated -
Offline PDF to XLSX/CSV/JSON converter for Yandex Bank statements (deposit Сейв + card account). Конвертер банковских выписок Яндекс Банка из PDF в Excel — всё локально.
Updated -
-
Turn a folder of lab programs into a print-ready record: syntax-highlighted source, real inputs, real captured output. https://www.npmjs.com/package/labpress
Updated -
Downloader for MacMillan Education / MacMillan Everywhere eBooks to PDF
Updated -
Open-source OCR app for Linux. Extract editable text from scanned PDFs, photos and images with Tesseract, translate it and export to .txt. MIT.
Updated