A Golang CLI for converting PDF files to JSONL for efficient use with LLMs
Go CLI with built-in OCR fallback when JinaAI and Firecrawl already handle this.
Developers building RAG pipelines or LLM applications
JinaAI · Firecrawl · LangChain PDF loaders
Splits LLM Markdown into chat-sized WhatsApp messages while preserving lists, links, emails, tables and even Spanish punctuation. It applies a priority chain of processors — structural splits first, semantic fallbacks — and ships with zero dependencies plus 100% test coverage, which makes it a pragmatic, focused tool for messaging pipelines.
Client-side WASM conversion is nice, but CyberChef and pdf2go already do this.
ModernBERT disambiguates kanji readings by context, unlike basic dictionary lookup tools.
DeepSeek-OCR–inspired visual tokenization saves 40% tokens vs text, with academic validation.
WASM-based conversion keeps sensitive PDFs on-device when cloud tools aren't an option.
llms.txt generation from whiteboards is clever, but Notion AI already shares context between chats.
