llm-reader provides a command-line interface that processes diverse documents—PDFs, presentations, Markdown, and HTML—from local files or URLs. Upon providing a document, it extracts text, splits it into semantic chunks, and creates an embedding-based vector store. Using your configured LLM (OpenAI or alternative), users can issue natural-language queries, receive concise answers, detailed summaries, or follow-up clarifications. It supports exporting the chat history, summary reports, and works offline for text extraction. With built-in caching and multiprocessing, llm-reader accelerates information retrieval from extensive documents, enabling developers, researchers, and analysts to quickly locate insights without manual skimming.