← all repositories

abgulati/LARS

A local LLM application that enables RAG-based document querying with detailed citations including page numbers, text highlighting, and in-response document readers.

LARS
Velocity · 7d
+0.9
★ / day
Trend
steady
star history

LARS runs LLMs locally on the user’s device and allows document uploads for grounded AI responses. The application implements Retrieval Augmented Generation to reduce hallucinations and includes a distinctive citation system that provides specific document names, page numbers, text highlights, and images for every response. It supports a wide range of file formats including PDFs, Word documents, Excel files, PowerPoint presentations, and images, making it a comprehensive document-grounded AI tool.

heatdrop uses Google Analytics to see which pages get read — nothing else. Your call. How we handle data.