Local RAG CLI Tool 'raggy' Based on Ollama Released

·2026.09.10 00:57

Key point

A CLI tool named 'raggy' has been released, performing RAG on local documents using Ollama and hybrid indexing.

Details

Developer Paul Knysh has released raggy, a lightweight CLI tool built on Ollama. This tool is designed to perform Retrieval-Augmented Generation (RAG) on local documents, with embedding generation and hybrid database operations (vector + BM25 index) processed entirely locally for data privacy.

Key Features

Hybrid Search: Combines vector search and BM25 keyword search to improve search accuracy.
Support for Various Inputs: Supports common document formats, with images or scanned documents automatically converted to text via OCR.
Flexible Answer Generation: The answer generation stage can use a local LLM or connect to remote models via API keys.

ollama open-source local-llm rag vector-database cli-tool

Read originalShare on Threads

This summary was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.

Our guide explains how the AI works. Report summary errors, attribution issues, or removal requests via Contact.