Local RAG System Based on Ollama

Empower Your Data with Local AI Capabilities

RAGO is a fully local RAG system that provides powerful document retrieval and intelligent Q&A through Ollama, protecting your data privacy and improving work efficiency

Core Features

RAGO provides a complete local RAG solution, from document processing to intelligent Q&A, meeting all your needs in one stop

Fully Local

No external APIs required, protecting data privacy and security, all processing done locally

Multi-format Support

Supports TXT, Markdown and other document formats, easily build knowledge base

High Performance

Based on SQLite vector database, providing fast and accurate semantic search

Local LLM

Call local models through Ollama, no dependence on cloud services

Web Interface

Built-in modern web interface, supporting drag-and-drop upload and real-time chat

Dual Interface

Provides both CLI tools and HTTP API to meet different usage scenarios

Quick Installation

Use Go command to install RAGO with one click and quickly start your local RAG journey

Installation Command

$ go install github.com/liliang-cn/rago/cmd/rago-cli@latest
Installing...
$ rago-cli --help
Show help information

Basic Configuration

Create configuration file to customize RAGO behavior and parameters

Create config.toml

config.toml
[server]
port = 7127
host = "localhost"
enable_ui = true
cors_origins = ["*"]

[ollama]
embedding_model = "nomic-embed-text"
llm_model = "qwen3"
base_url = "http://localhost:11434"
timeout = "30s"

[sqvect]
db_path = "./data/rag.db"
top_k = 5

Why Choose RAGO?

RAGO is not just a RAG system, but the perfect combination of your data security and AI capabilities. We focus on local deployment to ensure your sensitive data never leaves your control.

🔒 Data Privacy Protection - All data processing is done completely locally
⚡ High Response Speed - Go implementation, low memory usage
🔧 Easy to Extend - Modular design, supports custom functions
📱 Cross-platform Support - Supports Windows, macOS, Linux
🎯 Accurate Retrieval - Intelligent search based on semantic understanding
🚀 Quick Deployment - Docker support, one-click startup
$ rago ingest ./docs/
✓ Processing documents: 15 files
✓ Generated vectors: 1,234 chunks
$ rago query "What is RAG?"
🤖 RAG (Retrieval-Augmented Generation) is an AI technology that combines information retrieval and text generation...

Ready to Get Started?

Download RAGO now and experience the powerful features of local RAG system, making your document data more valuable