RLAMA

RLAMA (Retrieval Augmented Local Assistant Model Agent) is an open source artificial intelligence solution that integrates local AI models for creating, managing, and interacting with Retrieval Augmentation Generation (RAG) systems. It allows users to build powerful document question and answer systems, supporting multiple document formats, advanced semantic segmentation, and local storage and processing.

RLAMA can be installed and used via the command line. Users can create RAG systems by indexing document folders, query documents in interactive sessions, and manage RAG systems using commands such as `rlama rag`, `rlama run`, `rlama list` and `rlama delete`. RLAMA Unlimited provides a coding-free visual interface for building RAG systems.

Create, manage and interact with RAG systems
Supports multiple document formats (.txt, .md, .pdf, etc.)
Advanced semantic segmentation strategy
100% local processing, no data sent externally
Web crawler creates RAG directly from website
Directory monitoring enables automatic RAG updates
Hugging Face integration, supporting 45,000+ GGUF models
HTTP API server for application integration
Cross-platform support (macOS, Linux, Windows)
Supports OpenAI models and Ollama
AI agents and teams support complex tasks
Visual RAG builder (RLAMA Unlimited)