RAGLight and ragctl

RAGLight provides the modular framework for building RAG systems while ragctl offers command-line tooling to test and optimize those pipelines—making them complements that work together rather than alternatives.

RAGLight
68
Established
ragctl
50
Established
Maintenance 20/25
Adoption 10/25
Maturity 16/25
Community 22/25
Maintenance 6/25
Adoption 6/25
Maturity 22/25
Community 16/25
Stars: 655
Forks: 99
Downloads:
Commits (30d): 33
Language: Python
License: MIT
Stars: 18
Forks: 7
Downloads:
Commits (30d): 0
Language: Python
License: MIT
No Package No Dependents
No risk flags

About RAGLight

Bessouat40/RAGLight

RAGLight is a modular framework for Retrieval-Augmented Generation (RAG). It makes it easy to plug in different LLMs, embeddings, and vector stores, and now includes seamless MCP integration to connect external tools and data sources.

RAGLight helps you quickly build a chatbot that can answer questions using your own documents, like PDFs, Word files, or code. You feed it your collection of files, and it produces a chat interface where you can ask questions and get answers grounded in your specific information. This is ideal for anyone who needs to quickly create a custom AI assistant that understands their unique knowledge base.

knowledge-management custom-chatbot document-intelligence information-retrieval AI-assistant-creation

About ragctl

datallmhub/ragctl

A powerful CLI tool to manage, test, and optimize RAG pipelines. Streamline your Retrieval-Augmented Generation workflows from terminal.

This tool helps AI engineers and developers prepare various documents like PDFs, Word files, and images for use in Retrieval-Augmented Generation (RAG) applications. It takes raw documents, extracts text using advanced OCR, intelligently breaks them into meaningful chunks, and exports them in formats like JSON or directly into a vector store. This streamlines the crucial data preparation step for building robust RAG systems.

AI-engineering NLP-data-prep document-processing RAG-application-development vector-database-ingestion

Scores updated daily from GitHub, PyPI, and npm data. How scores work