ragbits and agentic-rag-for-dummies

These are complementary but positioned at different abstraction levels: ragbits provides lower-level building blocks for production RAG systems, while agentic-rag-for-dummies offers a higher-level reference implementation using LangGraph that demonstrates how to assemble those patterns into a complete agentic system.

ragbits
74
Verified
agentic-rag-for-dummies
64
Established
Maintenance 20/25
Adoption 10/25
Maturity 25/25
Community 19/25
Maintenance 17/25
Adoption 10/25
Maturity 15/25
Community 22/25
Stars: 1,627
Forks: 136
Downloads:
Commits (30d): 24
Language: Python
License: MIT
Stars: 2,743
Forks: 383
Downloads:
Commits (30d): 11
Language: Jupyter Notebook
License: MIT
No risk flags
No Package No Dependents

About ragbits

deepsense-ai/ragbits

Building blocks for rapid development of GenAI applications

This project offers robust building blocks for quickly creating Generative AI applications. It allows you to feed various document types, like PDFs and spreadsheets, into an AI system to get accurate, context-aware answers. It's designed for AI developers and engineers looking to build scalable and reliable AI assistants, chatbots, or intelligent search tools.

Generative AI development Large Language Model deployment AI agent orchestration Enterprise search Chatbot creation

About agentic-rag-for-dummies

GiovanniPasq/agentic-rag-for-dummies

A modular Agentic RAG built with LangGraph — learn Retrieval-Augmented Generation Agents in minutes.

This project helps developers build advanced AI assistants that can intelligently answer questions using custom data. It takes your documents (like PDFs or Markdown files) and processes them into a searchable format, then uses an AI to interpret user questions, find relevant information, and generate clear, coherent answers. It's designed for AI developers or data scientists who want to create sophisticated conversational agents.

AI-development conversational-AI information-retrieval large-language-models agent-systems

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