agentic-rag-for-dummies and autonomous-agentic-rag
These are complements positioned at different points on the learning-to-production spectrum: the first provides an educational, modular framework for understanding agentic RAG fundamentals with LangGraph, while the second builds on those concepts with a self-improving pipeline for more advanced autonomous workflows.
About agentic-rag-for-dummies
GiovanniPasq/agentic-rag-for-dummies
A modular Agentic RAG built with LangGraph — learn Retrieval-Augmented Generation Agents in minutes.
Built on LangGraph's agentic framework, this system implements hierarchical parent-child chunk indexing for precision search paired with context-rich retrieval, conversation memory across turns, and human-in-the-loop query clarification. Multi-agent map-reduce parallelizes sub-query resolution with self-correction and context compression, while supporting pluggable LLM providers (Ollama, OpenAI, Anthropic, Google) and Qdrant vector storage—all orchestrated through observable graph execution with Langfuse integration.
About autonomous-agentic-rag
FareedKhan-dev/autonomous-agentic-rag
Self improving agentic rag pipeline
Implements a multi-agent architecture with specialist agents orchestrated via LangGraph that collaboratively generate outputs, evaluated across multiple dimensions (accuracy, feasibility, compliance) by a custom scoring system. An outer evolutionary loop uses diagnostician and SOP architect agents to iteratively refine standard operating procedures based on performance vectors, identifying Pareto-optimal trade-offs. Integrates LangChain/LangGraph for orchestration, Ollama for local LLMs, FAISS and DuckDB for multi-source knowledge indexing (PubMed, FDA guidelines, MIMIC-III clinical data), and LangSmith for observability.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work