ragbits and Controllable-RAG-Agent
These are complements: ragbits provides the foundational building blocks and framework for constructing RAG systems, while Controllable-RAG-Agent offers a specialized, graph-based agentic RAG implementation that could be built on top of or integrated alongside ragbits' components.
About ragbits
deepsense-ai/ragbits
Building blocks for rapid development of GenAI applications
Provides modular Python packages for LLM integration (100+ models via LiteLLM), RAG pipelines with 20+ document formats, and multi-agent coordination using the A2A protocol and Model Context Protocol. Features type-safe prompt execution with Python generics, support for Qdrant/PgVector and other vector stores, Ray-based distributed document ingestion, and OpenTelemetry observability—installable as granular components (core, agents, document-search, evaluate, guardrails, chat, CLI) rather than monolithic framework.
About Controllable-RAG-Agent
NirDiamant/Controllable-RAG-Agent
This repository provides an advanced Retrieval-Augmented Generation (RAG) solution for complex question answering. It uses sophisticated graph based algorithm to handle the tasks.
Implements a deterministic graph-based agent that breaks down complex questions through multi-step reasoning—anonymizing queries to avoid pre-trained knowledge bias, decomposing tasks into retrieval or answer generation steps, and verifying outputs against source documents. Built on LangChain and FAISS with Streamlit visualization, it processes PDFs into chunked content, LLM-generated summaries, and quote databases to enable grounded, hallucination-resistant responses.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work