ragbits and oreilly-retrieval-augmented-gen-ai
One is a set of building blocks for GenAI application development, while the other is an O'Reilly course demonstrating how to augment LLMs with real-time data, thus making them ecosystem siblings since one provides the components for the concepts taught in the other.
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 oreilly-retrieval-augmented-gen-ai
sinanuozdemir/oreilly-retrieval-augmented-gen-ai
See how to augment LLMs with real-time data for dynamic, context-aware apps - Rag + Agents + GraphRAG.
Implements end-to-end RAG workflows using vector databases (Pinecone), multiple LLM providers (OpenAI, Anthropic, Gemini, Cohere), and LangGraph for orchestration with built-in evaluation components. Covers advanced patterns including knowledge graph-based retrieval (GraphRAG with Neo4j), embedding fine-tuning with synthetic data, multimodal search, and agentic workflows with semantic re-ranking.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work