cognita and oreilly-retrieval-augmented-gen-ai
The first tool is an open-source framework for building modular RAG applications, while the second is a demonstration of augmenting LLMs with real-time data using RAG, agents, and GraphRAG; thus, the second project could be considered an example or tutorial for concepts that might be implemented using the first framework.
About cognita
truefoundry/cognita
RAG (Retrieval Augmented Generation) Framework for building modular, open source applications for production by TrueFoundry
This framework helps developers quickly build, organize, and deploy Retrieval Augmented Generation (RAG) applications that can answer questions based on specific documents or data. It takes in various document types (text, audio, video) and uses them to power a question-answering system. Data scientists and machine learning engineers who need to move RAG prototypes from notebooks to production-ready systems would use this.
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