A complete collection of RAG interview questions, answers (200 questions & 12 RAG types), system design scenarios, architecture patterns, and production-ready concepts.

Training code for advanced RAG techniques - Adaptive-RAG, Corrective RAG, RQ-RAG, Self-RAG, Agentic RAG, and ReZero. Reproduces paper methodologies to fine-tune LLMs via SFT and GRPO for adaptive retrieval, corrective evaluation, query refinement, self-reflection, and agentic search behaviors.

Self-Reflective Question Answering for Biomedical Reasoning. GRPO fine-tuning via QLoRA & Unsloth with rewards for correctness, relevance, groundness, utility & XML structure. Structured think → answer → self-reflection with context grading, relevance assessment & groundness evaluation. DeepEval LLM-as-a-Judge (GEval, Faithfulness, Relevancy).

Evidence-synthesis RAG assistant for TCM practitioners — hybrid vector + knowledge graph retrieval over 17 classical texts, with query classification, self-critique verification, and blind A/B arena evaluation.

生产级 3GPP 5G 规范 RAG Agent：自然语言提问，回答带段落级原文引用 + 严格 grounding，覆盖 Rel-18/19 全部 TS。

Production-ready Retrieval-Augmented Generation (RAG) system with hybrid retrieval, Self-RAG agent workflows, cross-encoder reranking, and comprehensive benchmarking.

Backend Of STELLA that run SELF Retrieval-Augmented Generation [Senior Project]

AutoDocThinker is a production-ready Agentic RAG system that ingests PDFs, DOCX, URLs, and raw text into a Hybrid Search index (ChromaDB + BM25 + RRF + CrossEncoder), then answers natural language queries through four selectable LangGraph workflows — Naive, Advanced, CRAG, and Self-RAG.

Advanced RAG with hybrid search, query classification, answer fusion, and self-correction

Agentic RAG Multi-Agent Exam Tutor — LangGraph multi-agent system for Marine Structures | DeepSeek V4 Pro | BGE-M3 | ChromaDB | Self-RAG | FastAPI

A hybrid Retrieval-Augmented Generation (RAG) system

Advanced RAG Implementations

Advanced RAG Q&A for PDFs. Delivers structured, educational answers with diagrams & follow-ups via Streamlit. Powered by LangGraph, featuring hybrid retrieval, cross-encoder reranking, and Self-RAG verification using Groq Llama 3.3 70B & local Ollama embeddings. Includes persistent chat & semantic search.

https://files.rochiey.dev/s/APqtCyBpZXiwTHZ

A progressive learning lab implementing 8 RAG pipelines from scratch to Agentic, Self-Correcting, and Evaluated RAG using LangChain, LangGraph, CRAG, & RAGAS.

Advanced RAG using langgraph which uses websearch functionality to produce relevant documents.

A Streamlit-based Self-RAG-inspired evidence QA assistant with retrieval, evidence critique, answer revision, and reflection.

Hallucination-free AI medical assistant using Self-RAG verification on Llama-2-7B

Production adapters and pipelines for PortfolioCore. Vector stores (pgvector, Qdrant), graph stores (Neo4j), embedders (OpenAI), Broadway pipelines, advanced RAG (Self-RAG, CRAG, GraphRAG, Agentic), multi-graph federation, and observability.