self-rag

A complete collection of RAG interview questions, answers (548 questions & 41 RAG types), system design scenarios, architecture patterns, and production-ready concepts.

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。

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.

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).

Learn Retrieval-Augmented Generation (RAG) from scratch by manually building chunking, embeddings, retrieval, reranking, answerability, local generation, Graph-RAG, and Self-RAG.

Self-correcting agentic RAG with LangGraph — combines Adaptive, Corrective, and Self-RAG. Routes queries, grades retrieved documents, and checks answers for hallucinations. Runs fully local on Ollama.

Self-RAG: a self-reflective RAG system built from scratch in LangGraph. Grades its own retrieved documents and generated answers (relevance, grounding, usefulness), then self-corrects via bounded regenerate/re-retrieve loops. MAANG-standard structure with config, custom exceptions, logging, and tests.

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

企业级 Agentic RAG 技术文档问答系统

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

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

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

A verification gate combining Chain-of-Verification, Self-RAG, and Constitutional AI. Cited verdicts, policy checks, CI exit codes.

Agentic RAG system with five workflow modes from Naive to Deep, routing each question to the cheapest path that answers it well, fusing dense and BM25 retrieval through Reciprocal Rank Fusion with CrossEncoder reranking, verifying groundedness and citations, and gating risky answers behind a human-in-the-loop approval queue.

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

A modular Self-Reflective RAG framework with built-in critique system. Features 3 adaptive critics ([Retrieve], [ISSUP], [ISCOMP]) for on-demand retrieval, factual verification, and completeness checking. Works with any document source with full reasoning trace visibility.

Prometheus is an open-source, multi-agent AI research engine that uses Corrective RAG (CRAG), hybrid retrieval, and Neo4j graph-based contradiction detection to autonomously synthesize complex biomedical literature.

검증까지 내장한 한국어 문서 RAG 파이프라인 — Hybrid 검색(BGE-M3+BM25+RRF) · CRAG · Self-RAG · Critic 재생성 · RAGAS 평가