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

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

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]

MBSPro is an AI-assisted billing copilot for Australian GPs. It turns clinical notes (typed; optional STT) into top-N MBS item suggestions with explicit rule/ethics checks, then generates a FHIR-ready claim and draft clinical docs (e.g., referral/care plan), with a lightweight compliance dashboard for errors/rejects and revenue snapshots.

Context-aware tool for automated BDD test generation and execution using RAG, VectorDB, and LLaMA.

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

Advanced RAG Implementations

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.

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

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.

This project is built using Python and the Flask web framework, providing a user-friendly web interface for interacting with the RAG system. The core logic, including document processing, embedding generation, retrieval strategies (Self-RAG and Agentic RAG), and integration with the Gemini API, is organized within the utils directory.

podcast chatbot using the ell llm framework uses self RAG with memory