self-rag

🩺 Agentic RAG chatbot for medical Q&A on Diabetes, Hypertension & Asthma. Powered by a LangGraph multi-step reasoning agent, hybrid retrieval (dense + BM25 + Cohere rerank), Groq LLaMA 3.3 70B, Qdrant, and Supabase. FastAPI backend on Cloud Run.

A self-correcting RAG agent in LangGraph — routes questions, grades its own retrieval, falls back to web search, and refuses answers that aren't grounded in its sources.

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

Agentic RAG with self-reflection, query decomposition, iterative retrieval and hallucination detection — CRAG + Self-RAG + Corrective RAG in production

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.

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

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

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

Enterprise Agentic Corrective RAG (CRAG) & Self-RAG platform powered by LangGraph cyclic state machine, IBM Docling table-aware chunking, Qdrant hybrid vector search, Heterogeneous Model Routing (Groq/Ollama), and Arize Phoenix OpenTelemetry observability.

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

An agentic Self-RAG system that answers biomedical research-verification questions using a LangGraph pipeline — retrieves from PubMed abstracts, grades its own retrieval, checks for hallucination, and abstains when evidence is weak.

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.

Advanced RAG Implementations

A self-reflective academic research assistant built with Self-RAG, LangGraph, Google Gemini, and ChromaDB. Features automated PDF ingestion, document relevance grading, hallucination detection, web search fallback, and a Streamlit UI for grounded Q&A over research papers.

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.

Self-RAG API for NexaAI ? retrieval-gated, context-graded, and self-correcting QA bot built with FastAPI, LangGraph, pgvector, and Google Gemini.

Hands-on implementation of modern Retrieval-Augmented Generation (RAG) systems using LangChain, LangGraph, vector databases, RAGAS, and Agentic AI workflows.

企业级 Agentic RAG 技术文档问答系统

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.

RAG pipeline notebooks: document loaders, chunking, embeddings, Self-RAG & Corrective RAG with LangChain and LangGraph