AgenticRAG is an advanced AI-powered retrieval-augmented generation (RAG) Agent designed to provide users with an interactive and intelligent conversational experience
-
Updated
Jul 21, 2025 - Python
AgenticRAG is an advanced AI-powered retrieval-augmented generation (RAG) Agent designed to provide users with an interactive and intelligent conversational experience
A simple NaiveRAG pipeline.
ทำนอกเวลา อยากไปสาย AI
A comprehensive research project comparing different Retrieval-Augmented Generation (RAG) techniques applied to medical question-answering in obstetrics.
Production-grade Naive RAG pipeline built from scratch: PDF loading, recursive chunking, HuggingFace embeddings, FAISS (cosine) retrieval with score-threshold filtering, and grounded Groq LLM generation with source citations. Every design decision documented — from the FAISS cosine gotcha to empirical threshold tuning.
A lightweight, high-performance, production-ready Retrieval-Augmented Generation (RAG) system built strictly using Google Gemini 3.6 Flash, Chroma DB, SentenceTransformers (all-MiniLM-L6-v2) Embedding Model, and Python, built entirely without LangChain or third-party orchestration frameworks.
Explore the evolution of Retrieval-Augmented Generation (RAG) through three progressively sophisticated pipelines built with Langflow: Naive RAG (basic retrieval), Advanced RAG (semantic chunking + re-ranking + hallucination control), and Modular RAG (multi-store routing with LLM-powered query classification).
Pipelining, and implementing RAG, and evaluating comparative performance across enhancements
To associate your repository with the naive-rag topic, visit your repo's landing page and select "manage topics."