Graph RAG workshop using Kùzu and LanceDB for hybrid RAG
-
Updated
Jan 12, 2025 - Python
Graph RAG workshop using Kùzu and LanceDB for hybrid RAG
A hybrid retrieval system for RAG that combines vector search and graph search, integrating unstructured and structured data. It retrieves context using embeddings and a knowledge graph, then passes it to an LLM for generating accurate responses.
BestRAG: A library for hybrid RAG, combining dense, sparse, and late interaction methods for efficient document storage and search.
Code from the ODSC Agentic Graph RAG workshop combining vector, FTS & graph retrieval for RAG. Includes observability and guardrails for evaluating outputs.
🚀 HAG: Next-Gen AI | Neo4j + Weaviate Fusion | Dual-Similarity Retrieval | 100% Local & Private | Graph Intelligence Meets Vector Search
A Visual and Interactive tool to learn and explore Hybrid RAG (Vector + Graph DBs) and Agentic RAG systems.
PromptWeaver: RAG Edition helps design effective prompts for Traditional, Hybrid, and Agentic RAG systems. It offers templates, system prompts, and best practices to improve accuracy, context use, and LLM reasoning.
A genral RAG Search chatbot, with SoTA RAG techniques such as HyDE, Hybrid retrieval with BM25 + RRF and Cross encoder reranking. Evaluated on the BEIR scifact dataset and compared all the different pipelines i tried along the way
This repository consists the source code of Curriculum Compass: A Hybrid RAG Chatbot Empowering Northeastern Students in Course Selection.
A personal RAG based chatbot that uses llama-3.1-8B-instrcut-Q4_K_M.gguf model as its llm and ChromaDB to store and repond to the user on their day to day queries. Intelligent session management with smart information retention across sessions and better retrieval of summaries with hybrid retrieval
Exploring and comparing RAG techniques for financial documents- including naive RAG, knowledge graph-powered RAG, and long-context (no chunking) RAG
A custom hybrid RAG-based chatbot for exam preparation. WIP
AI-powered personal finance assistant using Tabular RAG to turn natural language questions into safe SQL queries and clear answers expense data.
UrduWhiz is an AI-powered web app that makes Urdu storybooks accessible and interactive. Users can upload scanned Urdu PDFs, which are processed with OCR and semantic search. The app summarizes, indexes, and stores the content for fast retrieval, allowing users to ask natural language questions in Urdu and receive intelligent context aware answers
A production-ready Retrieval-Augmented Generation (RAG) system with advanced features including hybrid retrieval, adaptive feedback loops, comprehensive evaluation, and explainable AI logging.
compare between the Result of Vanilla RAG (BM25 + dense + RRF) VS Hybrid RAG (BM25 + dense reranker + RRF ).
AI-powered smart api for document processing with RAG pipeline for insurance decisions
A collection of mini-projects covering sub-topics in Langchain
A powerful web-based application designed to answer questions based on the content of uploaded PDF documents. This project leverages a Hybrid Retrieval-Augmented Generation (RAG) approach, combining the strengths of vector-based semantic search and keyword-based search to deliver accurate and relevant responses
Add a description, image, and links to the hybrid-rag topic page so that developers can more easily learn about it.
To associate your repository with the hybrid-rag topic, visit your repo's landing page and select "manage topics."