RAG & retrieval pipelines
5,258 agents · most starred first
RAG & retrieval pipelines, page 46 of 53
Personal RAG toolkit for local document retrieval
RAG scaffolder + embedded library: 7 backbones incl. code-graph/R2R/Onyx, advanced retrieval (contextual, parent-doc, query-expansion+RRF, CRAG), scored advisor, SaaS Query API with auth + rate limit
永續性知識管理系統:基於 Obsidian-NotebookLM-Claude Code 三層防幻覺 RAG 框架
PrivateGPT Python SDK
A library for interfacing with pg_vector for RAG
RAG-enabled agent for code refactoring assistance
Rag
Common utilities
A powerful RAG (Retrieval-Augmented Generation) system built with LangChain, designed as an MCP server for Cursor, VS Code, and other AI assistants
CLI Projects of On-Premise RAG. You can use your own LLM and vector DB. Or just add remote LLM servers and vector DB.
The best RAG interface yet - Built-in vector store, embeddings, citations, and auto-updates
PolarisRAG: Fast and Easy Retrieval-Augmented Generation
An open-source Python toolkit for turning documents, repositories, and web content into a citable, persona-aware assistant
RAG (Retrieval-Augmented Generation) System
A Python SDK for PowerRAG API, providing easy-to-use interfaces for knowledge base management, document processing, chunking, extraction, RAPTOR, knowledge graph, and retrieval.
An open-source python library designed to enhance RAG application performance during data ingestion by skipping files that have already been processed for Dell PowerScale storage.
Proxy-Pointer RAG suite for text, multimodal, and cross-document comparison workflows
A Firebase Firestore RAG system that bridges natural language prompts with structured database queries. It converts user input into intelligent retrieval operations, allowing developers to interact with Firestore using plain English instead of writing queries manually.
A library for building Retrieval-Augmented Generation (RAG) systems using ChromaDB and popular language models (LLMs).
Predictive Retrieval with Intelligent Memory Embeddings
Haystack integration for xLink identity-based authentication (RAG pipelines, 603× faster M2M auth)
PrivateRAG Python SDK with Rust-backed local search and PIR retrieval.
LangChain retriever adapter for the PrivateRAG Python SDK.
Enterprise-ready Retrieval-Augmented Generation framework with superior performance, reliability, and observability
Prompt flow index build
Basic RAG
RAG layer for pydantic-ai agents. Part of pydantic-ai-toolkits.
LLM Powered Advanced RAG Application
A rag api for extending your applicaiton
A reusable RAG core library built on FAISS and Ollama
A document ingestion and RAG query system with FAISS indexing and OCR support
A package to running RAG models, especially for the TREC 2023 Retrieval Augmented Generation (RAG) track.
PyTerrier RAG pipelines
AI RAG bot utilities for OpenAI + LangChain with FAISS
A rag api for extending your applicaiton
A set of helper classes that abstract some of the more common tasks of a typical RAG process including document loading/web scraping.
RAG ingest + retrieval engine — section_table chunker, hybrid retrieval, optional rerank/enrichment
A QA pipeline with RAG capabilities using OpenAI and FAISS
Index-Heavy, Query-Light RAG Engine — Put in docs, ask questions, it just works.
A pipeline for question answering and retrieval-augmented generation (RAG)
A Quick Retrieval-Augmented Generation (RAG) system using transformers.
A lightweight, modular RAG system using ChromaDB
A powerful RAG system for querying code repositories using tree-sitter parsing, LanceDB vector storage, and Qwen models
RAG (Retrieval-Augmented Generation) pipeline implementation
Production-ready RAG + AI Agent platform with FastAPI, LangGraph, and OpenRouter
Python SDK for RAG Agent API - A comprehensive client library for RAG Agent services
Installable RAG + MCP skills framework with a domain-free retrieval harness and Overleaf sync.
Add your description here
This repository includes rag_assistant
Production contract layer for RAG systems — typed, explicit, observable, composable.
Add your description here
RAG Citation is an project that combines Retrieval-Augmented Generation (RAG) with automatic citation generation. This tool is designed to enhance the credibility of AI-generated content by providing relevant citations for the information used in generating responses.
Classical Machine Learning methods for Reterival Augmented Generation
A project to show good CLI practices with a fully fledged RAG system.
CLI tool for RAG over local documents
rag-colls - Implement recent advanced RAG techniques
Indexador de contexto enriquecido para optimización de RAG en LLMs con soporte Agentic Scaffolding, Auto-Sync, Trazabilidad, Persistencia tmux e Integración Claude Code
The rag-core-api contains the API layer for the RAG template for document retrieval, question answering, knowledge base management in the vector database and more.
The rag-core-lib contains the shared components of at least two of the rag libs.
This package offers a lightweight and straightforward solution for implementing Retrieval-augmented generation (RAG) functionality with large language models (LLMs).
A simple and secure RAG framework to rag any LLM model with ease.
A Retrieval-Augmented Generation (RAG) Engine for managing embeddings and similarity search
Fact-checking system using large language models.
RAG pipeline primitives: ingestion, retrieval, context management, and security
CLI tool for evaluating and comparing RAG systems.
rag-house
RAG integration plugin for mloda
A simple RAG implementation for educational purposes implemented by Murat Karakaya Akademi
RAG Knowledge Preparation in Python
Bronze / Silver / Gold 텍스트 처리 실습 라이브러리
RAG system for lecture notes using LangChain and OpenAI
This repository contains a project that implements a Retrieval-Augmented Generation (RAG) system using the LLaMA3 model. The project focuses on creating embeddings for instructions of a professional bioinformatic software to help users conduct biology research.
Multimodal RAG pipeline for low-compute, local, real-world deployment
A simple RAG module with in-memory vector store and OpenAI integration
A simple RAG implementation for educational purposes implemented by Özgür ÖZŞEN
RAG workflow Optimizer based on Bayesian Optimization
AI-powered document analysis and query generation tool with RAG capabilities
A library for Retrieval-Augmented Generation with Azure OpenAI
Production-grade RAG: BGE-M3 + FAISS + BM25 + RRF + Reranker + HyDE
A pipeline for question answering and retrieval-augmented generation (RAG)
RAG client
Improve your RAG pipelines for your python repositories.
A tool for crawling, indexing, and semantically searching web content with RAG capabilities
A flexible RAG (Retrieval-Augmented Generation) experimentation framework
Semantic code chunking for LLM processing with policy-based configuration
Add a short description here!
RAGssistant: A RAG Assistant for your tasks
Find stale RAG chunks by age, version, and freshness requirements. Python port of @mukundakatta/rag-staleness-auditor.
A lightweight Python starter for retrieval-augmented generation workflows.
Generate startup ideas grounded in real YC data using Retrieval-Augmented Generation (RAG).
FAISS-based RAG utility library
An extensible, abstract framework for building Retrieval-Augmented Generation (RAG) systems with unlimited technique possibilities
rag tokenizer for RAGFlow
This is my tools package. Rag tool for now. Initial version with dynamic lists
A library for building Retrieval-Augmented Generation pipelines.
Interactive terminal debugger and optimizer for RAG chunking pipelines
Simple RAG for URLs - 1-line setup, LangChain/LlamaIndex ready
rag007 — multi-backend retrieval-augmented generation with LangGraph