RAG & retrieval pipelines
5,258 agents · most starred first
RAG & retrieval pipelines, page 42 of 53
Lightweight pre-RAG routing layer for LLM applications
An efficient python library for building AI applications using the Retrieval-Augmented Generation (RAG) pipeline.
RAG-powered chat interface for career profiles
A tool for cell type annotation using RAG
Connect AI Agents to your Local Documents
ChatBot with Retrieval Augmented Generation
Haystack integration for chonkie
A small library to chunk large files into smaller arrays that can be used for generating RAG embeddings
Universal knowledge base with Qdrant for Claude Code integration
Cited text, vector and graph retrieval for RAG applications on ClickHouse
Production-ready RAG agent for intelligent code retrieval and question answering
RAG-based Q&A system for code repositories with verifiable citations
The Production-Ready Open Source RAG for Education
RAG using Langchain and RAGatouille
A RAG pipeline using ColBERT via RAGatouille
A tool to index Confluence content for RAG
ConsistentRAG: Improving factual consistency in RAG through knowledge graph grounding and multi-agent refinement
A python cookiecutter application to create a new python project for GenAI RAG application that uses poetry to manage its dependencies.
Single-user RAG framework for personal archives. Local-first, MCP-native.
CortexRAG library for quick search and creation of RAG systems
Cognitive Thought and Retrieval Augmented Generation - An advanced AI agent framework combining CoTAEngine and AcceleRAG
A boilerplate for creating agentic RAG applications
CLI tool to scaffold RAG projects
A command-line tool to generate modern RAG applications with various components.
GoodMem knowledge storage and RAG tools for CrewAI agents
FastAPI service for the CSHA AI Agent (RAG-powered question answering over CSHA documents and website data)
RAG-powered Q&A library for the CSM (Communicable State Machine) / LabVIEW knowledge base.
RAG system for Cube.js analytics with vector search capabilities
Use GPT to chat/search your large Cubox datasets
CurateGPT
A customizable RAG pipeline supporting multiple LLM providers and embedding backends.
Domain-Adaptive Meta-Learning RAG Framework for Vertical Domain AI Applications
Databricks RAG Studio Library
DeepLightRAG: High-performance Document Indexing and Retrieval System (use with any LLM)
Haystack integration for Dewey — document store, retriever, and research component
dify's rag patch module
🎧 DJ's Production RAG Pipeline - PDFs → Pinecone → LLM → RAGAS (Sub-10s E2E)
Installable RAG infrastructure for Django projects.
Django app library for RAG integration
OpenAI-backed document retrieval and conversational querying for Django
Multimodal RAG with knowledge graph and contextual intelligence
DNA analysis RAG pipeline powered by LLMs
DocRag: An advanced document search and retrieval system leveraging Retrieval-Augmented Generation for intelligent natural language search across PDF document collections.
Universal RAG system for project documentation
Docling → Chroma → Ollama: Simple RAG pipeline
Docugami partner package for LangChain
RAG toolkit - standalone library for building, searching, and evaluating RAG pipelines
CLI agent for building RAG pipelines
Async HTTP client for interacting with the Donkit ragops-api-gateway
Community Edition CLI agent for building RAG pipelines
A Dropbox langchain integration
DSPy retriever modules for Built-Simple research APIs (PubMed, ArXiv, Wikipedia)
State-of-the-art RAG pipeline from D-Star AI
State-of-the-art RAG pipeline from D-Star AI
Extends RAG with structured query capabilities using dual vector + relational storage
Python SDK for RAG serving optimization — RAGO Pareto scheduler + RAGCache KV cache manager
Batteries-included, importable RAG core.
Easily implement RAG workflows with pre-built modules and context expansion.
Chat with PDFs using LangChain In Few Lines of Code
A reusable and configurable RAG (Retrieval-Augmented Generation) pipeline.
Description
RAG in 3 lines of code — load documents, ask questions, get answers
EasyRAG Python Package
x
This is my tools package
Retrieval-Augmented Generation - (RAG)
A simple package for RAG in the educational context
An LLM-based Retrieval-Augmented Generation (RAG) component for education, supporting problem solving, academic literature analysis, and knowledge Q&A.
LangChain retriever integration for Egnyte document search and retrieval
Elasticsearch-based RAG system with ingest pipeline processing
Embedding-Less retrieval with Iterative Text Exploration (ELITE)
Simplest open source retrieval (RAG) framework
Simplest open source retrieval (RAG) framework
An example of Python package
embedchain is a framework to easily create LLM powered bots over any dataset
Simplest open source retrieval (RAG) framework
embedchainai
Simplest open source retrieval (RAG) framework
ENCOURAGE
Cross-industry compliance patterns for RAG pipelines: FERPA, HIPAA, GDPR, NIST AI RMF, OWASP LLM Top 10, and more. Vector store adapters, framework integrations, and audit logging.
User Manual Search Agent for Enthusiast
Entropy-regulated retrieval-augmented reasoning system inspired by diffusion physics.
the implementation of the eRAG score.
XRAG: eXamining the Core - Benchmarking Foundational Component Modules in Advanced Retrieval-Augmented Generation
Official Python SDK for the RAGify RAG-as-a-Service API
Async-first RAG SDK. The fastest way to build RAG applications with Python.
This is a dockerized RAG FastAPI service with vector store handling.
A Python library for Retrieval-Augmented Generation (RAG) capabilities in LLM applications.
An Efficient Retrieval Augmentation and Generation Framework for Intel Hardware.
CLI tool to manage the lifecycle of a RAG
FastRustRAG: Blazing-fast document deduplication using MinHash and LSH - 50-100x faster than Python
Simplified fine-tuning of retrieval-augmented generation (RAG) systems.
A comprehensive RAG framework with Arabic language support, multi-provider embeddings, and advanced RAG strategies
FERPA-compliant document filter for Haystack RAG pipelines — enforces identity-scoped access control before documents reach the LLM