RAG & retrieval pipelines
5,258 agents · most starred first
RAG & retrieval pipelines, page 43 of 53
My tiny package
My tiny package
My tiny package
A library for efficient Retrieval-Augmented Generation research
Flexible RAG (Retrieval-Augmented Generation) framework for building AI applications.
Fully automated RAG SDK - Initialize with a directory and start querying
Retrieval augmentation for humans
A minimal ForestRAG package
A forgetting layer for RAG systems — heat-based decay, tiered storage, graceful eviction.
A simple RAG API - build a question and answer interface to your own content in minutes
Local-first RAG indexer for repos, docs, and PDFs
Fast fragment-based retrieval for MT prompting with word-level inverted index, query-time fragment sizing, and masked fallback.
Hybrid retrieval-augmented generation — graph × vectorstore → enriched context. Placeholder release.
Lightweight RAG library for internal knowledge systems
Production-grade Python toolkit for building GDPR-compliant RAG systems with automatic PII detection, audit trails, and compliance validation
It is a rag standalone package
getbased-rag — standalone RAG knowledge server (formerly the Electron-bundled Lens)
Graph Foundation Model for Retrieval Augmented Generation
An open-source, high-transparency modular RAG framework for AI/ML applications
Enterprise-grade knowledge loading, indexing, and search for Python
Interface between LLMs and your data
GPT RAG (Retrieval-Augmented Generation) common library
GPT RAG (Retrieval-Augmented Generation) common library
A Gradio custom component to display RAG sources
A simple package for implementing RAG
Fast grep-based document search for LLM agents. No embeddings, just speed.
Production-grade Graph RAG with RL self-improvement and multi-hop reasoning
Gragal API Client
A Python package for hybrid Graph + Vector RAG using completely Open Source tools
GraphRAG: A graph-based retrieval-augmented generation (RAG) system.
Graphrag and vectorstore for all LLMs
Graphreader Implementation
High-performance RAG pipeline for GRASS GIS with >90% accuracy and <5s response time
Privacy-first, fully offline AI document assistant secured by tiered safety guardrails
Official Python SDK for GuidedMind RAG API
guinsoft_rags
Python SDK for the Gushwork Retrieval-Augmented Generation (RAG) API
Python SDK for the Gushwork Retrieval-Augmented Generation (RAG) API
Local-first agentic RAG with citations - hybrid search, reranking and multimodal retrieval over your own documents, no database server required
Local-first agentic RAG with citations - hybrid search, reranking and multimodal retrieval over your own documents, no database server required - Minimal dependencies
LLM advisors with varied personalities and knowledge bases
A Python package for building RAG systems with HawkinsDB and multiple data source integrations
Haystack node for checking the entailment between a statement and a list of Documents
An Lemmatizing node for Deepset Haystack
This component filters documents based on a threshold percentage, ensuring only the documents above the threshold get passed down the pipeline
Advance hybrid rag imeplementation using Postgresql Vector DB
A hierarchical RAG framework for chunks retrieval.
AI-Powered Legal Document Retrieval Engine based on Hierarchical Clustering & RAG
CrewAI tool for searching the HiveMind shared knowledge commons
LangChain retriever for HiveMind shared knowledge commons
Add your description here
A smart toolkit for HTML cleaning and pruning for RAG systems.
A RAG system that operates like a human
A Python Toolkit for RAG to build a efficient and productive applicaton.
A small example package
HydRAG — Multi-Headed Retrieval-Augmented Generation with CRAG supervision
Reserved package name for future project
Hierarchical RAG: FAISS retrieval + subtree expansion over a parent/child chunk hierarchy.
Wandering RAG CLI tool
Markdown based RAG system
A Retrieval-Augmented Generation (RAG) system that indexes the OWASP Web Security Testing Guide (WSTG) into a vector database, providing instant access to security testing methodologies via MCP (Model Context Protocol) for Claude Code integration.
Add your description here
RAG utilities for igbot
Indox Retrieval Augmentation
Indox Retrieval Augmentation
A RAG (Retrieval-Augmented Generation) library for document processing and retrieval.
An integration of Intersystems Iris with Haystack for datastore and retrievers
Enterprise RAG pipelines with native IRIS vector search. 6 production implementations with RAGAS evaluation, LangChain, AWS/Azure configs. No external VectorDB required.
SAGE RAG Framework - Document loaders, chunkers, retrievers for RAG pipelines
RAG benchmarking suite for the SAGE ecosystem
ISE3309 AI 智能助教系统 - 基于级联式 RAG 架构的课程助教
Reverse RAG database - index questions, not chunks
Interface between LLMs and your data, added UniversalFilter for MetadataFilters
Jaguar document store for Haystack framework
A minimal Python project template built with Poetry.
Retrieval Augmented Generation (RAG) starter library
Private local RAG assistant for Outlook • Calendar • Jira • Confluence
Convert json to string for RAG applications.
Maximal token-efficient RAG for headless Claude. Uses your existing claude CLI; auth-agnostic; slice-level retrieval.
智能 Agent,支持多渠道对话和 RAG 能力
Just do RAG without pain.
OCR Vector Database - Document parsing, semantic segmentation, and vector search
KAITO RAG Engine Client
A library for KitchenAI to use LlamaIndex
Local RAG System for Claude Code — Hybrid search + Cross-encoder Reranking + 13 MCP Tools + 20 Format Parsers. Zero external servers.
A package for extracting and querying knowledge using GPT models
A Retrieval-Augmented Generation (RAG) framework with MongoDB and Sentence Transformers
A search engine using machine learning models and Elasticsearch for advanced document retrieval.
A flexible Retrieval-Augmented Generation framework by Ksschkw
Layout Aware RAG
A label-driven RAG pipeline built on top of paralabelgen.
Uma biblioteca Python leve para RAG (Retrieval-Augmented Generation) compatível com LangChain, que não requer dependências pesadas como NumPy ou bibliotecas de ML.
A modern and secure RAG chatbot using FastAPI and LangChain.
Tools package for various database and RAG operations
Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and Llama) RAG and Agent app with langchain