RAG & retrieval pipelines
5,258 agents · most starred first
RAG & retrieval pipelines, page 45 of 53
Interface between LLMs and your data
High-performance document chat and RAG system powered by Ollama
Advanced RAG made simple: LlamaIndex document processing + ZeusDB enterprise vector storage with production-ready performance.
read and cache structured documents from remote for LLM agents
Semantic-aware chunking with provenance tracking for production RAG and LLM data pipelines
Add your description here
State-contracted verification and explainable retrieval gating for agentic RAG.
A Python library for parsing LLM conversation JSON files into RAG-optimized format
RAG llm datatech
Ask questions of LLM documentation using LLM
Talk to your PDFs using an LLM.
Takes a given directory and parses its contents to create a text vectorstore to be consumed in prompts for various LLM models.
LLM with RAG
Это библиотека на Python, предназначенная для упрощения создания и управления моделями генерации с использованием поиска (Retrieval-Augmented Generation, RAG).
A tool plugin for LLM to enable searching over embeddings
RAG from documents in a local directory
Interface between LLMs and your data.
Create and run a local LLM with RAG
100% local RAG for Obsidian, Zotero, and Claude Code — LightRAG + Ollama + MCP
Chat with your documents locally.
Vectorless RAG with MCP — BM25 + temporal KG + link walking. Zero dependencies.
Neural Retrieval-Augmented Generation for GitHub code blocks
Interface between LLMs and your data
Hierarchical Retrieval-Augmented Generation with Haystack
Missing description.
ANOTHER big project.
A python package to index and search documents using GPT3
RAG function file
Local MCP server for RAG over PDFs, DOCX, images, and plaintext files.
基于mcp的rag服务
Add your description here
MCP server for RAG (Retrieval-Augmented Generation) operations with local document indexing - Fork with enhancements
Unified RAG + Memory layer for MCP servers
A core library for Markdown-aware chunking, semantic structuring, vectorization, and RAG retrieval.
Bridge legacy MySQL/MariaDB data into RAG pipelines without migration
MegaRAG: Large-Scale Multimodal RAG for Local File System.
a modular Python framework for semantic search, vector indexing, and retrieval-augmented generation
A Python package for memory-augmented retrieval-augmented generation
MetaRAG: A multi-LLM ensemble Retrieval-Augmented Generation framework with cosine similarity ranking.
A feature-rich, universal RAG library for Python with ONNX-backed embeddings and DuckDB storage
A Python package for MinerU document processing and RAG knowledge base construction
A lightweight RAG (Retrieval-Augmented Generation) library with document loading, chunking, embedding, vector storage, and re-ranking
Multi-modal video analysis with AI-powered RAG
A FastAPI application with Langchain, Weaviate, and MinIO integrations
MiniRAG: Towards Extremely Simple Retrieval-Augmented Generation
A complete RAG pipeline built on Mizan Similarity, MizanEmbedder, and MizanVector.
Complete and unopionated RAG algorithm for LLM
A simple SDK for the mmRag Application, the github for the app can be found here: https://github.com/marcoslashpro/multimodal-rag.git
MODE organizes documents into semantically coherent clusters and uses centroid-based retrieval to deliver scalable, efficient, and interpretable Retrieval-Augmented Generation without relying on large vector databases.
MongoDB-native AI application starter with hybrid search, graphs, and live validation
Local-first Python SDK for adaptive document retrieval.
RAG pipeline library — chunking, embeddings, vector search, and retrieval for the Willian SaaS platform
MCP Server for LightRAG
Add your description here
A hybrid LangChain RAG assistant supporting OpenAI, GROQ, and HuggingFace providers
A fake package to warn the user they are not installing the correct package
Agentic RAG MCP Server — 12 tools for AI-driven multi-round code retrieval that outperforms naive single-shot RAG
Needle RAG tools for Haystack
Balance precise embeddings and context retention with advanced strategies
NeoGPT: Chat effortlessly with Documents, YouTube Videos,Code, and Social Media Chats. Your go-to for quick and smart interactions! 🤖💬
Reference implementation: agentic RAG on Nepal government policy and legal documents. Offline-capable, Nepali + English, hybrid retrieval with citations.
Framework-agnostic RAG pipeline SDK. Plug in any component, swap any stage, configure everything in YAML
Motor Central Python do Nexus RAG
Improvements, optimizations and back-ports for Haystack (with Elastic biases).
nilRAG SDK
nimbus_haystack
A Python library for document-based RAG
Neural Retrieval-Augmented Generation for GitHub code blocks
Subpackage for NVIDIA RAG in NeMo Agent Toolkit
This blueprint serves as a reference solution for a foundational Retrieval Augmented Generation (RAG) pipeline.
nyrag
Local, graph-aware semantic search over linked markdown — Obsidian vaults, OKF bundles, any docs tree. CLI + MCP server.
Obsidian RAG CLI - Ingest and Chat with your notes
RAG system for querying Obsidian notes with SQLite FTS5 and LanceDB
Simple and quick RAG (Retrieval Augmented Generation) using ollama API.
Ask questions about your documents using local LLMs — no cloud, no API keys
A RAG (Retrieval-Augmented Generation) system using Llama Index and ChromaDB
A tool to digest PDF files for Large Language Models and serving them via a REST API, including their source references.
A Python package for integrating Ollama with web search and RAG.
General-purpose RAG MCP plugin — index anything, search with hybrid BM25+semantic, zero-config
RAG pipeline for omnidoc-sdk — intent-aware chunking, evaluation, streaming, graph linking, and vector DB integrations
Multi-Language Voice RAG Framework
Production-ready modular RAG backend — swap Vector DB, LLM, Reranker with 1 line of config
A Python package for RAG Evaluation
OpenAI adapter of rag-control
Build production-ready RAG fast: OpenAI embeddings + ZeusDB vector storage with enterprise performance.
OpenRAG is a comprehensive Retrieval-Augmented Generation platform that enables intelligent document search and AI-powered conversations.
OpenRAG is a comprehensive Retrieval-Augmented Generation platform that enables intelligent document search and AI-powered conversations.
Official Python SDK for OpenRAG API
A document compression and optimization library using Groq LLMs and LangChain
Production RAG system with multi-agent reasoning, knowledge graph, and hybrid search for Oracle DB 26ai
PostgreSQL storage backend plugin for the Orchid AI framework
Custom Knowledge GPT
Hybrid RAG pipeline: semantic + keyword + RRF reranking
Production-ready PDF chunking library with intelligent content filtering and strategic header detection
PyMuPDF Utilities for LLM/RAG
pdfgpt is a Python package that provides users with the ability to engage in natural language conversations with their PDF documents.