RAG & retrieval pipelines
5,258 agents · most starred first
RAG & retrieval pipelines, page 49 of 53
Tera-RAG: Search Billions, Answer Instantly.
Token-Efficient Retrieval Augmented Generation with Graph-based Indexing
rag backend package
Privacy-first RAG CLI — local LLM + SearXNG, zero cloud, zero Docker
Complete In-Device RAG chatbot library, no API keys needed.With 2 lines of implementation in applications.
A minimal Python library for Retrieval-Augmented Generation with codebase indexing and multiple vector store backends
Query-aware semantic chunk selection under LLM context-window budgets.
A collection of database and RAG operation tools
A collection of database and RAG operation tools
Lightweight topic-aware document processing and retrieval
A topological data analysis library for detecting knowledge gaps in RAG systems.
Simple templating and web-source retrieval utilities for RAG.
Paragraph-level compliance audit trails for RAG pipelines
Embed transcript files into ChromaDB and query them with RAG
Lightweight structural RAG library — index documents as trees, query without a vector DB.
A python package for applying TriModal Retrieval-Augmented Generation (RAG) system.
RAG Framework within Reliable input,Trusted output
LangChain integration for TrustRAG — trust-verified retrieval + LangGraph multi-hop agent with trust budget
多论文 RAG 问答系统 - 基于检索增强生成的科研论文问答系统
TuringPulse SDK integration for Haystack
TuringPulse SDK integration for LlamaIndex
Incremental message indexing and querying pipelines using Structured RAG
RAG pipeline: ChromaDB vector search + LLM gateway multi-provider (DeepSeek, OpenAI, Ollama)
A modular, production-ready Retrieval-Augmented Generation (RAG) platform with multi-vector database support
Complete RAG with built-in Ollama + FastAPI + Swagger - Zero Config!
A plug-and-play multimodal Retrieval-Augmented Generation (RAG) framework
A visual sandbox for experimenting with RAG configurations
Here is an enhanced version of the LocalEmbeddings class that provides similar functionality to the OpenAI embedding model and includes more features and detailed comments in English and Chinese
Search code and feature records by meaning through the command line or Model Context Protocol (MCP). Inference runs on your GPU.
RAG (Retrieval-Augmented Generation) System
Qt6 GUI for searching local vector RAG stores with markdown rendering
RAG tool with local FAISS and remote S3 Vectors backends, using Ollama embeddings
Document intelligence API — no vectors, no embeddings, just LLM reasoning over document structure.
A production-ready, provider-agnostic Python SDK for End-to-End RAG pipelines.
Velixar AI memory retriever for LlamaIndex
Lightning-fast RAG for AI agents. ONNX-powered, 4-layer fusion, MCP server. No PyTorch.
Sistema modular de RAG (Retrieval Augmented Generation) para processamento de documentos e geração de respostas
Provenance-first extractive RAG with verbatim source spans and citations
Veritone Agents Toolkit: Knowledge bases
Vietnamese Retrieval-Augmented Generation (RAG) Framework
Minimal Python SDK for interacting with the ViaRAG API
RAG vertical for Victor AI - Document ingestion, vector search, and knowledge management
Retrieve relevant transcript chunks from YouTube videos
Universal multi-domain research system with RAG (Retrieval-Augmented Generation) capabilities
Simple RAG library
TurboPuffer RAG integration for Vision Agents with hybrid search
Video RAG — a Python library for retrieval-augmented generation over video
End-to-end visual document retrieval with ColPali, featuring two-stage pooling for scalable search
ViTax-RAG: Alignment-augmented language model for viral taxonomy classification
Provider-agnostic voice RAG pipeline. Plug in your voice provider, LLM, vector store, and document parsers.
vrag
Subpackage for Arango Integration in vss_ctx_rag
Subpackage for NAT Integration in vss_ctx_rag
Retrieval-Augmented Generation for VTK code and documentation
A RAG PyPI package by Wasif
A search engine using machine learning models and Elasticsearch for advanced document retrieval.
python rag for wechat application
A utlity package for RAG operations
Local self-learning RAG system for Wireshark logs
Agent Framework plugin for RAG
Ask natural-language questions about Singapore Workplace Safety and Health PDFs, with citations.
Haystack RAG components for Twitter search and public user timelines. Not affiliated with X Corp.
Coming Soon
Time-aware uncertainty for RAG — temporal decay of evidence confidence using Subjective Logic
A package to prevent Dependency Confusion attacks against Yandex.
Your tool for RAG on any source of knowledge
Yrag aim to deploy machine-learing model quickly and easily
YouTube transcripts to RAG-ready volumes
Open Q&A dataset for the Swedish construction industry (byggbranschen). 503 bilingual (SV+EN) Q&As grounded in Swedish law. DOI: 10.5281/zenodo.19630803. By Zaragoza AB.
Tiny RAG with implicit knowledge graph, powered by zvec
A modular, production-ready Retrieval-Augmented Generation (RAG) pipeline.
RAG (Retrieval-Augmented Generation) for Zeta MLX
Private AI document assistant — local RAG and Skills. Chat with your documents and generate accurate business documents from them. Zero cloud required.
基于 ZIM 文件和本地大模型的 RAG 知识库问答系统
zk-rag is a command-line chat tool for your zettelkasten
rak — Semantic search over your Zotero library
A simple library for building Retrieval Augmented Generation (RAG) applications.
The Epstein Island review: compare features, pricing, use cases, access model, and alternatives for this Research agent in 2026. The conspiracy theorist's dream - an Epstein Files RAGBOT
Talk to your documents like a friend, get instant answers by voice.
Offline-capable AI virtual assistant client with local RAG fallback and agentic capabilities for AsterMind
Build AI apps that give accurate answers with unlimited context.
Run AI on your own documents, offline and completely private.
Multi-agent RAG system for RBAC-secured financial document Q&A. 72.7% on FinanceBench. Ships a CLI client + self-hostable FastAPI backend.
Haystack Document Store and Retriever backed by Pixeltable multimodal data infrastructure.
A framework that replace traditional RAG pipelines. Ingest any number of documents in multiple workspaces (channels, departments, etc.), index it with BM25, and let the agent search, fetch, and reason over it, exactly like searching the web, but entirely on your machine. No vector store, no embedding needed.
Drop-in RAG SDK for website chatbots
Universal RAG orchestration layer with pluggable vector DB adapters
Document influence analysis for RAG systems using social network centrality measures
TypeScript SDK for [Agentset](https://agentset.ai), an agentic RAG-as-a-service.
RAG pipeline for Claude Code — indexes your codebase and exposes it as an MCP server
CLI tool for generating production-ready FastAPI RAG backend templates
Smart RAG — the retrieval layer for local AI agents. Replaces Tavily + Firecrawl + Perplexity with a single open-source package.
Premium Agentic RAG System for n8n
A simple, unified interface for RAG across multiple vector store backends (txtai, Chroma, Qdrant, LightRAG)
BrainPalace - Typed-memory & retrieval engine for AI agents (BM25 + vector + GraphRAG); code & docs today, more domains coming
Local-first general-purpose RAG with an MCP server, CLI, and web console
Self-hosted document ingestion and hybrid (vector + keyword) retrieval server backed by Postgres/pgvector and Google embeddings.
Visual Retrieval-Augmented Generation — render, embed, index, search
A standalone RAG package for Pydantic AI with support for multiple vector stores.