RAG & retrieval pipelines
5,258 agents · most starred first
RAG & retrieval pipelines, page 21 of 53
A Genshin Impact Book Question Answer Project supported by LLM
A command line utility that queries websites for answers using a local LLM
An experimentation platform for comparing 10+ RAG retrieval, chunking, generation, and caching strategies.
Retrieval-Augmented Generation system: ask a question, retrieve relevant documents, and generate precise answers. RAG demo: document retrieval + LLM answering
TinyRag is a minimal Python library for retrieval-augmented generation. It offers easy document ingestion, automatic text extraction, embedding generation, and retrieval with vector stores. Designed for quick setup and flexible provider configuration, TinyRag enables fast, contextual responses from language models.
用最少的代码实现完整的 RAG 引擎,零依赖,纯 JavaScript,详细中文注释,适合学习和理解 RAG 原理。
Welcome 👋 to the WetroCloud SDK. An easy-to-use toolkit for integrating with the WetroCloud API. Manage collections, work with resources, and run AI-powered queries including Retrieval-Augmented Generation (RAG)
RagE (RAG Engine) - A tool supporting the construction and training of components of the Retrieval-Augmented-Generation (RAG) model. It also facilitates the rapid development of Q&A systems and chatbots following the RAG model.
RAG/StructRAG using SQLite, C# and Ollama
End-to-end architecture for document-centric conversational AI
Muzlin: a filtering toolset for semantic machine learning
Semantic search and RAG summarization in local PDF book collection with .NET (Semantic Kernel) / QDrant and Ollama.
Typescript client for Unbody's API
A small Next.js app which utilises search results to feed context to the LLM.
Privacy-First Retrieval-Augmented Generation (RAG) app for macOS. Search, index, and chat with your local documents directly on your Mac. No cloud, no tracking — everything runs fully offline for maximum privacy.
TinyRAG is a minimalist Python library that enables developers to rapidly build RAG-powered applications. It supports a flexible range of LLM endpoints and provides a clean API for combining retrieval with generation.
基于 LangGraph + MCP + FastAPI(SSE) + Streamlit 的本地知识库问答助手
Multi-step Agentic Self-Corrective RAG with websearch
Building a chatbot using Streamlit, LangChain, and SQLite
Backend source code of the wahl.chat platform. Our mission: Make politics more accessible.
TypeScript client for Graphlit Platform
This project leverages SOTA techniques to retrieve relevant information from large datasets and generate coherent, contextually accurate text that includes image data references.
Advanced NLP system with multilingual sentiment analysis and retrieval-augmented question answering. Built with PyTorch, Transformers, FAISS, and FastAPI.
Offline Survival AI & Knowledge Base. Run air-gapped LLMs (Ollama) connected to Wikipedia, iFixit, and StackOverflow via Kiwix. A complete digital prepper system for rebuilding civilization without internet.
Production-ready RAG movie recommender with multi-agent architecture, OpenAI embeddings, and conversational web UI. Ask naturally about movies - get intelligent recommendations instantly!
This project leverages the Phi3 model and ChromaDB to create a Retrieval-Augmented Generation (RAG) application.
A comprehensive, containerized Second Brain Database built with FastAPI, MongoDB, and Redis. Features advanced RAG, family management, and micro-frontend architecture.
simple rag with c#
Ontbo: Cognitive Context API for LLMs - retrieve only relevant facts → fewer hallucinations, lower latency & cost.
A production-ready RAG (Retrieval-Augmented Generation) API built with .NET 8. Upload documents, ask questions, and get AI-powered answers with source citations and streaming support.
Packages and SDKs for Agentset.ai
Local RAG Chatbot with Ollama on Mac
AI-powered document query system using LangChain, ChromaDB, and OpenAI for efficient RAG-based information retrieval.
Modern, header-only C++ library for Retrieval-Augmented Generation (RAG) with Ollama-hpp.
State of the art search based RAG coding agent, with morphic, ollama, openweb-ui and faiss
Enterprise Knowledge Base Platform (RAG + ACL + Evaluation + Kafka pipeline) Website
PDF Ninja is a modern AI-powered PDF SaaS built with Next.js, enabling seamless document viewing, conversion and secure authentication.
Fine-tuned Llama 3.1 8B · QLoRA · RAG serving stack · FastAPI · Pinecone · Azure
A production-ready, embeddable AI chatbot widget built with Cloudflare Workers that can be integrated into any website with a single script tag. Features real-time streaming responses, RAG-powered FAQ answers, session persistence, and dark/light mode support.
This guide covers project structure, environment setup, running Qdrant (Docker), starting the Web App, setting OpenAI secrets, ingesting sample data, and testing with the provided question list.
A chat bot for domain specific knowledge. Headless RAG for the enterprise. RAG as a service.
An AI-powered Multi-Agent Research Assistant built with Generative AI, Agentic AI, LangGraph, RAG, Persistent Memory, FAISS, and FastAPI. It supports multi-format uploads, intelligent PDF analysis, and expert-like Q&A via Researcher, Summarizer, Critic, and Editor agents—offering deep, contextual, and interactive research insights.
This repository contains a Streamlit-based Document Question Answering System implementing the Retrieve-and-Generate (RAG) architecture, utilizing Streamlit for the UI, LangChain for text processing, and Google Generative AI for embeddings.
SymRAG adaptively routes queries through neuro-symbolic, neural, or hybrid paths based on complexity and system load, ensuring efficient and accurate RAG for diverse QA tasks.
A Genshin Impact Question Answer Project supported by Qwen1.5-14B-Chat
📑 DAYA: Document Aware hYbrid Architecture, A RAG Pipeline for Illustrated Documents (PPTs).
Simple TypeScript library with RAG primitives for embeddings, chunking, storage, and semantic retrieval.
Add a cited agent/knowledge folder to Eve agents.
🤖 An open-source Agentic RAG framework powered by ReAct Agent — LLM autonomously orchestrates hybrid retrieval, deep reading, and web search for traceable, evidence-first Q&A over your documents.
RAG with SQLite, provide easy setup for document website
Production grade RAG SaaS with multi-tenant auth, semantic caching, LLMOps observability (Prometheus/Grafana), per-tenant token cost tracking, and rate limiting - inspired by Kapa.ai (YC S23)
[EMNLP 2025] M-LongDoc: A Benchmark For Multimodal Super-Long Document Understanding And A Retrieval-Aware Tuning Framework
Project once, retrieve distillations, create tools: a pre-loading retrieval architecture and tool builder for distributable, source-grounded assistants for complex, repeatable work in your known task domains.
docker agent-demo-track region:us
gradio region:us
gradio region:us
gradio region:us
docker region:us
streamlit region:us
safetensors text-generation en dataset:FreedomIntelligence/RAG-Instruct arxiv:2501.00353 base_model:meta-llama/Llama-3.1-8B
A interctive offline chatbot vault that stores your personal documents, notes, and files locally, no internet or servers required.
本地 AI Agent 桌面应用(Windows)。Spring Boot + Vue 3 + JCEF,内置 MCP 工具、本地知识库与 RAG 检索,完全离线运行。
A harness for question-answering agents over your own documents — bounded context, bounded cost, every claim cited.
Exam-scored knowledge brains for AI agents: paste a docs URL, get a searchable brain over MCP with a measured score and known gaps. AGPL.
Arabic-Egyptian RAG assistant for Hikvision technical support using BM25, multilingual embeddings, OpenRouter, and Streamlit.
A native macOS reader that treats a PDF like a book — realistic page turns, 9 reading themes, and AI author personas grounded in your own library. SwiftUI + AppKit, BYOK.
"A Retrieval-Augmented Generation (RAG) chatbot built with LangChain, Streamlit, and FAISS, designed to answer questions accurately from custom documents (PDFs)"
A visual webapp that helps you figure out how to ingest, extract, and RAG. Design a pipeline, see the tradeoffs, get an architecture recommendation, export a plan.
This Python project demonstrates semantic search using MongoDB and two different LLM frameworks: LangChain and LlamaIndex. The goal is to load documents from MongoDB, generate embeddings for the text data, and perform semantic searches using both LangChain and LlamaIndex frameworks.
Self-hostable RAG and semantic search infrastructure. High-performance, low-cost, and up in minutes.
Legal Intelligence Terminal — Hybrid RAG for UAE & Indian Law, Taxation & Compliance. Built by Evolucent AI, engineered by Eulogik.
A reproducible, evaluated, secured, observable, and deployable Agentic Retrieval-Augmented Generation (RAG) platform for continuously changing organizational knowledge.
PostgreSQL full-text + pgvector cosine retrieval with reciprocal-rank fusion, bound filters, and a key-free local demo.
Search and cited RAG answers over files, folders and databases: keyword, boolean, BM25, TF-IDF, semantic and hybrid from one import, a CLI or an HTTP API.
Company knowledge. With receipts. A self-hosted AI workspace for documents, connected business data, and answers grounded in evidence.
Corax-RAG (Strata) — a lightweight Agentic RAG framework for QQ chats: long-term memory, identity isolation, and a virtual-filesystem shell with snapshot approval.
✴MyNexus: 你的阅读Agent
Customer service RAG API with FastAPI, PostgreSQL + pgvector, a cross-encoder reranker, answer guardrails, a feedback-aware cache, and a Streamlit reaction dashboard. Runs fully on open-source models.
[SIGMOD2027] CE-RAG4EM: Cost-Efficient RAG for Entity Matching with LLMs: A Blocking-based Batch Processing Framework
Local RAG with a fine-tuned Indonesian Llama 3.1 8B (GGUF) and nomic-embed on GPU, evaluated on in-domain, compound, and out-of-domain questions with and without a similarity threshold.
Teaching material of the HPI AI Service Centre for the RAG workshop series (RAG II and III): marimo notebooks on chunking, embeddings, retrieval metrics, document types, OCR and RAGAS evaluation
RAG evaluation and observability lab.
Custom Trained LLM application with Llama, and grounding via RAG. This project uses Streamlit to create a simple UX LLM based chatbot with Llama3 & RAG grounding on Stehen Hawking's books
A simple AgenticAI RAG agent showcasing autonomous reasoning and decision-making by integrating thought, logic, and action in real-time tasks.
Chat with Lex! A RAG app, using HyDE with milvus DB for vector store, VLLM for LLM inference, and FastEmbed for Embeddings!
AI cup contest
SitemapRAG is an open-source tool designed to leverage your website's sitemap as a Retrieval-Augmented Generation (RAG) source. It empowers developers to build intelligent, context-aware applications by extracting, indexing, and querying content directly from a sitemap.
In this we implements a Retrieval-Augmented Generation (RAG) based conversational AI agent designed for intelligent knowledge extraction from PDF documents. Leveraging LangChain and Google’s Gemini LLM
Agentic RAG demo for public patent text (Streamlit + hybrid retrieval + verification)
Metadata filtering in RAG application
A RAG application feeding on board games running locally. Create a database with your favorite board game rulesets and query the RAG model to get answers to your questions!
基于 ChatGLM 等大语言模型与 Langchain 等应用框架实现,开源、可离线部署的 RAG 与 Agent 应用项目
This repository contains practical examples and sample projects demonstrating how to use Moorcheh, a framework for building AI-powered chat applications.
An open source template of Custom Content AI Chatbot built with LangChain, Upstash and Next.js, deployed to Fly.io.
LLM chatbot example using OpenVINO with RAG (Retrieval Augmented Generation).
AI chatbot 🤖 for chat with CSV, PDF, TXT files 📄 and YTB videos 🎥 | using Langchain🦜 | OpenAI | Streamlit ⚡
hnn-llm streamlines access to Human Neocortical Neurosolver (HNN) guide with advanced search mechanisms and efficient information retrieval.
Documind is an intelligent desktop assistant that allows users to upload documents (PDF, DOCX, TXT) and ask natural language questions about their contents. It leverages local LLMs via Ollama, integrates advanced OCR for scanned files, and uses semantic indexing with LangChain + FAISS to deliver fast, context-aware answers.
A basic "retrieval augmented generation" (RAG) app with Langchain and OpenAI in Python + Pinecone + Gradio app.