RAG & retrieval pipelines
5,258 agents · most starred first
RAG & retrieval pipelines, page 18 of 53
Improved RAG retrieval by adding context to the chunks and performing Hybrid Search (Vector Semantic Search + BM25 Keyword Search) and Reranking.
RAG heuristic to heal damaged business records - assuming its lost, then educated guesses become better than nothing.
Source code of the wahl.chat platform. Our mission: Make politics more accessible.
RAG-API: A production-ready Retrieval Augmented Generation API leveraging LLMs, vector databases, and hybrid search for accurate, context-aware responses with citation support.
Clinical Rag AI
Offline AI assistant - chat with your documents locally. No cloud, no API key, no data leaks. Built with Python + FastAPI + Ollama + LangChain.
Embeddable, self-hosted AI chat widget for your docs — a single Cloudflare Worker that retrieves your documentation and streams cited OpenAI answers, behind layered abuse controls.
gradio region:us
docker region:us
llamafile rag text-generation pl base_model:speakleash/Bielik-4.5B-v3.0-Instruct base_model:finetune:speakleash/Bielik-4.5B-v3.0-Instruct
Multilingual NCERT doubt solver powered by an OPEA-based RAG pipeline, delivering curriculum-grounded, citation-backed answers in English, Hindi and Urdu with zero hallucinations.
A hybrid RAG chatbot that answers financial and tax questions using structured data, regulatory documents, and AI-powered retrieval. Built with Django, FAISS, NetworkX, and OpenAI.
RAG heuristic to heal damaged business records - assuming its lost, then educated guesses become better than nothing.
Header-aware chunking for RAG, plus mk.diagnose: test on your own documents whether to spend on the retriever, a reranker or LLM enrichment. Zero dependencies. Code for arXiv:2603.23533.
🍔 An AI restaurant agent demonstrating the RAG pattern using Semantic Kernel for orchestration and Qdrant for vector memory.
将语雀知识库接入大语言模型,实现基于 RAG(检索增强生成)的智能问答系统,支持FastAPI,兼容OpenAI API与本地Ollama模型。
Providing useful context by using Retrieval Augmented Generation (RAG) to Gemini
An agentic adaptive RAG system designed for intelligent query routing and multi-agent collaboration.
ChatTube: A Retrieval QA System to Youtube Videos
first attempt at creating and deploying rag based systems using langchain + ollama + streamlit
Question Answering Generative AI application with Large Language Models (LLMs), Amazon Bedrock, and Amazon MemoryDB for Redis
Javascript RAG Chatbot with Langchain, OpenAI and Supabase vector store.
AI YouTube Video Chat application, to ask questions to a YouTube video bot and get answers.
Inquiry videos with ChatGPT
A chatbot created with Next.js and AI SDK, using Langchain with RetrievalQA to provide information from a PDF loaded into a vector store in MongoDB.
This project combines Azure AI Search, Azure OpenAI Service, LangChain, React.JS, and Python FastAPI to create an intelligent system for managing Jira issues. It features advanced AI search for seamless document retrieval, a user-friendly React.JS front-end, and a robust Python FastAPI back-end.
Question Answering Generative AI application with Large Language Models (LLMs), Amazon Bedrock, and Amazon DocumentDB (with MongoDB Compatibility)
Developed a web app using LLM models, Langchain, and chatbots for PDF interactions. Users upload PDFs and ask questions, receiving instant chatbot responses for efficient content retrieval.
Say goodbye to endless Google searches and hello to our clever chatbot, the ultimate Wikipedia companion for all your Q&A needs.
Implementation of Reflective RAG, Self-RAG & Adaptive RAG tailored towards production-oriented applications with LangGraph and OpenAI API
此存储库展示了用于检索增强生成(RAG)系统的各种先进技术。RAG 系统将信息检索与生成模型相结合,以提供准确且上下文丰富的响应。
use 🦜️🔗 to communicate with varied files & web
Hybrid Knowledge Agentic RAG System
Virtual-Assistant LLAMA2/OpenAI with specific knowledge (RAG) in gradio UI.
This is a simple lab I have implemented to test Knowledge Augmented or Retrieval Augmented Generation (RAG) with Large Language Models. In particular, I am using LangChain, Streamlit, and OpenAI ChatGPT API.
End-to-end deployment of a scalable RAG chatbot utilizing LangChain for retrieval-based QnA. The project leverages robust CI/CD practices integrating MLFlow with emphasizes on cost analysis.
Open source RAG with Llama Index for Japanese LLM in low resource settting
🤖🎙️ Explore Lex Fridman Podcast Transcripts with a smart chatbot!
Чат-бот с LLL + RAG
Voxgig Podmind - a RAG chatbot for podcasts
Your Goto AI Buddy to solve questions with help of images and PDF files.
A local LLM chatbot with CAG / Context Caching for PDF input files
Chat with a PDF using a simple web UI
This app is a RAG (Retrieval Augmented Generation) chatbot that uses Amazon Q and Slack as it interface. It also provides a CloudFront links whenever it provides a source.
🐳 Docker Images for chatgpt-retrieval-plugin 🤖
Sync the contents of a directory to an OpenAI Assistant
A simple rag based plugin for obsidian
Automated fact-check
RAG applications repo for Uplimit course
Conversational, hierarchical, vector-less RAG
🐋 DeepSeek-R1: Retrieval-Augmented Generation for Document Q&A 📄
The standardized interface for information retrieval
Self Thinking Data Manifest
RAG implementation using Microsoft Semantic Kernel and .NET
Build your own RAG chatbot with Upstash
Ragnar is a pure Ruby command-line RAG (Retrieval-Augmented Generation) tool with zero external dependencies. It provides local document indexing, semantic search, and LLM-powered query processing. Built to be hackable, it lets Ruby developers experiment with agentic workflows and RAG pipelines natively in Ruby.
Speech-enabled Retrieval-Augmented Generation solution
AT-RAG (Adaptive Retrieval-Augmented Generation) is a novel RAG model developed to address the challenges of complex multi-hop queries
讲解并评估多种RAG算法
An advanced RAG (Retrieval-Augmented Generation) system that provides intelligent access to Cerebras inference documentation with citations, conversation memory, and multiple interfaces.
Hybrid enterprise AI agent built for ORRA. It utilizes a robust, RAGAS-evaluated retrieval pipeline and features a FastAPI API to allow seamless querying of ORRA documents and FAQs.
利用 Gemini 打造專屬的 DIY NotebookLM。透過自訂指令深度萃取 PDF 書心,建構個人化 AI 對話大腦 (Personal Deep Flux)
RAG system for chatting with documents using OpenAI & Anthropic, supports PDF/DOCX/TXT/MD with semantic search and source citations
Retrieval Augmented Generation (RAG) engine for intelligent document analysis. integrating LLM, embeddings, and vector database to extract, summarize, and query insights from multi-format documents.
Pharmaceutical Insight Retrieval System designed to help users gain meaningful insights from research papers and documents in the pharmaceutical domain.
Athena's Oracle: Enlightening AI for Document Insight and Discovery AI 驱动的文档洞察引擎
Implementation of "Distilling Knowledge for Fast Retrieval-based Chat-bots" (SIGIR 2020) using deep matching transformer networks and knowledge distillation for response retrieval in information-seeking conversational systems.
Personal RAG. Local-first. Drop a folder, ask a question.
Intelligent text chunking for RAG (Retrieval-Augmented Generation) and LLM applications in Crystal.
An advanced, fully local, and GPU-accelerated RAG pipeline. Features a sophisticated LLM-based preprocessing engine, state-of-the-art Parent Document Retriever with RAG Fusion, and a modular, Hydra-configurable architecture. Built with LangChain, Ollama, and ChromaDB for 100% private, high-performance document Q&A.
Rearview: Review your broswer knowledge with AI-Powered search.
OpenViking knowledge base integration for nanobot — RAG augmentation, semantic search, vector embeddings, document indexing. Free models on SiliconFlow.
Local, privacy-preserving semantic document search engine with citation verification
Local AI server with persistent memory, RAG, and multi-backend inference (MLX / llama.cpp / Ollama). Runs entirely on your machine — zero data sent to external services.
Experience a fully local, Spring AI-powered CLI chatbot using RAG, supporting various document types for domain-specific Q&A—all running entirely on your machine with no external services required.
Scrape, classify & chat over your LinkedIn Saved Posts with Supabase, pgvector, Vercel Edge Functions, Playwright MCP and OpenRouter + OpenAI LLMs.
Lightning-fast RAG for AI agents. ONNX-powered, 4-layer fusion, MCP server. No PyTorch.
Research guides and RAG indexes for AI agent development
🧠 NEXUS: Local RAG AI Agent for private document intelligence. Zero-cost, 100% local autonomous AI system with enterprise-grade performance.
QuantumPDF V1.3 enables intelligent conversations with PDF documents. Built with Next.js 15 and React 19, it uses Retrieval-Augmented Generation (RAG) to provide accurate, context-aware responses from your documents.
Advanced RAG System with Go featuring intelligent adaptive chunking, hierarchical document processing, semantic search, and flexible LLM integration
A modern web UI for semantic document search and management using Google Gemini File Search API.
工业知识智能问答系统
Python package that constructs a structured markdown knowledge base from external sources such as PDFs, websites, and GitHub repos with LLM summarization. Ideal for RAG, search-friendly LLM contexts (/llms.txt), and chatbots.
Full-stack RAG template: FastAPI + LangChain LCEL + Next.js 14. Multi-KB retrieval, hybrid search (dense+BM25/RRF), FlashRank reranking, SSE streaming, RAGAS evaluation & JWT auth. MySQL + Chroma + MinIO.
基于 Spring AI Alibaba ReAct 的FishAgent全栈智能体应用。具备分层记忆、三路 RAG 检索、知识库闭环、流式对话与多维限流能力。Java + Python + Vue 3 全栈架构。
AI-powered document intelligence platform for research administration
一个基于 Eino 框架的综合性大模型应用,用eino实现了一个流式对话AI和一个集成了Qdrant向量数据库的RAG知识库。是学习和实践大模型工程化的绝佳案例。
[MLSys'26] TeleRAG: Efficient Retrieval-Augmented Generation Inference with Lookahead Retrieval
Gebo.ai The open source Enterprise AI vendor agnostic platform
A RAG pipeline for question answering about PES University
Full-stack RAG platform for document loading, smart chunking, embedding, indexing, hybrid retrieval, and answer generation. Features chunking/model recommendation, query enhancement, and modular debugging. Built with FastAPI, Vue 3, Milvus, and LangChain
Open source RAG with Llama Index for Japanese LLM in low resource settting
Production RAG chatbot with cited answers — FastAPI, React, Qdrant, OpenRouter, and Render.
A personal AI knowledge assistant powered by RAG, semantic search, and document understanding for context-aware answers.
Public portfolio release of a multi-agent RAG system for football scouting.
Search your browsing history in plain English. Local-first RAG - Chrome extension + private Python backend (FastAPI, SQLite FTS5, LanceDB). Your data never leaves your machine.
Your personal knowledge base powered by local AI. Ingest anything, ask anything — fully offline with Ollama, or connect to cloud models.
RedHop — a reasoning-aware retrieval & context runtime for RAG (in-process, no vector DB). Light weight alternative to langchain and llamaindex for retrieval alone.
RAG-Powered Financial Query Assistant for JPMorgan Chase documents with Hybrid Search, Docker support, and Streamlit UI