RAG & retrieval pipelines
5,258 agents · most starred first
RAG & retrieval pipelines, page 19 of 53
私有部署的 AI 运维数字员工——自建 RAG 引擎(BM25+向量混合检索+重排序),知识库管理,申告工单全流程,数据不出域。Go + Next.js 全栈,Docker Compose 一键部署。
Educational AI chatbot project for Aparsoft interns, built with Django 6+ & Next.js 16+. Learn RAG (Retrieval-Augmented Generation), LangChain/LangGraph, Celery, PostgreSQL with pgvector, and Redis. Complete Docker setup for easy development.
Opensource AI Hub & Intelligent Agentic Platform for the Enterprise - self-hostable AI hub for enterprise knowledge.
A hyper-optimized, local RAG system built on Streamlit using Google's TurboQuant algorithm and Turbovec vector index for 4 GB RAM setups.
Your data, domiciled on your device. A private AI stack — vector database, RAG, and local LLM — that runs entirely in the browser. Zero egress, zero third-party processors.
Build an AI advisor SKILL from any YouTube channel — transcripts, BM25 + semantic RAG, verbatim quotes with timestamps.
gradio region:us
PageIndex-inspired agentic RAG app for vectorless document QA, FastAPI, multi-document retrieval, context compaction, and self-hosted AI workspaces.
Evidence-preserving multimodal RAG for bilingual (Vietnamese/English) document Q&A — hybrid dense+sparse+graph retrieval, bounded agentic planning, verifiable citations. FastAPI · Qdrant · MongoDB.
DeepDimension 是一个企业级的 AI 知识库管理系统,采用检索增强生成(RAG)技术,提供智能文档处理和检索能力。
知识管理平台:上传文档即可获得带引用来源与置信度的 RAG 智能问答,以及 LangGraph 编排的 Agent 工作流(含 human-in-the-loop 人工确认节点)。Spring Boot 3 + Vue 3 + FastAPI 混合全栈,Qdrant 语义检索、Redis Streams 异步文档流水线、多租户隔离、编辑社论风前端;API Key 界面化配置,Docker 一键部署开箱即用。
Document-scoped enterprise RAG API with FastAPI, SQLite, Qdrant, citations, refusal, and evaluation.
Vidify is an ASR-first video understanding agent that turns YouTube, local files, and live streams into timelines, searchable Q&A, reports, and highlight clips
Steadlith reuses unchanged RAG chunks with content-defined identities, cache-aware planning, and transactional indexing.
Production-style Retrieval-Augmented Generation document Q&A: LangChain ingestion, Chroma/pgvector store, hybrid retrieval, citation-grounded answers and a streaming chat API.
Production-grade RAG pipeline built from scratch (no LangChain) — hybrid FAISS + BM25 retrieval, cross-encoder reranking, evaluation harness, and AWS Lambda deployment.
This is the RAG Lab used during MongoDB Developer Days that covers building RAG applications using MongoDB.
ai-kit Filament — v5 admin panel: manage knowledge bases & documents, ingest files/URLs, conversation logs with token usage, playground, analytics dashboard.
DevIntel AI is an AI-powered developer productivity platform that enables developers to connect GitHub repositories, index code bases, and chat with an AI assistant using Retrieval Augmented Generation (RAG). Get instant code insights, refactoring suggestions, and intelligent explanations.
Visual video search & RAG — ask questions about videos by what's seen on screen. CLIP + Qdrant + bring-your-own-LLM. Apache 2.0.
Document-scoped enterprise RAG API with FastAPI, SQLite, Qdrant, citations, refusal, and evaluation.
Production-grade hybrid RAG: BM25 + dense retrieval + cross-encoder reranking + LLM-as-Judge
AI 智能学习助手系统:基于 Spring Boot 3.3 + Java 17 + Vue 3 + Qdrant + Redis,实现AI学习助手、RAG检索评测、资料管理、在线练习和学习分析系统,适合作为学习和简历项目,学习门槛低。
面向中小企业的企业知识问答与办公任务 Agent:支持 RAG 知识问答、预置企划/方案/报价单等多步骤工作流,Agent 自主检索资料并生成材料,关键行动经用户确认。
Low-power, offline retrieval (RAG) for disaster and infrastructure-failure guidance.
Research sandbox for ablation studies of RAG components (chunking, embeddings, retrieval, LLMs) on Russian-language corpora.
Production-grade Document RAG with IBM Docling AST parsing, automated VLM table repair (Pixtral), dual-representation serialization, hybrid RRF retrieval, and sub- 2s latency.
Vietnamese-first self-hosted RAG on internal documents — Spring Boot + FastAPI + Next.js, hybrid dense/sparse/graph retrieval. DX-OS Open-Core entry (OLP 2026), Apache-2.0.
An open-source implementation of ToC-Aware RAG inspired by IBM's STAIR paper. Preserves document hierarchy for structured addressable retrieval and near-zero hallucinations.
二十四史(加新元史,清史稿)+资治通鉴(史记,三国志,宋书,旧五代史...)的skill.提升llm智力。
Open reimplementation of STAIR: structure-aware generative retrieval that returns real section titles instead of chunk IDs. Constrained decoding gives 0.00% hallucination. Runs Mistral-7B QLoRA in 5GB.
Bank RAG Benchmark 中文银行知识库 RAG 评测基准,包含 100 份 PDF 文档和 450 条测试案例。联合发布单位:上海交通大学苏州人工智能研究院、上交致微(苏州)信息技术有限公司。
📍 Storing Text Location in Vector Databases for QA tasks
Terraform-Based Bedrock RAG Deployment
LLM RAG enabled bookshelf
Chat with any document
Recursive Abstractive Processing for Tree-Organized Retrieval - Neuron PHP Framework
Agent Workflow Has Personality
Simple Index is a chatbot/QA system that allows users to ask questions about their documents. It scans a specified folder, indexes data, and initializes a chatbot or QA system based on the model. Built on the Langchain library, it offers a web-based chat UI and command-line interaction. Utilize Docker for deployment or run manually with Python.
Python notebook for solving overlapping tables problem with Azure document intelligence , semantic chunking, RAG , Azure AI Search
基于LangGraph的智能保险合同 PDF 分析与问答助手,支持要点提取、检索、风险高亮、公式解析与可视化。AI-powered insurance contract PDF assistant: summarization, semantic/keyword search, risk highlighting, formula extraction, and visualization.
RAG chatbot using Llama 2, chainlit and Faiss
Chat with documents via a chatbot using LLMs
Langchain RAG model, with output streaming on Streamlit and using persistent VectorStore in disk
Retrieval-augmented generation (RAG) LLM app
Chat with Your Documents is an innovative application designed to simplify document analysis by utilizing the power of artificial intelligence.
Learn how to build a Retrieval-Augmented Generation (RAG) system from the ground up! In this session, you’ll break down the pipeline, see practical examples, evaluate retrieval quality, and learn tips for deploying a reliable RAG service. Ideal for developers who want to add factual, up-to-date knowledge to their AI apps.
Self-hosted PDF Q&A API with streaming answers, citations, Weaviate/pgvector, and Azure OpenAI, OpenAI-compatible, Vertex AI, or local embeddings.
Collection of different types of RAGs (Query Translation Patterns)
Question Answering Generative AI application with Large Language Models (LLMs) and Amazon OpenSearch Serverless Service
The AI Assistant uses OpenAI's GPT models and Langchain for agent management and memory handling. With a Streamlit interface, it offers interactive responses and supports efficient document search with FAISS. Users can upload and search pdf, docx, and txt files, making it a versatile tool for answering questions and retrieving content.
Insight-Chat: Chat with your documents
An Offline Document Enquiry LLM for Everyone
Fast Multimodal RAG on CPU
Agentic-AI framework w/o the headaches
These #LangChain-powered apps include a Research Assistant that generates reports using web scraping and GPT-4o-mini, and Chat With Video, a #Streamlit app that #transcribes videos and enables content-based Q&A via #embeddings.
The interactive handbook for Ignacian Marians
A RAG demo using LangChain that allows you to chat with your uploaded PDF documents
AIPLA an Artificial Intelligent powered Library Assistant is a Messenger chat-bot using NLP and DL to find, search and recommend books for various users, based on their taste of novels and past searches.
It shows a question/answering chatbot using Amazon Bedrock with RAG based on Amazon Kendra.
Camelot AI lets you upload documents, chat about their content, and get audible responses from the chatbot. It's perfect for digging into details or just getting a quick summary—all with text-to-speech for easier access and a better experience. Explore Camelot AI and make your documents talk!
Analysis Of The Context Size Impact In Deep Learning Conversational Systems.
It shows an advanced RAG with Reflection where LangGraph is used for workflow management.
A Next.js 14 Chatbot that uses OpenAI's Assistant Retrieval to chat with documents
Doppalf is a RAG powered AI chat bot application
A standalone desktop app for talking to my books (PDF,epub)
Transcribe YouTube videos, extract topics, and answer questions interactively.
This is an example of implementing the RAG feature based on OpenAI Assistant V2 and Anthropic's PDF feature.
Document based ChatGPT
Self-hosted RAG Knowledge Base. 私有化部署的 RAG 知识库,支持多模型管理与 API Key 分发,支持 GitHub/Gitee 登录、后台管理、OpenAI 兼容接口及完整的文档问答工作流。开箱即用,支持 Docker 部署。不仅仅是 Web 界面,YourRAG 还是一个 RAG API 网关。用户可以生成 API Key,将知识库能力集成到自己的飞书/钉钉机器人/CherryStudio/NewAPI/n8n/Dify/Kilocode/Roocode/Cline/Cursor/ClaudeCode中。
Pick Paul Graham's brain 🎨
RAG of the Military Strategy using Langchain Framework
Weave's extensions and toolkits
A playground for building and serving Retrieval-Augmented Generation (RAG) systems using best practices in MLOps and LLMOps, with open-source tools.
Prometheus AI Assistant para ajudar na criação de Alertas para sua infraestrutura!
Run a RAG system locally on your device and chat with your LLM!
Token-Oriented Object Notation (TOON) is an LLM-optimized data serialization format implemented in Python.
RAGO (Retrieval Augmented Generation Optimizer) is a toolkit that automatically discovers the best configuration for your RAG system through smart experimentation
An intelligent AI platform built with modern web technologies, providing comprehensive AI model management, knowledge base operations, and conversational AI capabilities.
AI-first interactive ebook reader
Retrieval Augmented Generation, Function Calling and Code Generation on GitHub Projects with Java
A simple demonstration of how you can implement retrieval augmented generation (RAG) for a book.
PDFGenie 📄🧞♂️ – Ask questions from your PDFs using AI! Generate embeddings with Gemini ✨, fetch content with GROQ 📚, and search fast via Pinecone ⚡. Your PDF, your answers! 🧠💬
Upload any document and start intelligent conversations. Get instant answers, summaries, and insights from your files using advanced RAG technology.
Universal Retrieval Protocol — one URL that any AI can read from, write to, and browse as a wiki. Cross-chat knowledge base for ChatGPT, Claude, Grok, and any LLM.
Turn your repository into local RAG / MCPServer.
A learning companion.
RAGGLE - LLM-powered search and chat for all your team's data
It generates a report based on documents.
A repository containing a modularized implementation of a Retrieval-Augmented Generation (RAG) model as Flask APIs.
Cofone is a small python library to manage RAG
Simple RAG solution demo in Python with LangChain, FastAPI and Chroma DB.
This is a simple example of how to use the Ollama RAG (retrieval augmented generation) using Ollama embeddings with nodejs, typescript, docker and chromadb
Showcase the use of Azure OpenAI's native On Your Data feature and integrates it with Streamlit, a robust framework for developing web applications purely in Python. The goal is to create an MVP for RAG with the most streamlined architecture possible.
云盘知识库系统前端,和AI-Cloud-Go一起使用。
This repository contains code for the RAGonite project, a flexible RAG pipeline developed by the NLP team at Fraunhofer IIS, Erlangen, Germany. RAGONITE supports conversational question answering over heterogeneous data, iterative retrieval over structured and unstructured sources, automated database induction from knowledge graphs, and much more.
High-throughput RAG ingestion engine in pure Go — 965 MB/s (Mixed Corpus), 2.4 MB heap, zero dependencies.
Book + RAG ChatAgent + SSO + Compunding RI Intelligence built in 2 days. Robolearn is what AI-driven development with Spec-Driven methodology and Reusable Intelligence makes possible.
Recursive reasoning engine for AI agents and vector databases. Powered by MIT's RLM.