Data, search & knowledge

RAG & retrieval pipelines

5,258 agents · most starred first

RAG & retrieval pipelines, page 9 of 53

anykb★ 42

AnyKB — 私有 RAG 知识库 + 透明 Agent

chat-with-pdf★ 42

ChatWithPDF is a cutting-edge platform that enhances PDF functionality. Users can upload PDFs, extract summaries, and get answers to questions. It features an attractive UI with shadcn and Tailwind CSS and employs advanced tech like Langchain and OpenAI models for chat completions and text embeddings. It's a powerful tool for document management

SearchWithOpenAI★ 42

Quick start. Index multiple documents in a repository using HuggingFace embeddings. Save them in Chroma and / or FAISS for recall. Choose OpenAI or Azure OpenAI APIs to get answers to your questions - Q&A with OpenAI and Azure OpenAI.

askdocs-ai★ 42

An AI-powered chatbot that leverages RAG (Retrieval-Augmented Generation) to answer your questions based on the content of uploaded PDFs

hugging-face-qa-bot★ 42

QA Bot for Hugging Face documentation to accelerate development within the ecosystem.

docspedia★ 42

Chat with your pdf using your local LLM, OLLAMA client.

ESG-Analysis-Using-Retrieval-Augmented-Generation-Engine★ 42

Analyse environmental, social, and governance policies for potential gaps using AI - powered by LLMs, RAG techniques, and a regulatory knowledge base using OpenAI API, LangChain, Pinecone and Streamlit.

NotionRag★ 42

Ask question over your Notion Database! A naive Retrieval-Augmented Generation (RAG) pipeline backed by Langchain and Streamlit

recommendation-systems-by-llms★ 42

Enhancing Recommendation Systems with Large Language Models (RAG - LangChain - OpenAI)

janus-llm★ 42

Leveraging LLMs for modernization through intelligent chunking, iterative prompting and reflection, and retrieval augmented generation (RAG).

morign★ 42

AI chat backend with knowledge base Q&A, MCP tools, and OAuth authentication.

rag-agents-workshop★ 42

From RAG to Agents: Building Smart AI Assistants

rag-project03-audit★ 42

[RAG训练营] u.geekbang.org/subject/airag/1009927 ESG合规审计系统 - 可持续发展报告检查工具

agentic_rag_with_langgraph★ 42

Exercises for the Agentic RAG live course for O'Reilly.

enowx-rag★ 42

RAG Skill and MCP for AI agents for codebase indexing and memory

ollama_rag★ 41

fully local RAG system using ollama and faiss

aitour26-BRK444-advanced-retrieval-for-your-ai-apps-and-agents-on-azure★ 41

Resources for the AI Tour Talk on "Advanced Retrieval for your AI Apps and Agents" on Azure - slides, talk recording, demo recording, demo setup instructions.

Local_RAG_Agent_01★ 41

Local RAG agent with LLaMA3

mAIcro★ 41

A reusable, open-source AI infrastructure designed for communities and organizations. It understands structured data, processes official announcements, and answers questions accurately by centralizing important information.

fitz-sage★ 41

Fully local governed RAG for code, documents, and tables. No LLM API key. No GPU. No infrastructure.

WiredBrain-Hierarchical-Rag★ 41

Hierarchical RAG architecture scaling to 693K chunks on consumer hardware (4GB VRAM). Features 3-address routing, hybrid vector+graph fusion, and SetFit classification.

laravel-rag★ 41

A complete, driver based RAG pipeline for Laravel with pgvector & sqlite-vec, streaming, agentic retrieval, hybrid search, evals, MCP server, Filament admin.

spring-ai-rag-ollama★ 41

This project contains source code to demonstrate the usage of Retrival Augmented Generation (RAG) feature using Spring AI using PG Vector as the Database and Ollama as the Local LLM

Spring-AI-Ailibaba-Best-Practices★ 41

基于个人知识库的AI问答系统SSE流/Agent智能体/知识图谱RAG/FunctionCall/历史消息/图片生成/图片理解/Embedding/VectorDatabase/RAG

Advanced-RAG-LangGraph★ 41

Advanced-RAG-LangGraph is a Streamlit-based web application that implements an advanced Retrieval-Augmented Generation (RAG) pipeline using LangGraph, ChromaDB, and Tavily to enable interactive document-based Q&A with enhanced retrieval and error-handling capabilities.

pageindex-chat-studio★ 41

Extends pageIndex into an AI document workspace with multi-format parsing, OCR, visual TOC, custom models, citations, and agentic QA.

multimodal-rag-system★ 41

Multimodal RAG system with CLIP/text embeddings, rank-fusion reranking, FastAPI serving, and Recall@5 evaluation.

togolm★ 41

First open-source AI knowledge layer for Togo - 62K+ documents, RAG API, fine-tuned LLM. Built for developers, startups and institutions in francophone West Africa

SLM-RAG-Arena★ 41

gradio region:us

llm-full-stack-tutorial★ 41

Full-stack RAG application — OpenAI, Pinecone, Flask, React — and the tutorial series that builds it end to end.

llm-wiki-claude-agent-sdk-agentic-rag★ 41

Claude Agent SDK + LLM-wiki,就是最强大的agentic RAG 。让 AI 当一个“知识编译器”,先把你的所有资料读一遍,整理成一本结构清晰、彼此关联的百科全书。以后你再提问,AI 直接翻这本百科书就行了。 本项目主要展示了我制作的 llm-wiki 怎样通过 Claude Agent SDK 转为 agentic rag, 效果非常好的。使用方法:.venv\Scripts\Activate.ps1; python 7_wiki_writer.py --request "怎样拼搭微型车"

Multimodal-RAG★ 41

基于多模态 Embedding + Zilliz + Qwen 视觉理解的多模态 RAG 系统。支持 **Cohere / DashScope Embedding** 和 **DashScope / OpenRouter LLM** 双引擎切换。上传 PDF,用自然语言提问,系统自动检索最相关的页面并由 AI 生成回答。 与传统 RAG 不同,本系统**不做文本提取和 OCR**,而是直接将 PDF 页面当作图片处理,通过视觉 Embedding 模型编码,完整保留表格、图表、排版、手写批注等所有视觉信息。

docusaurus-ai★ 40

This is a simple AI assistance for Docusaurus generated documentation. It is a simple chatbot that can answer questions about your docs.

moviegpt★ 40

MovieGPT: A RAG, Gen AI application for Movie Recommendations

VisionRAG★ 40

A new novel multi-modality (Vision) RAG architecture

OpenKimi★ 40

Unlimited context on any LLM ✨在任何语言模型上使用无限的上下文窗口 | 顺便一提,我们没有股权纠纷 :)

ReT★ 40

[CVPR 2025] Recurrence-Enhanced Vision-and-Language Transformers for Robust Multimodal Document Retrieval

Guido★ 40

景区导览服务 AI 数字人:基于 Spring Boot、Vue 3、UniApp 与本地 RAG 的智能导览系统。

vid-lens★ 40

基于 Go 与 React 的视频知识库与 Agent 问答平台,支持多模态检索、跨视频分析与来源回放

PrivatePulse-AI★ 40

RAG-powered document intelligence assistant built for the Midnight Hackathon AI Track. Users upload confidential documents (medical records, contracts, financial statements, legal files) and interrogate them through a natural-language chat interface. The system returns grounded, cited answers without exposing raw document contents unnecessarily.

RideRecall-Agent★ 40

Stateful ride-support agent: versioned claims, evidence-backed RAG, durable memory and guarded MCP tools.

PdfPal★ 39

Teach a chatbot to be a bookworm with Langchain and OpenAI's GPT-3.5 language model. Get answers to all your burning questions straight from the pages of a PDF!

Gemini-RAG★ 39

Chatbot that uses Gemini-1.0-Pro to answer questions, with memory by using LangChain. Also, it's enriched by RAG and deployed in Dialogflow

llama3-langchain-kor★ 39

It shows a korean chatbot using LangChain based on Llama3

Agentic-RAG-with-LangChain★ 39
LangChain-RAG-Linux★ 39

Examples of RAG using LangChain with local LLMs - Mixtral 8x7B, Llama 2, Mistral 7B, Orca 2, Phi-2, Neural 7B

Retrieval-based_Chatbot★ 39
pdf-rag★ 39

RAG (Retrieval-Augmented Generation) template with PDF OCR, vector search and chat/documents UI

rust-llm-rag★ 39

To implement LLM as a services.

chat-pdf-hugginface★ 39

This is a fun Python project that allows you to chat with a chatbot about the PDF you uploaded. and generate a PDF transcript of the conversation. The project is built using Python and Streamlit framework.

TutorAI★ 39

TutorAI is a RAG system capable of assisting with learning academic subjects and using the curriculum and citing it. The project revolves around building an application that ingests a textbook in most formats and facilitates efficient learning of the course material.

VideoContext-Engine★ 39

Local Video RAG Engine. A FastAPI microservice for video understanding: Scene Detection + Whisper ASR + Qwen3-VL. Optimized for Apple Silicon (MLX) & Windows/Linux (Llama.cpp).

Psi-RAG★ 39

[ICML'26] Hierarchical Abstract Tree for Cross-Document Retrieval Augmented Generation

MiniCPMV-RAG-PDFQA★ 39

gradio region:us

SourceLens★ 39

Multilingual source-grounded research workspace with agentic RAG, cited chat, podcasts, PowerPoint, and video.

rag-research-agent-template-js★ 38
QChunker★ 38

QChunker: Learning Question-Aware Text Chunking for Domain RAG via Multi-Agent Debate

kisahari★ 38

a personal journaling app where you can chat with your entries locally

rag-semantic-kernel-mongodb-vcore★ 38

A sample for implementing retrieval augmented generation using Azure Open AI to generate embeddings, Azure Cosmos DB for MongoDB vCore to perform vector search, and semantic kernel.

Talk-with-PDF★ 38

An interactive AI chatbot for querying and discussing the contents of PDF documents using Streamlit and OpenAI/other AI language models.

Piazza-Updater★ 38

Piazza-Updater automates updates to a Weaviate database with real-time vectorial data. By continuously searching the internet and integrating with Verba repositories, it enhances retrieval-augmented generation (RAG) capabilities, keeping your applications informed and responsive.

Vault-for-LLM★ 38

🧠 Local-first knowledge system for LLM agents — sqlite-vec + ONNX embeddings, no cloud/Docker/PyTorch dependency

exact-rag★ 38

AI-augmented, conversational information retrieval and data exploration

synthetic-rag-index★ 38

Service to import data from various sources and index it in AI Search. Increases data relevance and reduces final size by 90%+. Useful for RAG scenarios with LLM. Hosted in Azure with serverless architecture.

OmniClip-RAG★ 38

Local-first RAG desktop app & official MCP Server. Let any AI instantly search your private Markdown, PDF, and 1290+ document formats. (本地优先的 RAG 桌面端与官方 MCP 服务器。让任意 AI 瞬间检索你的私有 Markdown、PDF 及 1290+ 种文档格式。)

agentic-rag-recommendation-engine★ 38
ask-a-question★ 38

Trustworthy question-answering AI plugin for chatbots in the social sector with advanced content performance analysis.

GRIP★ 38

[ACL'26 Main Conference] Retrieval as Generation: A Unified Framework with Self-Triggered Information Planning

AgentCraft★ 38

🚀 多Agent协作智能知识库系统 — 五层可编排Agent架构 + RAG全链路 + 统一ToolRegistry,Spring Boot + FastAPI + React,核心亮点是 五层可编排 Agent 架构——Interface、Orchestrator、Tool、Memory、Evaluation 五层解耦,支持意图识别→问题改写→检索→充分性判断→答案生成的完整工作流。系统内置 Router / Retrieval / Ops / Inspection 多 Agent 协作,通过统一 Tool Registry 管理 AI 能力,支持 runId/traceId 全链路追踪、四级记忆体系与 Caffeine + Redis 多级缓存。适合Agent后端开发学习与简历展示

docuchat.app★ 38

Private, self-hosted document chat for attorneys: parse legal PDFs and query them with local open-source LLMs (Ollama) + verifiable page citations. One-click desktop app at docuchat.app.

Shaft-Machining-Planner★ 38

Machining process planning for motor shafts - input shaft geometry, RAG-grounded operations, machine tools, cutting tools, heat treatment, exported as a process-card Excel.

chat-with-pdf-llm★ 37

Chat with your PDFs, built using Streamlit and Langchain. Allows the user to ask questions to a LLM, which will answer based on the content of the provided PDFs.

huxley-pdf★ 37

Upload personal docs and Chat with your PDF files with this GPT4-powered app. Built with LangChain, Pinecone Vector Database, deployed on Streamlit

auto-hyde★ 37

🔎 A deep-dive into HyDE for Advanced LLM RAG + 💡 Introducing AutoHyDE, a semi-supervised framework to improve the effectiveness, coverage and applicability of HyDE

documon★ 37

Chat with your PDF documents using this AI-powered SaaS - leveraging TypeScript, Next.js 14, Tailwind CSS, Pinecone, and Langchain.

document-qa★ 37

Scientific Document Insight Q/A

eden-aigc-qna★ 37

AIGC 知识库问答系统快速搭建,便于企业级定制化,支持文档上传,向量存储,聊天式问答。

rag-as-a-service-with-vision★ 37

This repository offers a Python framework for a retrieval-augmented generation (RAG) pipeline using text and images from MHTML documents, leveraging Azure AI and OpenAI services. It includes ingestion and enrichment flows, a RAG with Vision pipeline, and evaluation tools.

NextRag★ 37

Next.js RAG with PGVector

videodb-cookbook★ 37

Build use cases with VideoDB

agent★ 37

基于检索增强生成(RAG)技术的微信聊天记录智能问答系统

DocFinder★ 37

DocFinder is a local-first indexing and searching documents using semantic embeddings stored in SQLite. Everything runs on your machine, no external services required.

AI-Multi-Model-RAG★ 37

✈ AI 🚀 Multi 🛬 Model 🚁 RAG 🚂 is 🚃 an 🚝 advanced 🚋 artificial 🚠 intelligence 🚟 implements 🛸 a ⛱ Retrieval 🏘 Augmented 🏩 Generation 🏪 system 🏬 powered 🏯 by 🕌 multiple 🏦 AI ⛪ models 🕍 language 🍎 models 🍏 retrieval 🍑 systems 🫑 intelligent 🎂 context 🥃 processing 🫐 to 🍋 generate 🌽 accurate 🍇 knowledge 🦁 grounded 🦊 responses

lasagna★ 37

Swap one RAG pipeline stage, hold the rest fixed, and measure whether the gain survives composition. The framework behind "Retrieval Augmented Generation Compositionality": 450 configurations, eight benchmarks, corpora from 5K to 200K documents.

Experimental_RAG_Tech★ 36

A collection of experimental Retrieval Augmented Generation (RAG) Techniques to elevate your pipelines, all with code and intuitive explanations

WebMoniter★ 36

虎牙/哔哩哔哩/微博/抖音/斗鱼/小红书 开播&动态监控 · iKuuu/贴吧/雨云/阿里云盘/值得买 等 30+ 签到 · 企微/钉钉/飞书/Telegram 推送 · Web 管理 · AI 助手 · 青龙·Docker · 配置热重载

obsidianRAGsody★ 36

CLI tool for intelligent Obsidian vault interaction using RAG. Query your notes with natural language and convert URLs to markdown files with AI-powered content extraction.

DRAG★ 36

(ACL 2025 Main) Distilling RAG for SLMs from LLMs to Transfer Knowledge and Mitigate Hallucination via Evidence and Graph-based Distillation

local-agentic-rag★ 36

Local Agentic RAG using Langchain and Agno

rag-postgresql-agent-bedrock★ 36

This application is built in four stages using infrastructure as code with CDK with Python to deploy. In the first stage, an Amazon Aurora PostgreSQL vector database is set up. In the second stage, the Knowledge Base for Amazon Bedrock is created using the established database. The third stage involves creating an Amazon

llmc★ 36

One stop shop - Local-first RAG stack with intelligent polyglot-code/docs, remote code execution, local llama enrichment, progressive disclosure tools, mcp server, sandboxed security.

almanac★ 36

Lightning-fast data access platform designed specifically for AI agents

azure-sql-db-ai-samples-search★ 36

To gain access, please finish setting up this repository now at:

SmartDocs-Multillingual-Agentic-Rag★ 36

Intelligent multilingual PDF Q&A system for Indian professionals. Sarvam-30B + multilingual-e5-large. 22 Indian languages, no translation layer.

retrieval-agent-template-js★ 36
wikimind★ 36

WikiMind is a personal LLM-powered knowledge OS. Feed it articles, PDFs, YouTube videos, podcasts, or papers — it compiles them into a structured wiki and answers questions with full source attribution.

msmarco-genqa★ 36

RAG-based question answering system on MS MARCO with retrieval, reranking, evaluation, and reproducibility checks.

simpread-karpathy-llm-wiki-compiler★ 36

简悦 Andrej Karpathy LLM Wiki 方案

pi-knowledge★ 36

Local-first RAG knowledge base for Pi agents with hybrid code/doc search, reranking, diagnostics, and large-project indexing.

esg-rag-platform★ 36

gradio region:us

More in Data, search & knowledge