Data, search & knowledge

RAG & retrieval pipelines

5,258 agents · most starred first

RAG & retrieval pipelines, page 15 of 53

PDFizado★ 16

Una aplicación para interactuar con el contenido de tus archivos PDF y poder hacer tu estudio más sencillo.

doc-genius-ai★ 16

DocGenius AI - Generative AI Chatbot for your Documents

Agentic-Web-Starter★ 16

A FastAPI-based backend scaffold for building agentic applications and pipelines. It exposes ingestion, retrieval, and chat APIs, integrating Qdrant for vector-based similarity search and Redis for persistent, session-scoped conversation memory.

AWS-LLM-SageMaker★ 16

SageMaker Ployglot based RAG opensearch

carbon-almanac.ai★ 16

Chatbot for The Carbon Almanac book or a climate change related topic

LangChain-RAG-Pattern-with-React-FastAPI-and-Cosmos-DB-Vector-Store★ 16

Complete project (web, api, data) covering the implementation of the RAG (Retrieval Augmented Generation) pattern using Azure Cosmos DB for MongoDB vCore and LangChain. The RAG pattern combines leverages the new vector search capabilities for Azure Cosmos DB.

Langchain-PDF-App-using-ChatGPT★ 16

Build a ChatGPT-Powered PDF Assistant with Langchain and Streamlit

WeatherChatAI★ 16

☁️ ❄️ ⚡ Don't just get the weather. Get the answer to your underlying weather-related question. Using retrieval augmented generation with LangGraph, OpenAI, the National Weather Service, and Streamlit. ⛅ 🌡️ ☂️

RAG_over_LLM_for_pdf_ChatBot_Free★ 16

Retrieval-Augmented Generation on PDF for Free, Integrated with Memory to recall previous interactions, it operates as a sophisticated lang-chain application.

Babu-LOHAR★ 16

A Slack Bot powered by the advanced LLM model for interacting with Your uploaded Documents.

simplified-corrective-rag★ 16

How to build a simplified Corrective RAG assistant with Amazon Bedrock using LLMs, Embeddings model, Knowledge Bases for Amazon Bedrock, and Agents for Amazon Bedrock.

DocuConverse★ 16

🤖💬💡Chat with any document using conversational AI! Our project allows you to easily ask questions and get answers from any document. Built with Langchain.

ragme-io★ 16

RAGme-io is a personalized RAG agent for the web sites you visit and documents you care about

gemai★ 16

GemAI - A Free RAG CLI ChatBot 🤖

AURORA★ 16

AURORA (Artificial Unified Responsive Optimized Reasoning Agent) uses lobes and web research for RAG based memory and learning.

sentio★ 16

Boilerplate RAG System with LangGraph Architecture

LangChain★ 16

This project implements RAG using OpenAI's embedding models and LangChain's Python library

rag-from-scratch★ 16

Demo done in a jupyter notebook to show how Retrieval Augmented Generation (RAG) can be done without using any frameworks.

rag-code-sorting-search★ 16

RAG code sorting search, RAG knowledge organization

parla-frontend★ 16

AI assistant for written inquiries of the Berlin House Of Representatives (AGH)

rag-app★ 16

An RAG (retrieval augmented generation) app which iterates through a PDF document and can answer user's questions based on the document uploaded. This application needs a Google API Key.

rag-systems-production★ 16

Enterprise-grade RAG systems with monitoring, scalability, and production features

PetCare-AI-Chatbot★ 16

🐶 PetCare AI Chatbot, powered by Langchain, Ollama, and Flask, utilizes RAG for context-aware answers from PDF documents.

llama-index-RAG★ 16

A RAG implementation on Llama Index using Qdrant vector stores as storage. Take some pdfs, store them in the db, use LLM to inference.

chatbot_app★ 16

LLM-powered chatbot app to enhance accessibility to knowledge contained within PDFs

RAG_Project★ 16

本项目是一个完整的RAG系统教程,涵盖了从基础概念到高级技术的全面内容。通过Jupyter Notebook的形式,逐步讲解如何构建和优化一个高效的检索增强生成系统。本项目使用的所有模型都是本地化部署的,在3090上可以运行。

swift-rag-demo★ 16

SwiftUI demo of Retrieval-Augmented Generation (RAG) using local embeddings and Google Gemini API. Features semantic search, reranking, and step-by-step visualization of the RAG pipeline.

RECAP★ 16

Code for ICASSP 2024 Paper: RECAP: Retrieval-Augmented Audio Captioning

rag-elixir-doc★ 16

Livebook to run a Phoenix_LiveView documentation Retrieval-Augmented Generation (RAG) enhanced LLM

videodb-node★ 16

VideoDB Nodejs SDK

csrd_assistant★ 16

In this solution accelerator, we demonstrate how generative AI, retrieval augmented generation (RAG) and multi stage reasoning can be used to better navigate through the complexities of regulatory filings, bringing more transparency for companies to disclose their societal and environmental impacts.

AML-MultiAgent-RAG★ 16

A Multi-Agent RAG platform using Vector DBs and AI models to accurately answer AML/CFT compliance queries.

pdf-qa-bot★ 16

A PDF Question-Answering App built with RAG (Retrieval-Augmented Generation), allowing users to upload PDFs and ask context-based questions. Powered by Streamlit, LangChain, Ollama, and Chroma for efficient and accurate answers.

PaperAgent★ 16

📚 Local paper management + AI-powered reading assistant with RAG, vector search, and multi-session chat.

local-rag-engine★ 16

Local RAG app with zero-config Docker setup. FastAPI + Streamlit + Qdrant + Ollama. Just run `docker-compose up --build`! 🚀

role-aware-rag-platform★ 16

企業内文書向けの Role-aware RAG Platform。権限フィルタ、Excel 仕様書解析、hybrid search/rerank、FastAPI + React に対応。

rag-pipelines★ 16

Advanced RAG pipelines for medical (HealthBench, MedCaseReasoning, MetaMedQA, PubMedQA) and financial (FinanceBench, Earnings Calls) QA. LangGraph orchestration + BAML structructed generation, Milvus Hybrid search (Dense + BM25 + RRF), three-layer Metadata Enrichment, Contextual AI instruction-following reranker, and DeepEval evaluation.

OrgMind★ 16

OrgMind 是一个集成了 OA 组织架构管理、RAG 知识库问答、AI 智能考试与企业级权限管理的现代化组织智能系统。 系统采用前后端分离架构,前端基于 Ant Design Pro (React) 构建,后端采用高性能的 FastAPI (Python) 框架,底层数据存储使用 PostgreSQL 并结合 `pgvector` 实现向量检索能力。

local-rag★ 16

Offline RAG-powered technical support agent for gas field engineers using Foundry Local, Phi-3.5 Mini, and SQLite vector store

RAGOndevice★ 16

gradio region:us

OCC-RAG-1.7B★ 16

transformers safetensors qwen3 text-generation rag faithful-qa

vercel-chatbot-template★ 16

Next.js chatbot example backed by Pinecone and the OpenAI API, deployable to Vercel.

Llama-3-8B-RAG-v1★ 16

transformers safetensors llama text-generation RAG conversational

localOllamaRAG★ 16

MonkeyGrab: a local, multilingual (ES/CA/EN) RAG system for PDFs. MinerU parsing, hybrid BM25 + FAISS retrieval with cross-encoder reranking, and generation with open models via Ollama. Flask + React web app and Windows desktop build; no data leaves your machine.

system-design-rag-enterprise★ 16

Curso System Design Interview Notebook LM - From Zero to Production

rag-chatbot★ 16

Python RAG-based chatbot for document Q&A using retrieval-augmented generation

ocg-ruling-assistant★ 16

Evidence-assisted Yu-Gi-Oh! rulings for OCG and TCG, with card-text checks and cited sources. TCG public preview.

NexusMind★ 16

Local-first Agentic RAG engine - GraphRAG, hybrid retrieval (BM25 + dense + RRF + rerank), multi-agent orchestration, MCP-native, 100% local inference via Ollama.

proofpick_agent★ 16

Agentic RAG consumer decision agent with ReAct, Text2SQL, multi-hop retrieval, memory and deterministic constraint checking.

Agentic-AutoRAG★ 16

Reasoning-driven optimizer for RAG pipelines: LLM agents diagnose retrieval failures and propose the next config.

your-agent★ 16

A high-performance RAG system featuring Multi-modal reasoning, Semantic Chunking, and Knowledge Graph extraction powered by vLLM and Milvus.

bowerbird★ 16

Open-source NotebookLM alternative. Local-first research notebook: ask questions about your PDFs, books, web pages, YouTube videos and recordings, and get answers with every quote checked against its source. Any model, plain-file notebooks, local OCR, search and speech. Linux, Windows, Android, web.

nvidia-NIM-RAG★ 15

Project demonstrates the power and simplicity of NVIDIA NIM (NVIDIA Inference Model), a suite of optimized cloud-native microservices, by setting up and running a Retrieval-Augmented Generation (RAG) pipeline.

Project-WebSage★ 15

WebSage is an AI Engine that extracts content from any URL, generates summaries, and enables interaction using AI models. Choose between Closed Source (OpenAI) or Open Source (Ollama) for flexible summarization and conversation.

Multilingual-RAG★ 15

multilingual RAG

FileSearchStore-extension★ 15

This repository introduces a Gemini CLI extension that integrates File Search feature. This tool provides a fully managed Retrieval-Augmented Generation (RAG) system directly in your command line, enabling content generation grounded in your private documents and data.

rag-langchain-nodejs★ 15

Getting started with RAG system using Langchain in Node.js. This project uses OpenAI for embedding and Pinecone for Vector DB.

LLM-Chat★ 15

Implementing Chat with Pdf using langchain, React, Cohere & Postgres

chatbot_with_pdf_streamlit★ 15

This code example shows how to make a chatbot for semantic search over documents using Streamlit, LangChain, and various vector databases. The chatbot lets users ask questions and get answers from a document collection. The code is in Python and can be customized for different scenarios and data.

generativeai-questions-and-answers-app★ 15

Question and Answer application using AWS Bedrock, AWS ECS, Langchain, Qdrant, and FastAPI

local-llms-rag-cosmosdb★ 15

RAG application with LangChain and Local LLMs powered by Ollama

Agentic-AI-Chatbot-Llamaindex★ 15

Production-ready Agentic AI ChatBot using Llamaindex and Groq-Llama 3.3

LangGraphRAG★ 15

LangGraphRAG: A terminal-based Retrieval-Augmented Generation system using LangGraph. Features include message history caching, query transformation, and vector database retrieval. Ideal for NLP researchers and developers working on advanced conversational AI and information retrieval systems.

let-me-confluence-that-for-you★ 15

A GPT-based chatbot who knows the content of your Confluence wiki.

talking-pdf★ 15

Talking PDF, powered by GPT3 & Next.js

question-answering-chatbot-with-vector-store★ 15

It is a chatbot for question and answering using RAG based on LLM

pdfwhisper-openai★ 15

PDFwhisper allows you to have a conversation with your PDF docs. Finding info on PDF files is now easier than ever. 🚀🔥 Most secure authentication measures using Passkeys🔑

claude-pdfchat★ 15

Chat with PDF powered by Anthropic's Claude AI on Amazon Bedrock!

Examplify★ 15

An offline CPU-first low-resource chat application to perform RAG on your corpus of data. Powered by OpenChat and CTranslate2.

Maux-API★ 15

open source API for your RAG Workflows. by Maux

nucleus★ 15

Nucleus is a modular Rust library for building advanced local AI tools and applications, built-in RAG for private documents, and an extensible plugin system for custom workflows.​

rag-chat-bot★ 15

A Retrieval-Augmented Generation (RAG) Chat Bot that provides accurate responses based on available documents. This application uses PostgreSQL with pgvector extension for storing and searching vector embeddings, and OpenAI for generating embeddings and responses.

grag★ 15

GRAG is a simple python package that provides an easy end-to-end solution for implementing Retrieval Augmented Generation (RAG). The package offers an easy way for running various LLMs locally, Thanks to LlamaCpp and also supports vector stores like Chroma and DeepLake.

nexusync★ 15

Intuitive RAG system on top of LllamaIndex

ReT-2★ 15

[TPAMI 2026] Recurrence Meets Transformers for Universal Multimodal Retrieval

kryten★ 15

Kryten is a CLI tool to ask questions and get sourced answers from any .pdf, .doc, .docx, and many more documents.

Hashtag★ 15

Hashtag is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestration, letting you easily develop and deploy complex question-answering systems without the need for extensive setup or configuration.

OpenAI_Assist_All_Tools★ 15

Simple demo of OpenAI Assistant with all tool types

OSM-chatbot★ 15

Chatbot that answers OpenStreetMap-related queries powered by Rasa Open Source.

llama-index-vector-search-javascript★ 15

A sample app for the Retrieval-Augmented Generation pattern using LlamaIndex.ts, running in Azure, using Azure AI Search for retrieval and Azure OpenAI large language models to power ChatGPT-style and Q&A experiences using your own data.

hugo-Community★ 15

Foundational platform for integrating knowledge and AI. Simple, Secure and adaptable to your use case.

openwebui-knowledgesync★ 15

synchronizes a directory with e.g. markdown files with a knowledge base in OpenWebUI

Reducing-Hallucinations-in-LLM-Agents-with-a-Verified-Semantic-Cache★ 15

This repository contains sample code demonstrating how to implement a verified semantic cache using Amazon Bedrock Knowledge Bases to prevent hallucinations in Large Language Model (LLM) responses while improving latency and reducing costs.

RAG-MCP★ 15

Simple RAG implementation from scratch using MCP, focusing on Perception, Memory, Decision and Action

mt_llmkit★ 15

A Flutter toolkit for local and cloud LLM apps. Run GGUF models on Android and iOS, connect to OpenAI, Gemini, Claude and others through one unified API, and build fully local RAG pipelines. Supports streaming, multimodal vision models, and mobile-first AI workflows.

PFRP★ 15

[2026 AAAI] Predicting the Future by Retrieving the Past

RAG-FundaMentals★ 15

🔰 A Comprehensive RAG repository covering basic vanilla RAG techniques, advanced retrieval methods, hybrid search fusion approaches, hands-on reranking techniques with code + explanation 📚✨

dspy-opt★ 15

Advanced RAG pipeline optimization framework using DSPy. Implements modular RAG pipelines with Query-Rewriting, Sub-Query Decomposition, and Hybrid Search via Weaviate. Automates prompt tuning and few-shot selection using GEPA, SIMBA, MIPRO, COPRO, and BootstrapFewShot optimizers on datasets like FreshQA, HotpotQA, TriviaQA, Wikipedia and PubMedQA.

Hashtag★ 15

Hashtag is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestration, letting you easily develop and deploy complex question-answering systems without the need for extensive setup or configuration.

id-legal-rag★ 15

Hybrid RAG over Indonesian legal documents (UU, PP, Perpres, court decisions) with local LLM via Ollama.

mtcb★ 15

The chunking benchmark

Mistral-RAG★ 15

transformers safetensors mistral text-generation it dataset:DeepMount00/gquad_it

Hashtag★ 15

Hashtag is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestration, letting you easily develop and deploy complex question-answering systems without the need for extensive setup or configuration.

NexusMind★ 15

Local-first Agentic RAG engine - GraphRAG, hybrid retrieval (BM25 + dense + RRF + rerank), multi-agent orchestration, MCP-native, 100% local inference via Ollama.

ragfs★ 15

Agentic FUSE filesystem for LLM agents. Structured file operations with JSON feedback, audit logging, undo support, and semantic search.

astrbot-rag-kb★ 15

中文互联网梗 / 黑话 RAG 语料库:5 个分层知识库(4544 条 chunk)+ AstrBot 导入工具 + 使用 wiki。

aps-design-chatbot★ 14

Simple chatbot for querying metadata of designs in Autodesk Platform Services using Amazon Bedrock.

web-search-ollama-qwen-local★ 14

Local LLM Web search using qwen model and Ollama

corgiai★ 14

Community retrieval augmented generation AI

AI-Chatbot★ 14

Multi-User Chatbot with Langchain and Pinecone in Next.JS

More in Data, search & knowledge