Data, search & knowledge

RAG & retrieval pipelines

5,258 agents · most starred first

RAG & retrieval pipelines, page 25 of 53

RAG-Qwen2.5-7B★ 6

transformers pytorch qwen2 text-generation text-generation-inference unsloth

PDF-Assistant★ 6

streamlit region:us

RAG-Financial-Multimodal★ 6

gradio finance rag nlp document-question-answering multimodal openai gemini

rag-traffic-vn★ 6

RAG for Vietnamese traffic law with OCR ingestion, FAISS retrieval, source citations, LangSmith tracing, and human review for evals.

Legal-RAG★ 6

RAG-ChatBot for Vietnamese Legal Document

Pleias-SLM-RAG★ 6

gguf rag retrieval-augmented-generation llama-cpp flask raspberry-pi

sigir26-nuggetindex★ 6

Reproducibility artefacts for "NuggetIndex: Governed Atomic Retrieval for Maintainable RAG" — annotation tool, RQ runners, baselines, and evaluation scripts. SIGIR 2026.

ostk-recall★ 6

Local-first cross-corpus retrieval MCP server — model2vec embeddings + LanceDB (Tantivy BM25) + SQLite. One binary; hybrid (dense + BM25) search across markdown, code, and Claude Code sessions.

research-assistant★ 6

A local AI research assistant with streaming chat, Hybrid RAG, and document search.

irisChatGPT★ 6

🏆 Application of the Year Winner — AI assistant for InterSystems IRIS powered by LangChain, ChatGPT, FHIR, RAG, Streamlit, and Embedded Python.

TerrariaAIHelpDesk★ 6

A Multi-Agent RAG Support System using Google ADK, Milvus, Supabase, and Crawl4AI

lab-resource-reservation-platform★ 6

Backend reservation and knowledge Agent platform with Spring Boot, FastAPI, RAG, Redis and RocketMQ

contract-analyst★ 6

Agentic RAG system for analyzing legal contracts. Chat with agreements, extract clauses, flag risks, and compare terms using a local LLM.

FennecRAG★ 6

Local AI-powered RAG designed to understand your documents effortlessly.

ResearchOS★ 6

ResearchOS — a local-first AI research assistant with streaming chat, Hybrid RAG, and document search.

mastra-agentic-rag★ 5

TypeScript AI agent with retrieval-augmented generation (RAG) using Mastra, Vercel AI SDK, OpenAI, and LibSQL/pgvector-ready — local-first RAG pipeline

rag-chatbot★ 5

A FastAPI application that uses Retrieval-Augmented Generation (RAG) with a large language model (LLM) to create an interactive chatbot. This chatbot leverages PostgreSQL vector store for efficient document retrieval and supports text and CSV data sources for initialization.

Hybrid-Search-RAG★ 5

This repository contains a production-ready Hybrid Search Retrieval-Augmented Generation (RAG) system built using Python, FastAPI, Pinecone, and Llama 3 (served via Groq).

notion-chatbot★ 5

This AI-powered app enables users to ask questions to their Notion database using natural language.

DocQA-TextSummarization-App★ 5

A Streamlit app for document question answering and text summarization.

Custom-Chatbot-for-University★ 5

Customizable RAG chatbot made with LangChain, ChromaDB, Streamlit using gpt-3.5-turbo, text-embedding-ada-002 also sporting database integration

pdf-insights-interactive-q-and-a-with-llamathree-groq-api★ 5

Click below to visit my website

rag-agent★ 5

🎓 RAG Agent: Intelligent University Policy Assistant

open-ragbook★ 5

一个基于RAG(Retrieval-Augmented Generation)技术的智能知识管理系统,支持多种大语言模型和嵌入模型的集成与管理。

Tiny-RAGFlow★ 5

Tiny-RAGFlow is a lightweight Retrieval-Augmented Generation (RAG) framework designed for quickly building efficient vector retrieval systems.

RAG-project★ 5

This project is a Retrieval-Augmented Generation (RAG) system that allows users to upload PDF documents and ask questions about the content, with responses generated using OpenAI's GPT model.

cookbook-chat★ 5

Source code for the Gilded Age Gourmet, a cooking chat app based on the Boston Cooking-School Cook Book.

Rag-Agent-Chatbot★ 5

An all-in-one AI assistant powered by LLMs, RAG pipelines, and agents for chatting, summarizing, searching, and answering questions.

Intelligent-Query-Retrieval---Rocchio★ 5

by BYTE BUILDERS

chat-with-documents★ 5

Chat With Documents is a Streamlit application designed to facilitate interactive, context-aware conversations with large language models (LLMs) by leveraging Retrieval-Augmented Generation (RAG). Users can upload documents or provide URLs, and the app indexes the content using a vector store called Chroma to supply relevant context during chats.

groq-rag★ 5

Extended Groq SDK with RAG (Retrieval-Augmented Generation), web browsing, and AI agent capabilities. Features include document retrieval, web search, URL parsing, and ReAct-style agents with tool use.

quickrag★ 5

🔍🤖 A fast and flexible RAG tool for indexing and querying documents

AgentRag★ 5

.NET 10 solution showcasing RAG agents with query reformulation, contextual search, source-aware answers, streaming console responses, and ASP.NET Core REST/AG-UI endpoints built with Microsoft Agents AI and OpenAI.

foxnose-python★ 5

Official Python SDK for FoxNose

Portable_TA★ 5

Portable_TA is a lightweight, OpenAI-compatible LLM service that acts as an always-available AI Teaching Assistant. It provides document-grounded answers using RAG, maintains conversation memory, and integrates easily with tools like OpenWebUI for fast, portable, and intelligent student support.

pinecone-rag★ 5

Using Pinecone, LangChain + OpenAI for Generative Q&A with Retrieval Augmented Generation (RAG).

Gemini-LangChain-MultiPDF-Chatbot★ 5

Gemini-Powered-MultiPDF-Chatbot is a Streamlit application that leverages Google Generative AI Gemini and LangChain for conversational question-answering based on PDF documents. This chatbot allows users to ask questions related to the content of uploaded PDF files.

Rag-doc-assistant★ 5

Production-ready Retrieval-Augmented Generation (RAG) system for PDF question-answering. Built with LangChain LCEL, OpenAI GPT-3.5, and ChromaDB vector store. Features smart chunking, persistent storage, and source tracking. CLI included.

GeminiAi-★ 5

Using FineTune Models for Document Q/A and Chatbots

llm_rag★ 5

Chat with AI

chatbot★ 5

Built a FastAPI backend for an AI chatbot with RAG capabilities, supporting website, PDF, and text data ingestion. Implemented FAISS-based retrieval with embeddings and integrated a Groq LLM for context-aware responses.

Viam-Docs-Chatbot★ 5

This project is a chatbot that lets you ask the Viam docs questions to help you in your next Robotics project.

knowledgebot★ 5

A Q&A RAG AI assistant and web crawler

ai-portfolio-platform★ 5

This repository provides a complete solution, including a React frontend, a Python backend with advanced RAG capabilities, and a containerized infrastructure for seamless deployment.

pdf-chat-app★ 5

A full-stack AI-powered application that lets users upload and chat with their PDF documents. It combines seamless PDF processing, intelligent responses, and a minimalistic design to deliver a smooth and intuitive user experience.

LLM-Blog-Answer-Generator★ 5

A Retrieval-Augmented Generation (RAG) framework utilizing Large Language Models to answer queries based on blog articles.

PromptlicityAI★ 5

PromptlicityAI is a platform for storing and managing custom content, enabling users to retrieve knowledge-based responses via API calls. It simplifies AI integration by allowing structured content storage and retrieval without requiring expertise in Retrieval-Augmented Generation (RAG) or complex frameworks.

FinAI★ 5

🚀Information Retrieval & Question Answering 🔥LLMs 🌐Streamlit

RAG-Chatbot★ 5

My first RAG question-answering app that answers questions based on files uploaded. The app has been deployed on streamlit

RAG-Simplified★ 5

Enhance GPT-3.5-Turbo output using Retrieval-Augmented Generation (RAG) with a user-friendly interface. Select between Wikipedia or integrate external documents to experience precise, context-aware responses.

FullStackChatbot★ 5

Full stack LLM application created using React and FastAPI for document chatting

openai-embeddings-api★ 5

Nodejs a REST API is designed to provide users with an interactive chat interface where they can ask questions and receive responses generated by an AI model. The application utilizes OpenAI embeddings and Langchain to process the user's input and generate relevant responses based on the context of the conversation.

chat-with-doc★ 5

RAG pipeline using LangChain, Gemini pro, Faiss

llama3_qa_chatbot_mongodb★ 5

Llama3 in MongoDB: Conversational QA App with Langchain + Ollama + MongoDB + Streamlit.

DocuVisQA★ 5

DocuVisQA(Document Visual Question Answering) is a Python project that leverages Google's Generative AI and Langchain for document processing, text splitting, and question answering. It also supports image processing with Streamlit for interactive UI.

chatpdf-ai-powered-document-interaction★ 5

ChatPDF leverages Retrieval Augmented Generation (RAG) to let users chat with their PDF documents using natural language. Simply upload a PDF, and interactively query its content with ease. Perfect for extracting information, summarizing text, and enhancing document accessibility.

RAG-Pipeline★ 5

In this project I have built a RAG pipeline to showcase how we can augment LLM knowledge with additional data.

rag_extraction★ 5

A tutorial on how to build Summary Brief from Evaluation Report - Offline+Open Source

FileChat-RAG★ 5

FileChat-RAG is a simple Retrieval-Augmented Generation (RAG) system that allows users to ask questions about the contents of various file formats. It extracts text from PDFs, JSON, text files(.txt, .docx, .odt, .md), and code files, then enables interactive conversations using an LLM powered by Ollama.

BLOGing-AI★ 5

A simple application for blog content retrieval implemented using RAG as the core technology.

trustii-secure-rag-system★ 5

Solution for the Trustii's "Secure RAG System" Data Challenge 2024

gpt-pdf-bot★ 5

A gpt bot which allows you to chat with multiple pdfs.

OpenAI-bring-your-own-data★ 5

Langchain | OpenAI | Train with Custom markdown data

cognis★ 5

A Rust implementation of the RAG ecosystem

IntelliDocChat★ 5

AI-driven document chat app. Engage in dynamic conversations with PDFs using Langchain, ChromaDB, Sentence Transformers, and Streamlit. Gain insights interactively.

papermind-ai★ 5

PaperMind AI is a modern PDF document chat application powered by AI that allows you to upload PDF documents and have intelligent conversations about their content..

Airline-QnA-Bot★ 5

RAG-powered HR policy Q&A bot: query Flykite Airlines employee handbook via natural language. LangChain, FAISS/ChromaDB, OpenAI/Claude. Source attribution & hyperparameter tuning.

llm-prototypes★ 5

Google Summer of Code 2023; Experimental projects with LLMs such as RAG-based langchain agent chatbot

RAG-PDF-ChatBot★ 5

RAG-Based PDF ChatBot is an AI tool that enables users to interact with PDF content seamlessly. Powered by Ollama LLM and LangChain, it extracts and provides accurate answers from PDFs, enhancing document accessibility and usability. Perfect for efficient information retrieval.

thesis-rag-chatbot-gemini★ 5

retreival augmented generation based chatbot using langchain and google's gemini which reduces hallucination and gets the latest data ensuring privacy and concise answers

Pluto.ai★ 5

A conversational Retrieval Augmented Generation (RAG) chatbot built with LangChain, Chainlit, and the Claude API for question-answering from documents.

adora★ 5

Python package that makes it easy to spin up a custom Retrieval-Augmented Generation (RAG) pipeline.

pdfai★ 5

A Nextjs and stripe integrated Saas app starter where users can upload their own pdf and chat with their pdf with openai apis bootstraped with shadcnUI React-Query Zod using neon-DB

Vectify★ 5

Vectify integrates SAP HANA Cloud Vector Engine with Langchain and SAP Generative AI Hub to enhance generative AI use cases like automatic replies and issue deduplication. It demonstrates Retrieval Augmented Generation (RAG) for business context embedding.

ElasticSearch-LLM★ 5

A QA Bot based on Retrieval Augmented LLM

PDF-Chatbot★ 5

This repository contains a chatbot designed to answer questions about the content of PDF documents. It leverages the power of LangChain to extract information from PDFs, OpenAI's API for natural language processing and generation, and Pinecone as a vectorstore.

XEPT-1.0★ 5

It is a LLM where we given the links related to the new articles, then it answers the questions based on the content in the link.

colab-ai★ 5

Private AI chat for running LLMs w/ RAG

RAGLink★ 5

一个开源的RAG框架,旨在为用户提供了一个强大、灵活且简单的开发环境。

openai-rag-chatbot★ 5

Demo LLM (RAG pipeline) web app running locally using docker-compose. LLM and embedding models are consumed as services from OpenAI.

Asknotes★ 5

Langchain based AI RAG chat for question answering from PDF notes

llama2-langchain-chainlit-pdf★ 5

Chatbot using Llama2 model, Langchain and Chainlit to make a LLM review pdf documents.

askdoc★ 5

The Intelligent "ASKDOC" project combines the power of Langchain, Azure, OpenAI models, and Python to deliver an intelligent question-answering system, that scans your PDF documents and answer queries based on its contents. It can be queried using Human Natural Language.

mini_RAG_LLM★ 5

A minimal example for in-memory RAG using ChromaDB and Ollama LLM

StudyBot★ 5

Revise your subjects with studybot using RAG

info_gpt★ 5

Information Retrieval chatbot to get answers on your internal data.

pdf-ai-saas★ 5

Full stack (Next.js) PDF AI SaaS App

DocGPT★ 5

Ues langchain to build up document Q&A assistant

RagImplementation★ 5

Implementing Retrieval Augmented Generation (RAG) via using GPT-3.5-Turbo as the LLM model and Langchain to simplify the implementation, with the data being feed is in the form of list to make it easier to understand.

RAG-Ai-Agent★ 5

AI-powered agent leveraging RAG (Retrieval-Augmented Generation) with tool integration capabilities. Built with langchain, OpenAI, FastAPI, React frontend, it combines document-based knowledge with real-time data access and calculation tools to provide context-aware responses.

RAG-StreamLitDocs★ 5

Streamlit-powered document query web app

RAG_in_CPU★ 5

This repo is for advanced RAG systems, each branch will represent a project based on RAG.

Bookshelf-QABot★ 5

Multi-model knowledge assistant/QA-Bot based on Langchain, leveraging LLMs, RAG, FastAPI and Gradio

RAG-LangChain-QA★ 5

Retrieval Augmented Generation using LangChain and FAISS.

Medical-RAG-System★ 5

Retrieval-augmented generation (RAG) system for medical Q&A using the Merck Manual of Diagnosis and Therapy (19th Edition). Semantic search via ChromaDB and GTE-large embeddings; answer generation with Mistral 7B (GGUF). Runs fully locally for privacy, with optional GPU acceleration.

VChat-BigDL★ 5

🤖VChat-BigDL: A ChatBot for Video Understanding Based on BigDL

chat-with-PDFs-using-LLMs★ 5

Simple PDF chatbot using LangChain, OpenAI API, FAISS and Streamlit.

reprebot★ 5

A chatbot that uses Retrieval Augmented Generation (RAG) to answer questions for the Faculty of Engineering community at the National University of Colombia.

multimodalragApp★ 5

Advanced multimodal RAG system for querying PDF documents with text, images, and tables using vector embeddings, semantic chunking, and LLMs via Groq API

llm-fastapi-example★ 5

FastAPI + Hugging Face Transformers + LlamaIndex

More in Data, search & knowledge