RAG & retrieval pipelines
5,258 agents · most starred first
RAG & retrieval pipelines, page 29 of 53
Offline-capable preparedness search platform. Runs on Raspberry Pi, LAN, or air-gapped environments. Source-pack architecture, local LLM support via Ollama.
A production-ready, self-hosted RAG (Retrieval Augmented Generation) chatbot widget built with Next.js, Redis vector storage, and multiple AI model fallbacks. Perfect for embedding into portfolio websites or any web application.
Production-grade Corrective RAG (CRAG) & Hybrid Retrieval engine combining BM25 lexical search, Dense Vectors, Reciprocal Rank Fusion (RRF), and ONNX Cross-Encoder reranking.
Production-oriented RAG pipeline — PDF upload, FAISS retrieval, Groq LLM (free), custom evaluation metrics, Langfuse observability. Deployable on Hugging Face Spaces.
Experimental RAG study assistant for answering questions and generating learning materials from PDFs.
Enterprise AI RAG Assistant built with Hugging Face, Sentence Transformers, FAISS, and Streamlit. Supports semantic search, vector retrieval, and context-aware question answering using Retrieval-Augmented Generation (RAG).
RAG platform built from scratch - async pipelines, 5 chunking strategies, RAGAS evaluation, Celery workers, PostgreSQL lifecycle management
A privacy-first, open-source Retrieval-Augmented Generation platform with real-time confidence metrics and source highlighting
Source-grounded AI workspace for secure document intelligence, OCR, retrieval, and cited team conversations.
RAG Retrieval Lab: 15 retrieval-augmented generation strategies (hybrid RRF, HyDE, corrective, agentic, reranking) behind one interface, with pgvector, eval metrics and tracing; runs offline.
Building a RAG knowledge base in DuckDB with idempotent ingestion, multilingual embeddings, HNSW cosine search, and a local Qwen2.5-3B answer step with similarity threshold.
Evidence-first local workbench for industrial machine investigation.
Production-ready, distributed Retrieval-Augmented Generation (RAG) system built with Django, Celery, Redis, and ChromaDB for document ingestion, vectorization, and contextual QA.
One offline agent that answers across your tables, your documents, and the knowledge graph between them.
Seizure-prediction literature RAG for PDF folders, with optional Zotero, bilingual hybrid search, page-level evidence, and MCP clients.
Local-first knowledge asset lifecycle platform — ingestion, governance, retrieval, feedback loops & ops dashboard. Built with Django, PostgreSQL (pgvector), Redis.
RAG CLI for Oracle AI Database, super easy to set up
This project consist on ChatBot implementation with two approach: Retrival-Augmented Generation (RAG) and Fine-Tuning
A RAG-based AI agent for breast cancer that uses Qdrant to retrieve answers, filter relevance, and grow its knowledge base.
Experimenting with langchain document QA with a set of PDFs
RAG powered PDF Q&A with source citations. LangChain, FAISS and LLaMA 3.3 via Groq
An agentic multimodal RAG assistant with voice queries, PDF/image understanding, web search, and grounded answers.
PassiveQA is a novel question-answering framework that teaches language models when to answer, ask for clarification, or refuse to answer - instead of always attempting to generate responses.
An intelligent system combining a sophisticated data pipeline with an AI-powered chatbot. The system features document processing capabilities, multi-modal AI integration, and a scalable architecture.
Self-adaptive Planning Agent。自适应规划代理的多模态检索增强生成技术。
An intelligent document reasoning system with a Matrix-themed interface. Now fully private on your device! (no API keys or online deployment).
A simple helm chart automating deployment of a retrieval augmented generation (RAG) solution on K8s Clusters.
The AI agent for the German Jordanian University, focused on accurate university documents retrieval
PDF Analysis Telegram Bot with LLM Integration (GROQ + Ollama models)
AI RAG agent that reads company documents and answers questions like a trusted senior colleague. Built with Claude API, FastAPI, React, ChromaDB.
Intelligent Answers from Any Document
This repository showcases the implementation of a Multi-Agent Research RAG (Retriever-Augmented Generation) Tool built with LangGraph.
Large Language Model (LLM) chatbot with a custom knowledge base
A template of AI Chatbot built with Pinecone, LangChain, HarperDB and Next.js, deployed to Vercel.
RAG with Redis. Parallel implementations with/without guardrails.
Local-first RAG engine with cited answers from your own docs. GraphRAG, sealed sharing, MCP-native, VS Code Copilot integration. Nothing leaves your machine.
A powerful AI chatbot built with Streamlit and Groq API that combines text-based interaction, document processing, and vector search capabilities. Features include multi-format document handling (PDF, PPT, Excel) and intelligent model selection.
LangChain agent with ollama for QA your papers
A local multi-agent RAG system where four LangGraph agents (Planner → Retriever → Critic → Synthesizer) collaborate to answer research questions from academic PDFs, with real benchmark results: 87% RAGAS faithfulness, 22pp hallucination reduction via LLM-as-judge, and 0% failure rate under Locust load testing.
This is a Streamlit app that leverages LangChain, a language processing toolchain, to generate responses based on user prompts and perform document similarity searches using Chroma.
Privacy-first, fully local Retrieval-Augmented Generation app — chat with your PDFs/DOCX/TXT/CSV via Ollama, LangChain and ChromaDB. No API keys, no cloud.
Document understanding with GPT 3.5 integrated with Telegram
Simple Generative AI enabled Streamlit web application that answers general questions from PDF documents provided to it.
A simple Q & A App built using Python and Langchain
Agentic RAG with LangGraph 🔥
RAG-based conversational AI for Superior University — 4,750+ pages indexed using LangChain, FAISS, and Groq LLM
A conversational agent that answers user questions using transcripts from the Lex Fridman podcast.
建立數位銀行RAG增強檢索的問答機器人
LangChain integration for FoxNose
Using Doc2Vec, Langchain and OpenAI to chat with Natserract blog https://engineering-natserract.vercel.app/
Data Whisperer is a chatbot that allows you to analyze your local files using Large Language Models (LLMs). You can upload PDFs, Markdown, Text, and Document files to the chatbot and then ask questions related to the content of these files.
Question Answering Generative AI application with Large Language Models and RAG powered by Amazon Bedrock and Amazon Kendra
RAG model created in langchain using python to tune Gemini API and give it context through tokenization of pdfs into vectorization of the databases.
MultiDocWebchat combines the functionality of a PDF document reader with a powerful QA bot for in-depth document exploration.
In this project, I created an application using Google Gemini Pro and Langchain to process multiple PDF documents. We will use FAISS vector embeddings to enhance document processing capabilities.
This is a chatbot QA RAG project implemented using LangChain, which answers based only on the context and is flexible to update and integrate with different LLM models and various vector databases
Design and develop your own AI chatbot with Streamlit! This session will guide you through setting up a chatbot interface, integrating a language model, and handling user interactions—all with minimal code.
Production-ready Retrieval-Augmented Generation (RAG) platform for intelligent log analysis, error diagnostics, and incident resolution. Built with LangChain and LangServe, the system provides an API-first, modular architecture designed for scalable observability and DevOps workflows.
Ask Manyu App to let users chat with multiple PDFs. Built with LangChain, OpenAI, Streamlit.
A chatbot that let you talk with your pdf file
Python-based MultiPDF Chatbot using Hugging Face and StreamLit
This repo is build to facilitate the state-of-the-art RAGs approaches with it's use cases and detailed descriptions.
The AI-Powered assistant for jargons.dev ecosystem
A Multi-Modal Agentic RAG pipeline designed to handle unstructured documents containing tables, charts, and images. It integrates Docling and ElasticSearch for structured indexing, and leverages LangGraph for agent-based reasoning and dynamic query reformulation.
AI chatbot, using LangChain and the 8-bit quantised Falcon-7B LLM. Crafted a conversational agent with Retrieval Augmented Generation (RAG) pipeline.
Improved RAG Architecture using semantic chunker, query input rewriter, and prompt engineering
AI Chatbot web-app using Django, integrating LangChain with GPT-3.5 and RAG for adaptive querying, Whisper JAX for audio transcription and leveraging OpenAI-Embeddings for enhanced interaction with podcast content
In this project I have built an end to end advanced RAG project using open source llm model, Mistral using groq inferencing engine.
This project is a RAG Q&A bot built in a jupyter notebook. It allows users to upload a custom document, which is then processed and stored in a Pinecone vector database using OpenAI embeddings. Users can ask questions about the document's content and receive accurate, context-aware answers generated by an OpenAI language model.
基于语言模型的NLP应用
AI-powered Q&A chatbot using Qdrant and Ollama for retrieval-based responses about magnesium-binding protein structures. Integrates Flask for web interface.
LLM POCs
A RAG back and front end application
Pinecone Hackathon 2023: Codextranauts Team Repository.
📄 A template for project for creating a chainlit application, using a locally run model via ollama and qdrant vector database for document retrieval.
Servidor Node.js para Retrieval-Augmented Generation (RAG) utilizando LangChain e Qdrant.
PDF Question Answering (QA) powered by ChatGPT
Adding InMemoryCaching, Ensemble Retrievers,langchain, faiss for a open domain chatbot
A self deployable LLM application with our innovational IC framework (a RAG method)
Explore the cutting-edge world of advanced retriever and generator (RAG) models through the "Advanced-RAG-Experiments" repository. This collection of Jupyter notebooks and experiments is designed to provide a deep dive into the capabilities and nuances of advanced RAG models in the field of natural language processing.
In this tutorial we will see 💡 How to get answers from a YouTube video using Chroma vector database, PaLM LLM by Google, and a question answering chain from LangChain. And finally, use Streamlit to develop and host the web application. You will need to use your google_api_key (you can get one from Google).
This project implements a complete offline RAG-Fusion application for text generation and retrieval, leveraging efficient local resources.
Learning and building LLM application using Langchain 🦜🔗 and Open AI
Ask PDF AI is an innovative solution powered by artificial intelligence that revolutionizes document management. This cutting-edge platform seamlessly integrates natural language processing and machine learning technologies to enhance the way users interact with PDF files.
Advanced local-first RAG system powered by Ollama and LangGraph. Optimized for high-performance sLLM orchestration featuring adaptive intent routing, semantic chunking, intelligent hybrid search (FAISS + BM25), and real-time thought streaming. Includes integrated PDF analysis and secure vector caching.
This repository contains an end-to-end Retrieval-Augmented Generation (RAG) system that leverages Deepseek and Ollama to provide intelligent responses based on any pdf content.
RAG-Complete-Cook-Book is a practical guide and code collection for building Retrieval-Augmented Generation (RAG) pipelines. It provides step-by-step Jupyter notebooks and Python scripts covering the entire RAG workflow.
An interactive CLI-based Smart FAQ system powered by LangChain and FAISS that retrieves accurate answers using semantic search and HuggingFace embeddings.
Centralize your own research material and consult it with the power of AI and LLMs
Build an AI Chatbot to chat with any PDF
RAG technique for QA tasks with PDF, website and video, leveraging LLMs and the OpenAI API for interactive applications
The RAG LLM ChatBot leverages Langchain to provide a robust and flexible framework for building intelligent chatbots. It combines the power of retrieval-augmented generation (RAG) with large language models (LLMs) to deliver precise and context-aware responses.
A fully local RAG system using Ollama and a vector database. Private, fast, extensible.
Built a Retrieval-Augmented Generation (RAG) chatbot using LangChain and OpenAI models.
Discover knowledge with ease using - AzureOpenAI, Chroma, and Langchain. This solution generates a knowledge base from a given URL and efficiently responds to queries, streamlining the information discovery process.
AI Assistant to interact with PDF documents and get instant answers. Built using Langchain and Gradio.