AI any text or file clusterer & sorting

An AI book recommendation system built with Streamlit and Ollama. It uses 'nomic-embed-text' for semantic search and 'llama3.2:1b' for generating in-depth analyses of books and user queries.

AI any text or file clusterer & sorting

Local RAG Chatbot with Ollama on Mac

A RAG application for East West University (Only Science Faculty)

Simple agents are good for 1-to-1 retrieval system. For more complex task we need multi steps reasoning loop. In a reasoning loop the agent can break down a complex task into subtasks and solve them step by step while maintaining a conversational memory.

SOC Analyst Automation using a RAG model integrates a knowledge retrieval system with generative AI to automate SOC Level-1 tasks. It processes server logs, retrieves relevant security insights, and generates accurate responses, enhancing incident analysis, reducing response times, and improving efficiency in handling cybersecurity threats through

A Retrieval-Augmented Generation (RAG) using Llama Model Fine Tune - The system that extracts and embeds Cirebon cuisine knowledge into a PostgreSQL database with pgvector, enabling efficient retrieval and contextual responses using FastAPI and Docker.

🤖 Build a smart AI assistant that learns from any website using a Retrieval-Augmented Generation framework with local models powered by Ollama.

GPU constrained! No More. Microsoft released Phi3 specially designed for memory/compute constrained environments. The model support ONXX CPU runtime which offers amazing inference speed even on mobile cpu.

LlamaTalks is a Spring Boot-based chatbot application leveraging LangChain4j and Ollama for advanced conversational AI with Retrieval-Augmented Generation (RAG) capabilities. It supports streaming responses, conversation management, document ingestion, and persistent chat history.

buddyRAG - a small AI rag chatbot for chatting with your Markdown notes. Yep, you can use it with Obsidian.

Este repositório foi criado para rodar uma IA generativa com RAG 100% local.

Fractal is a sophisticated AI-powered CLI agent that brings intelligent coding assistance directly to your terminal. Built with LangChain and LangGraph, it combines advanced RAG capabilities, multi-database support, and context-aware memory management to provide a seamless development experience.

A Retrieval-Augmented Generation (RAG) project built with FastAPI, MongoDB, Qdrant, and JWT authentication—featuring secure document uploads, chunking, embeddings, and context-aware AI responses. Designed to be scalable, reliable, and production-ready.

This project demonstrates how to integrate text embeddings using nomic-embed-text and granite-embedding models with PostgreSQL and pgvector. You can perform similarity searches, text analysis, and more.

This project provides a FastAPI-based web application for scraping websites, storing the content in a FAISS index, and using a chatbot model (via Ollama) to answer queries based on the scraped data. The app handles pagination of websites and ensures that irrelevant content (such as ads, navigation, footers, etc.) is excluded from indexing.

YuccAI is a voice assistant website for Universitas Ciputra, offering real-time answers to university-related questions via voice commands. With conversation history and topic recommendations, it simplifies access to campus information through innovative AI technology.

MCP server that connects Claude to local Ollama models, delegating simple tasks to save tokens for complex reasoning