Bot MicroIA es un bot inteligente para Telegram, diseñado para ofrecer respuestas dinámicas y contextuales mediante modelos de lenguaje avanzados como LLaMA 2 y LLaMA 3, integrados a través de Ollama. Su arquitectura basada en Java y Spring Boot, junto con una API REST, permite una comunicación fluida y escalable entre el bot y los servicios.

A bash script manages the Ollama listener service and starts or stops the LLM llama3 model.

Adapted BERTopic pipeline for Topic Modeling the arXiv dataset

a discord bot with features like conversation summary and semantic question answering with ai.

This RAG Application used techniques like Similarity Search, Chain and Retriever to chat with our files using OllamaEmbeddings, LLAMA3, Chromadb, FaissDB.

Exploring Accelerated Compound AI Systems with SambaNova & Llama 3.3-70B

How to Build an Open-Source AI App Using Together.ai and Streamlit

An Llama based chatbot for medical advise.

Knowledge base using LLM/RAG running locally, with ollama + qdrant

AI狼人杀大乱斗

An LLM-based app to determine the most suitable educational or professional path.

WhatsApp Chatbot with AI

Congress Trade Tracker App Version 1.0, Utilizing LLaMa 3 for a chat bot interface, playwright to obtain congress trade data, yfinance to get historical information of trade tickers.

A simple local chat app using Flask and Ollama to run LLMs like llama3, command-r7b, and deepseek-r1. Switch models, chat in a web UI, and export history — all offline, no API keys needed.

An AI-driven assistant that enables users to interact with PDF documents through natural language queries. Leveraging Retrieval-Augmented Generation (RAG), this application combines the capabilities of React for the frontend and FastAPI for the backend to provide accurate and context-aware responses based on the content of uploaded PDFs.

Este proyecto es una IA local basada en Llama-3 que funciona directamente en tu navegador gracias a WebLLM. No depende de servidores externos: todo el procesamiento se ejecuta en tu dispositivo, garantizando privacidad, accesibilidad y baja latencia.

AI-powered backend service designed to provide university professors with deep, actionable insights into their lectures. Uses LLMs like OpenAI Whisper v3 and Llama 3.3 to transcribe, analyze and structure the content. Cross-references that content against the course syllabus to track progress; exposes a clean API to power a frontend dashboard.

LLM-powered extraction of structured data from messy car accident descriptions

ChatLlama🦙 is an AI chat bot inspired by ChatGPT running LLMs locally on an Ollama Server via Docker