Create an AI-powered meeting summary tool with Python, Ollama, and Gemma

MaskClaw项目构建了一套基于端侧多模态大模型的自进化隐私防护架构，通过视觉脱敏与Agentic 规则演进，实现了 Agent 行为偏好与隐私防护策略的动态协同生长，确保了高危隐私数据在云端交互中的物理级安全与个体化适配。

Build LLM-enabled FastAPI applications without build configuration.

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

stud-IA made by Pizza numbers group. EdTech Challenge, AI google developer hackathon. Build with gemma-2b.

Explore the power of Gemma model with GemGPT, a project leveraging AI for innovative solutions. Join us in shaping the future of AI!

Invoice OCR Extraction Flask API

An advanced spam detection model fine-tuned from Gemma 2 2B for WhatsApp chatbots. Capable of identifying spam categories like abusive language, gibberish, and malicious links. Includes training, inference scripts, and configurable settings for customization. 🚀

An AI-powered Legal Information Retrieval System for Indian Laws and Court Judgments, built using FastAPI, LlamaIndex, and the Gemma 2B-IT model enabling offline, privacy-preserving, and semantic legal search.

gemma with questions

Welcome to the Exploding Population Myths 1995 repository! This project leverages the Google Gemma model to analyze and debunk common population myths from 1995 book, providing valuable insights into historical population trends.

Linear Algebra project Comparison of TF-IDF, Word2Vec, and Gemma-2B embeddings for Persian text semantic similarity with SVD dimensionality reduction., implemented in Python

A multiverse of AI models | Built with GROQ

A local, privacy-preserving RAG-based chatbot built with LangChain, ChromaDB, and the Gemma 2B model served via Ollama. It supports question answering over uploaded documents and URLs, with no external APIs or internet dependency.

GemmaLangServeAPI is a FastAPI-based API service that leverages Google’s Gemma 2B language model via Hugging Face Transformers and LangChain. It provides a /explain endpoint for code explanation, supports easy deployment with ngrok, and is ideal for educational, debugging, or AI-assistance use cases.

AskPdf is a Streamlit-based application for question-answering over PDF documents using Retrieval-Augmented Generation (RAG) with conversational history. Upload your PDFs and interactively ask questions to get concise, contextually relevant answers, leveraging LangChain, Chroma for vector storage, and HuggingFace embeddings.

An automated Telegram bot that generates daily briefings by collecting Emails and Canvas deadlines, using AI to summarize key information for users.

This repository contains the code for the GemmaGroq RAG Engine, which integrates Groq's AI capabilities with a custom RAG (Retrieval-Augmented Generation) system.

Agentic SRE for Kubernetes ☸️ cloud-native experiment exploring AI for SRE workflows inside Kubernetes. Monitors pod health, ChromaDB memory , local LLM (Gemma via Ollama) 🦙 for restart/ignore decisions. Focus: Kubernetes automation ⚙️, LLM-driven decisions 🧠, vector memory 📚, self-healing systems 🔁. Not production-grade-learning AI+ Devops

A Retrieval-Augmented Generation (RAG) tool that enables natural language conversations with any public GitHub repository with Gemma 2 2b.