Multimodal AI model based on Vision Transformers, implemented in approximately 500 lines of code

• educational
• transformers
• transformers code
• +3

Trove of Knowledge: Fully Local, Extensible, Open-Source RAG Chat with Docs 🔍💬

• artificial-intelligence
• docker
• flask
• +7

Gemini 1.5 - Terminal Aesthetics

• Aesthetics
• API
• Chatbot
• +9

LLM Analytics Accuracy - Evaluating Practical Implementations of Agentic SQL AI

Autonomous driving application car-detetction using YOLO

• #AI
• #AutonomousDriving
• #ComputerVision
• +4

lane tracking with image processing

• carla
• opencv
• sliding_window

Neural-Network-Image-Generator

• Image-Generator
• Neural-Network

shell assistantfor linux shell

• gpt
• linux
• shell

Movie streaming platform with Gemini LLM search

• gemini
• langchain
• llm
• +1

Ollama Git Commit Message Generator for Linux

YOLOv3 acceleration using a Low-cost FPGA

• Accelerator
• computer vision
• DPU
• +5

OpenAI/Anthropic-based PDF renamer

• anthropic
• openai
• pdf
• +2

ChatGPT for Discord

• ChatBot
• ChatGPT
• Discord
• +1

Lung disease recognition using a residual network

• cnn
• image classification
• residual network

JorEl: LLMs made easy - Multiple providers, images, documents, tools, and agents - in TypeScript

• agent-framework
• agents
• anthropic
• +5

Zed Math AI

• AI
• computer-vision
• zambia

Walaa Volidis AI Projects

• agent
• ai
• aws
• +7

Image compression with Auto-Encoders

• AI
• AutoEncoders
• DataCompression
• +3

ai_agent_project

• LLM
• openAI

Data Stream Anomaly Detection

• anomaly-detection
• moving-average
• numpy
• +1