Beginner-friendly tutorials and example projects for building applications using generative AI (LLMs, VLMs, TTS, AST, etc)
This repository contains code and tutorials for leveraging generative AI models to create powerful applications. The tutorials explore the capabilities of these models across various modalities, including:
- Input: Look, Read, Listen
- Actions: Think, Move
- Output: Write, Draw, Say
Learn how to build a local AI image tagger with Llama 3.2 Vision with Ollama and ChromaDB. This project combines look and write capabilities. This project has its own repo and can be pulled to run locally.
Learn how to turn voice recording into coherent writing with Whisper V3 Turbo and a locally hosted LLM. This project combines listen, think, and write capabilities.
Learn how to build your own news podcast with a free news API, local-running Llama-3 and xTTS. This project combines read, write, and say capabilities.
Learn how to build a generative search engine powered by a locally hosted LLM. This tutorial demonstrates how to perform online searches with local LLM. This project combines read, move, and write capabilities.
Explore how to build a podcast summarizer application using Whisper (for speech-to-text) and LLM (for summarization). Both models can be run completely locally. This project showcases how to combine listen and write capabilities of generative AI models.
- Local-LLM-Comparison-Colab-UI: Colab WebUI for many local LLMs that can be run on consumer-grade graphics card or on CPU.
- AI-Professional-Prompts: a collection of GPT prompts that are carefully designed to provide more consistent, high-quality results
Stay tuned for more exciting tutorials and projects as we continue to explore the potential of generative AI in creating innovative and powerful applications.