# ryzenai_notebook

**Repository Path**: Vickyiii/ryzenai_notebook

## Basic Information

- **Project Name**: ryzenai_notebook
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2025-05-07
- **Last Updated**: 2025-08-23

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# Ryzen AI Notebook

Welcome to the Gen AI Playground, a collection of notebooks designed to showcase generative AI workloads on AMD Ryzen AI PCs.

## Table of Notebook Contents

### Vitis HLS Teaching Assistant

* [HLS Agent](./hls_agent/README.md)


### LLM

* Tutorial
  - [Lemonade Tools Tutorial](https://gitee.com/Vickyiii/ryzenai_notebook/blob/master/llm/tutorial/lemonade_model_validation.ipynb)
* RAG
  - [Implementing RAG using Langchain on AI PC](https://gitee.com/Vickyiii/ryzenai_notebook/blob/master/llm/rag/streamlit_rag_noteook.ipynb)

- Agent
  - [Travel Agent using Langchain on AI PC](https://gitee.com/Vickyiii/ryzenai_notebook/blob/master/llm/travel_agent/AI_Travel_Agent_Tutorial.ipynb)

* Chat
  - [CLI Chatbox Using Lemonade API on AI PC](https://gitee.com/Vickyiii/ryzenai_notebook/blob/master/llm/chat/chat_hybrid.py)
* Search
  - [Search App Using Lemonade API on AI PC](https://gitee.com/Vickyiii/ryzenai_notebook/blob/master/llm/search/search_hybrid.py)

- Lemonade Server Examples

| App                                                                        | Guide                                                                                                                         |
| -------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------- |
| [Open WebUI](https://github.com/open-webui/open-webui)                        | [How to chat with Lemonade LLMs in Open WebUI](https://ryzenai.docs.amd.com/en/latest/llm/server_interface.html#open-webui-demo) |
| [Continue](https://www.continue.dev/)                                         | [How to use Lemonade LLMs as a coding assistant in Continue](./llm/server/continue.md)                                           |
| [Microsoft AI Toolkit](https://learn.microsoft.com/en-us/windows/ai/toolkit/) | [Experimenting with Lemonade LLMs in VS Code using Microsofts AI Toolkit](./llm/server/ai-toolkit.md)                            |
| [CodeGPT](https://codegpt.co/)                                                | [How to use Lemonade LLMs as a coding assistant in CodeGPT](./llm/server/codeGPT.md)                                             |
| [MindCraft](mindcraft.md)                                                     | [How to use Lemonade LLMs as a Minecraft agent](./llm/server/mindcraft.md)                                                       |
| [wut](https://github.com/shobrook/wut)                                        | [Terminal assistant that uses Lemonade LLMs to explain errors](./llm/server/wut.md)                                              |
| [AnythingLLM](https://anythingllm.com/)                                       | [Running agents locally with Lemonade and AnythingLLM](./llm/server/anythingLLM.md)                                              |
| [lm-eval](https://github.com/EleutherAI/lm-evaluation-harness)                | A unified framework to test generative language models on a large number of different evaluation tasks.                       |

### Hardware

[AMD® Ryzen AI 300 or Ryzen AI Max](https://www.amd.com/zh-cn/products/processors/consumer/ryzen-ai.html#tabs-9f9c97e306-item-6e04e82b39-tab)

## Requirements

The Ryzen AI Software supports AMD processors with a Neural Processing Unit (NPU). Consult the release notes for the full list of supported configurations.

The following dependencies must be present on the system before installing the Ryzen AI Software:

| Dependencies           | Version Requirement |
| ---------------------- | ------------------- |
| Windows 11             | build >= 22621.3527 |
| Visual Studio          | 2022                |
| cmake                  | version >= 3.26     |
| Miniconda or Miniforge | Latest version      |

## Installation Steps

1. [Install NPU Drivers](https://ryzenai.docs.amd.com/en/latest/inst.html#install-npu-drivers)
2. [Install Ryzen AI Software 1.5.1](https://ryzenai.docs.amd.com/en/latest/inst.html#install-ryzen-ai-software)
3. [Install Lemonade ](https://github.com/lemonade-sdk/lemonade)

## Featured LLMs

The following tables contain a curated list of LLMs that have been validated on Ryzen AI hybrid execution mode. The hybrid examples are built on top of OnnxRuntime GenAI (OGA).

The comprehensive set of pre-optimized models for hybrid execution used in these examples are available in the [AMD hybrid collection on Hugging Face](https://huggingface.co/collections/amd/ryzenai-14-llm-hybrid-models-67da31231bba0f733750a99c). It is also possible to run fine-tuned versions of the models listed (for example, fine-tuned versions of Llama2 or Llama3). For instructions on how to prepare a fine-tuned OGA model for hybrid execution, refer to [Preparing OGA Models](https://ryzenai.docs.amd.com/en/latest/oga_model_prepare.html).

## Notebook Contribution Template

1. Required pip packages
2. Main Application Logic
3. Deployment details with Local LLM
4. Performance Analysis

## Reference

1. [Examples, Demos, Tutorials — Ryzen AI Software 1.5 documentation](https://ryzenai.docs.amd.com/en/latest/examples.html)
2. [TurnkeyML and Lemonade Tool](https://github.com/onnx/turnkeyml/tree/main)
3. [Amuse](https://www.amuse-ai.com/)
4. [Digest AI](https://github.com/onnx/digestai)