From e2eccace98860432511764a2984952202662e0da Mon Sep 17 00:00:00 2001 From: Bruno Capuano Date: Sun, 23 Feb 2025 17:24:55 -0500 Subject: [PATCH 1/2] Update README and setup guide with instructions for pulling local models using Ollama Details Update lesson 2 readme to include the ollama details --- 02-SetupDevEnvironment/readme.md | 17 +++++++++++++++++ README.md | 12 ------------ 2 files changed, 17 insertions(+), 12 deletions(-) diff --git a/02-SetupDevEnvironment/readme.md b/02-SetupDevEnvironment/readme.md index 853545b..0aaf84c 100644 --- a/02-SetupDevEnvironment/readme.md +++ b/02-SetupDevEnvironment/readme.md @@ -33,6 +33,23 @@ Here's a quick rundown of the services: > - **Azure OpenAI** have your eye? [This is the document for you](getting-started-azure-openai.md). > - **Ollama** your choice? [This guide has the info you need](getting-started-ollama.md). +### **NOTE for local models with Ollama:** + +The Ollama Codespace will provision all the necessary models that you need. However, if you are working in local mode, once you have installed Ollama, you need to pull the models for the lessons you want to run. + +- For lesson "**02 - Setting Up for .NET Development with Generative AI**" and project [MEAIFunctionsOllama](https://github.com/microsoft/Generative-AI-for-beginners-dotnet/tree/main/02-SetupDevEnvironment/src/BasicChat-03Ollama) you need to pull model [llama3.2](https://ollama.com/library/llama3.2) by entering in terminal + +```bash +ollama pull llama3.2 +``` + +- For lesson "**03 - Core Generative AI Techniques with .NET**", when running the ollama projects like [RAGSimple-10SKOllama](https://github.com/microsoft/Generative-AI-for-beginners-dotnet/tree/main/03-CoreGenerativeAITechniques/src/RAGSimple-10SKOllama), you need to pull the models [all-minilm](https://ollama.com/library/all-minilm) and [phi3.5](https://ollama.com/library/phi3.5) by entering in terminal: + +```bash +ollama pull phi3.5 +ollama pull all-minilm +``` + ## Learn and test AI models with GitHub Models **GitHub Models** provides an intuitive way to experiment with various AI models directly within your development environment. This feature allows developers to test and interact with different models, understanding their capabilities and limitations before implementation. Through a simple interface, you can explore model responses, evaluate performance, and determine the best fit for your application requirements. Hosted within GitHub's infrastructure, these models offer reliable access and consistent performance, making them ideal for development and testing phases. Best of all, there is a free tier to start your exploration without any cost. diff --git a/README.md b/README.md index b9f9c59..06c9d18 100644 --- a/README.md +++ b/README.md @@ -36,18 +36,6 @@ Generative AI is transforming software development, and .NET is no exception. Th You'll learn how to implement Generative AI into .NET projects, from basic text generation to building full-fledged solutions using **GitHub Models**, **Azure OpenAI Services** and **local models with Ollama**. -#### **NOTE for local models with Ollama:** - -- For lesson "**02 - Setting Up for .NET Development with Generative AI**" and project "**MEAIFunctionsOllama**" you need to pull model "**llama3.2**" by entering in terminal - - **ollama pull llama3.2** - -- For lesson "**03 - Core Generative AI Techniques with .NET**" and project "**RAGSimple-10SKOllama**" you need to pull 2 models "**all-minilm**" and "**phi3.5**" by entering in terminal: - - **ollama pull phi3.5** - - **ollama pull all-minilm** - ## 📦 Each Lesson Includes - **Short Video**: A quick overview of the lesson (5-10 minutes). From 0a7df2d21cd6351ad28b4e7a686ec5b3d503bafc Mon Sep 17 00:00:00 2001 From: Bruno Capuano Date: Sun, 23 Feb 2025 17:26:52 -0500 Subject: [PATCH 2/2] Fix image filename in README and remove obsolete image file --- ...models-webapge.png => github-models-webpage.png} | Bin 02-SetupDevEnvironment/readme.md | 2 +- 2 files changed, 1 insertion(+), 1 deletion(-) rename 02-SetupDevEnvironment/images/{github-models-webapge.png => github-models-webpage.png} (100%) diff --git a/02-SetupDevEnvironment/images/github-models-webapge.png b/02-SetupDevEnvironment/images/github-models-webpage.png similarity index 100% rename from 02-SetupDevEnvironment/images/github-models-webapge.png rename to 02-SetupDevEnvironment/images/github-models-webpage.png diff --git a/02-SetupDevEnvironment/readme.md b/02-SetupDevEnvironment/readme.md index 0aaf84c..b3e466e 100644 --- a/02-SetupDevEnvironment/readme.md +++ b/02-SetupDevEnvironment/readme.md @@ -54,7 +54,7 @@ ollama pull all-minilm **GitHub Models** provides an intuitive way to experiment with various AI models directly within your development environment. This feature allows developers to test and interact with different models, understanding their capabilities and limitations before implementation. Through a simple interface, you can explore model responses, evaluate performance, and determine the best fit for your application requirements. Hosted within GitHub's infrastructure, these models offer reliable access and consistent performance, making them ideal for development and testing phases. Best of all, there is a free tier to start your exploration without any cost. -![Image for GitHub Models page, demonstrating multiple generative AI models](./images/github-models-webapge.png) +![Image for GitHub Models page, demonstrating multiple generative AI models](./images/github-models-webpage.png) ## Pre-flight check: Setting up GitHub Access Tokens