# GoogleCloudPlatform/generative-ai genai-sagemaker Directory: Tutorial Availability for Beginners > Discover if the GoogleCloudPlatform/generative-ai repository offers beginner tutorials for SageMaker integration. Learn about available resources for generative AI. - Repository: [Google Cloud Platform/generative-ai](https://github.com/GoogleCloudPlatform/generative-ai) - Tags: tutorial - Published: 2026-03-09 --- **The GoogleCloudPlatform/generative-ai repository does not contain a `genai-sagemaker` directory or any beginner tutorials specifically for AWS SageMaker integration.** Despite the repository's comprehensive collection of generative AI examples for Google Cloud platforms, a thorough analysis of the source code confirms that searching for `genai-sagemaker` returns no results, and the folder structure contains no SageMaker-specific onboarding materials for beginners seeking to deploy models on AWS infrastructure. ## Current State of the genai-sagemaker Directory An exhaustive examination of the repository's file tree confirms that **no `genai-sagemaker` directory exists** in the main branch. The glob pattern search across the entire codebase reveals a well-organized structure of tutorial collections, yet the specific `genai-sagemaker` path is completely absent. According to the source code analysis, the repository root contains active tutorial directories including `workshops/`, `open-models/`, `gemini/`, `embeddings/`, and `agents/`, but **no top-level or nested folder named `genai-sagemaker`** appears in the file listing located at the repository root. Additionally, a full-text search for the term "sagemaker" (case-sensitive) across all files in the codebase returns **zero matches**, definitively confirming that no references to SageMaker deployment patterns, configuration examples, or beginner guides exist in the current codebase. ## Existing Tutorial Directories for Beginners While the `genai-sagemaker` directory is unavailable for AWS-specific learning, beginners can access foundational materials through these verified alternative paths in the repository: - **`workshops/`** – Contains step-by-step notebooks covering retrieval-augmented generation, embeddings, and multimodal use-cases suitable for foundational learning - **`open-models/`** – Provides examples for deploying and serving open-source models on Google Cloud services - **`gemini/`** – Houses tutorials specifically for Google's Gemini model implementations and prompting techniques - **`embeddings/`** – Features beginner-friendly guides for vector embedding techniques and similarity search - **`agents/`** – Includes introductory materials for building AI agents and orchestration patterns These directories illustrate the repository's standard tutorial style, which typically includes Jupyter notebooks with detailed markdown explanations, executable Python code cells, and [`README.md`](https://github.com/GoogleCloudPlatform/generative-ai/blob/main/README.md) files providing setup instructions. ## Alternatives for SageMaker Beginners Since native `genai-sagemaker` tutorials do not exist within this repository, beginners seeking AWS SageMaker integration have three actionable pathways: **Adapt Existing Vertex AI Notebooks** Convert the existing tutorials found in `workshops/` and `open-models/` to the SageMaker environment. These notebooks contain foundational generative AI concepts—such as prompt engineering, RAG implementation, and model inference—that transfer to AWS infrastructure with modifications to the deployment and endpoint configuration cells. **Explore External Community Resources** Seek community-contributed examples or AWS-official sample repositories that specifically target SageMaker integration with generative AI models. The GoogleCloudPlatform/generative-ai repository maintains strict focus on Google Cloud Vertex AI and open-model deployments, so AWS-specific code must be sourced from dedicated AWS sample repositories. **Request Official Multi-Cloud Content** Open an issue in the GoogleCloudPlatform/generative-ai repository requesting the addition of a `genai-sagemaker` folder. The maintainers can evaluate community demand for beginner-level SageMaker content and potentially expand platform coverage in future releases if sufficient interest exists. ## Summary - **The `genai-sagemaker` directory does not exist** in the GoogleCloudPlatform/generative-ai repository main branch - **No SageMaker-specific tutorials** or beginner onboarding guides are present in any subdirectory or file path - **Existing tutorial collections** in `workshops/` and `open-models/` provide transferable foundational knowledge for generative AI concepts - **AWS-specific beginners** must adapt existing Google Cloud notebooks or seek dedicated SageMaker repositories for platform-specific deployment guidance ## Frequently Asked Questions ### Does the GoogleCloudPlatform/generative-ai repository support AWS SageMaker? No, the repository currently focuses exclusively on Google Cloud Vertex AI, open-source models, and related Google Cloud services. According to the source code file tree and full-text search results, no code examples, deployment scripts, or configuration files for AWS SageMaker exist in the codebase. ### What beginner tutorials are available in the generative-ai repository instead? Beginners should explore the `workshops/` directory, which contains introductory notebooks for retrieval-augmented generation and embeddings, or the `open-models/` directory for foundational model deployment concepts. These materials assume Google Cloud infrastructure but teach transferable generative AI principles applicable to any cloud environment. ### Can I request the addition of SageMaker tutorials to this repository? Yes, you can open a feature request issue in the repository's issue tracker on GitHub. While the maintainers prioritize Google Cloud integrations, community demand for a `genai-sagemaker` directory could influence future roadmap decisions regarding multi-cloud tutorial coverage. ### Are there any hidden or nested SageMaker examples in the repository? No, the search analysis confirms there are no hidden or nested references. The term "sagemaker" returns zero matches across the entire codebase, and the file tree reveals no directories or subdirectories containing AWS-specific deployment examples for beginners.