{"course":{"productid":34329,"modality":1,"active":true,"language":"fr","title":"Developing Generative AI Applications on AWS","productcode":"DGAIA","vendorcode":"AW","vendorname":"Amazon Web Services","fullproductcode":"AW-DGAIA","courseware":{"has_ekit":true,"has_printkit":false,"language":""},"url":"https:\/\/portal.flane.ch\/course\/amazon-dgaia","objective":"<p>In this course, you will learn to:<\/p>\n<ul>\n<li>Describe generative AI and how it aligns to machine learning<\/li><li>Define the importance of generative AI and explain its potential risks and benefits<\/li><li>Identify business value from generative AI use cases<\/li><li>Discuss the technical foundations and key terminology for generative AI<\/li><li>Explain the steps for planning a generative AI project<\/li><li>Identify some of the risks and mitigations when using generative AI<\/li><li>Understand how Amazon Bedrock works<\/li><li>Familiarize yourself with basic concepts of Amazon Bedrock<\/li><li>Recognize the benefits of Amazon Bedrock<\/li><li>List typical use cases for Amazon Bedrock<\/li><li>Describe the typical architecture associated with an Amazon Bedrock solution<\/li><li>Understand the cost structure of Amazon Bedrock<\/li><li>Implement a demonstration of Amazon Bedrock in the AWS Management Console<\/li><li>Define prompt engineering and apply general best practices when interacting with foundation models (FMs)<\/li><li>Identify the basic types of prompt techniques, including zero-shot and few-shot learning<\/li><li>Apply advanced prompt techniques when necessary for your use case<\/li><li>Identify which prompt techniques are best suited for specific models<\/li><li>Identify potential prompt misuses<\/li><li>Analyze potential bias in FM responses and design prompts that mitigate that bias<\/li><li>Identify the components of a generative AI application and how to customize an FM<\/li><li>Describe Amazon Bedrock foundation models, inference parameters, and key Amazon Bedrock APIs<\/li><li>Identify Amazon Web Services (AWS) offerings that help with monitoring, securing, and governing your Amazon Bedrock applications<\/li><li>Describe how to integrate LangChain with LLMs, prompt templates, chains, chat models, text embeddings models, document loaders, retrievers, and Agents for Amazon Bedrock<\/li><li>Describe architecture patterns that you can implement with Amazon Bedrock for building generative AI applications<\/li><li>Apply the concepts to build and test sample use cases that use the various Amazon Bedrock models, LangChain, and the Retrieval Augmented Generation (RAG) approach<\/li><\/ul>","essentials":"<p>We recommend that attendees of this course have:<\/p>\n<ul>\n<li>Completed <span class=\"cms-link-marked\"><a class=\"fl-href-prod\" href=\"\/swisscom\/fr\/course\/amazon-awse\"><svg role=\"img\" aria-hidden=\"true\" focusable=\"false\" data-nosnippet class=\"cms-linkmark\"><use xlink:href=\"\/css\/img\/icnset-linkmarks.svg#linkmark\"><\/use><\/svg>AWS Technical Essentials <span class=\"fl-prod-pcode\">(AWSE)<\/span><\/a><\/span><\/li><li>Intermediate-level proficiency in Python<\/li><\/ul>","audience":"<p>This course is intended for:<\/p>\n<ul>\n<li>Software developers interested in using LLMs without fine-tuning<\/li><\/ul>","contents":"<h5>Module 1: Introduction to Generative AI &ndash; Art of the Possible<\/h5><ul>\n<li>Overview of ML<\/li><li>Basics of generative AI<\/li><li>Generative AI use cases<\/li><li>Generative AI in practice<\/li><li>Risks and benefits<\/li><\/ul><h5>Module 2: Planning a Generative AI Project<\/h5><ul>\n<li>Generative AI fundamentals<\/li><li>Generative AI in practice<\/li><li>Generative AI context<\/li><li>Steps in planning a generative AI project<\/li><li>Risks and mitigation<\/li><\/ul><h5>Module 3: Getting Started with Amazon Bedrock<\/h5><ul>\n<li>Introduction to Amazon Bedrock<\/li><li>Architecture and use cases<\/li><li>How to use Amazon Bedrock<\/li><li>Demonstration: Setting up Bedrock access and using playgrounds<\/li><\/ul><h5>Module 4: Foundations of Prompt Engineering<\/h5><ul>\n<li>Basics of foundation models<\/li><li>Fundamentals of prompt engineering<\/li><li>Basic prompt techniques<\/li><li>Advanced prompt techniques<\/li><li>Model-specific prompt techniques<\/li><li>Demonstration: Fine-tuning a basic text prompt<\/li><li>Addressing prompt misuses<\/li><li>Mitigating bias<\/li><li>Demonstration: Image bias mitigation<\/li><\/ul><h5>Module 5: Amazon Bedrock Application Components<\/h5><ul>\n<li>Overview of generative AI application components<\/li><li>Foundation models and the FM interface<\/li><li>Working with datasets and embeddings<\/li><li>Demonstration: Word embeddings<\/li><li>Additional application components<\/li><li>Retrieval Augmented Generation (RAG)<\/li><li>Model fine-tuning<\/li><li>Securing generative AI applications<\/li><li>Generative AI application architecture<\/li><\/ul><h5>Module 6: Amazon Bedrock Foundation Models<\/h5><ul>\n<li>Introduction to Amazon Bedrock foundation models<\/li><li>Using Amazon Bedrock FMs for inference<\/li><li>Amazon Bedrock methods<\/li><li>Data protection and auditability<\/li><li>Demonstration: Invoke Bedrock model for text generation using zero-shot prompt<\/li><\/ul><h5>Module 7: LangChain<\/h5><ul>\n<li>Optimizing LLM performance<\/li><li>Using models with LangChain<\/li><li>Constructing prompts<\/li><li>Demonstration: Bedrock with LangChain using a prompt that includes context<\/li><li>Structuring documents with indexes<\/li><li>Storing and retrieving data with memory<\/li><li>Using chains to sequence components<\/li><li>Managing external resources with LangChain agents<\/li><\/ul><h5>Module 8: Architecture Patterns<\/h5><ul>\n<li>Introduction to architecture patterns<\/li><li>Text summarization<\/li><li>Demonstration: Text summarization of small files with Anthropic Claude<\/li><li>Demonstration: Abstractive text summarization with Amazon Titan using LangChain<\/li><li>Question answering<\/li><li>Demonstration: Using Amazon Bedrock for question answering<\/li><li>Chatbot<\/li><li>Demonstration: Conversational interface &ndash; Chatbot with AI21 LLM<\/li><li>Code generation<\/li><li>Demonstration: Using Amazon Bedrock models for code generation<\/li><li>LangChain and agents for Amazon Bedrock<\/li><li>Demonstration: Integrating Amazon Bedrock models with LangChain agents<\/li><\/ul>","outline":"<h5>Module 1: Introduction to Generative AI &ndash; Art of the Possible<\/h5><ul>\n<li>Overview of ML<\/li><li>Basics of generative AI<\/li><li>Generative AI use cases<\/li><li>Generative AI in practice<\/li><li>Risks and benefits<\/li><\/ul><h5>Module 2: Planning a Generative AI Project<\/h5><ul>\n<li>Generative AI fundamentals<\/li><li>Generative AI in practice<\/li><li>Generative AI context<\/li><li>Steps in planning a generative AI project<\/li><li>Risks and mitigation<\/li><\/ul><h5>Module 3: Getting Started with Amazon Bedrock<\/h5><ul>\n<li>Introduction to Amazon Bedrock<\/li><li>Architecture and use cases<\/li><li>How to use Amazon Bedrock<\/li><li>Demonstration: Setting up Bedrock access and using playgrounds<\/li><\/ul><h5>Module 4: Foundations of Prompt Engineering<\/h5><ul>\n<li>Basics of foundation models<\/li><li>Fundamentals of prompt engineering<\/li><li>Basic prompt techniques<\/li><li>Advanced prompt techniques<\/li><li>Model-specific prompt techniques<\/li><li>Demonstration: Fine-tuning a basic text prompt<\/li><li>Addressing prompt misuses<\/li><li>Mitigating bias<\/li><li>Demonstration: Image bias mitigation<\/li><\/ul><h5>Module 5: Amazon Bedrock Application Components<\/h5><ul>\n<li>Overview of generative AI application components<\/li><li>Foundation models and the FM interface<\/li><li>Working with datasets and embeddings<\/li><li>Demonstration: Word embeddings<\/li><li>Additional application components<\/li><li>Retrieval Augmented Generation (RAG)<\/li><li>Model fine-tuning<\/li><li>Securing generative AI applications<\/li><li>Generative AI application architecture<\/li><\/ul><h5>Module 6: Amazon Bedrock Foundation Models<\/h5><ul>\n<li>Introduction to Amazon Bedrock foundation models<\/li><li>Using Amazon Bedrock FMs for inference<\/li><li>Amazon Bedrock methods<\/li><li>Data protection and auditability<\/li><li>Demonstration: Invoke Bedrock model for text generation using zero-shot prompt<\/li><\/ul><h5>Module 7: LangChain<\/h5><ul>\n<li>Optimizing LLM performance<\/li><li>Using models with LangChain<\/li><li>Constructing prompts<\/li><li>Demonstration: Bedrock with LangChain using a prompt that includes context<\/li><li>Structuring documents with indexes<\/li><li>Storing and retrieving data with memory<\/li><li>Using chains to sequence components<\/li><li>Managing external resources with LangChain agents<\/li><\/ul><h5>Module 8: Architecture Patterns<\/h5><ul>\n<li>Introduction to architecture patterns<\/li><li>Text summarization<\/li><li>Demonstration: Text summarization of small files with Anthropic Claude<\/li><li>Demonstration: Abstractive text summarization with Amazon Titan using LangChain<\/li><li>Question answering<\/li><li>Demonstration: Using Amazon Bedrock for question answering<\/li><li>Chatbot<\/li><li>Demonstration: Conversational interface &ndash; Chatbot with AI21 LLM<\/li><li>Code generation<\/li><li>Demonstration: Using Amazon Bedrock models for code generation<\/li><li>LangChain and agents for Amazon Bedrock<\/li><li>Demonstration: Integrating Amazon Bedrock models with LangChain agents<\/li><\/ul>","summary":"<p>This course is designed to introduce generative artificial intelligence (AI) to software developers interested in using large language models (LLMs) without fine-tuning. The course provides an overview of generative AI, planning a generative AI project, getting started with Amazon Bedrock, the foundations of prompt engineering, and the architecture patterns to build generative AI applications using Amazon Bedrock and LangChain.<\/p>","objective_plain":"In this course, you will learn to:\n\n\n- Describe generative AI and how it aligns to machine learning\n- Define the importance of generative AI and explain its potential risks and benefits\n- Identify business value from generative AI use cases\n- Discuss the technical foundations and key terminology for generative AI\n- Explain the steps for planning a generative AI project\n- Identify some of the risks and mitigations when using generative AI\n- Understand how Amazon Bedrock works\n- Familiarize yourself with basic concepts of Amazon Bedrock\n- Recognize the benefits of Amazon Bedrock\n- List typical use cases for Amazon Bedrock\n- Describe the typical architecture associated with an Amazon Bedrock solution\n- Understand the cost structure of Amazon Bedrock\n- Implement a demonstration of Amazon Bedrock in the AWS Management Console\n- Define prompt engineering and apply general best practices when interacting with foundation models (FMs)\n- Identify the basic types of prompt techniques, including zero-shot and few-shot learning\n- Apply advanced prompt techniques when necessary for your use case\n- Identify which prompt techniques are best suited for specific models\n- Identify potential prompt misuses\n- Analyze potential bias in FM responses and design prompts that mitigate that bias\n- Identify the components of a generative AI application and how to customize an FM\n- Describe Amazon Bedrock foundation models, inference parameters, and key Amazon Bedrock APIs\n- Identify Amazon Web Services (AWS) offerings that help with monitoring, securing, and governing your Amazon Bedrock applications\n- Describe how to integrate LangChain with LLMs, prompt templates, chains, chat models, text embeddings models, document loaders, retrievers, and Agents for Amazon Bedrock\n- Describe architecture patterns that you can implement with Amazon Bedrock for building generative AI applications\n- Apply the concepts to build and test sample use cases that use the various Amazon Bedrock models, LangChain, and the Retrieval Augmented Generation (RAG) approach","essentials_plain":"We recommend that attendees of this course have:\n\n\n- Completed AWS Technical Essentials (AWSE)\n- Intermediate-level proficiency in Python","audience_plain":"This course is intended for:\n\n\n- Software developers interested in using LLMs without fine-tuning","contents_plain":"Module 1: Introduction to Generative AI \u2013 Art of the Possible\n\n\n- Overview of ML\n- Basics of generative AI\n- Generative AI use cases\n- Generative AI in practice\n- Risks and benefits\nModule 2: Planning a Generative AI Project\n\n\n- Generative AI fundamentals\n- Generative AI in practice\n- Generative AI context\n- Steps in planning a generative AI project\n- Risks and mitigation\nModule 3: Getting Started with Amazon Bedrock\n\n\n- Introduction to Amazon Bedrock\n- Architecture and use cases\n- How to use Amazon Bedrock\n- Demonstration: Setting up Bedrock access and using playgrounds\nModule 4: Foundations of Prompt Engineering\n\n\n- Basics of foundation models\n- Fundamentals of prompt engineering\n- Basic prompt techniques\n- Advanced prompt techniques\n- Model-specific prompt techniques\n- Demonstration: Fine-tuning a basic text prompt\n- Addressing prompt misuses\n- Mitigating bias\n- Demonstration: Image bias mitigation\nModule 5: Amazon Bedrock Application Components\n\n\n- Overview of generative AI application components\n- Foundation models and the FM interface\n- Working with datasets and embeddings\n- Demonstration: Word embeddings\n- Additional application components\n- Retrieval Augmented Generation (RAG)\n- Model fine-tuning\n- Securing generative AI applications\n- Generative AI application architecture\nModule 6: Amazon Bedrock Foundation Models\n\n\n- Introduction to Amazon Bedrock foundation models\n- Using Amazon Bedrock FMs for inference\n- Amazon Bedrock methods\n- Data protection and auditability\n- Demonstration: Invoke Bedrock model for text generation using zero-shot prompt\nModule 7: LangChain\n\n\n- Optimizing LLM performance\n- Using models with LangChain\n- Constructing prompts\n- Demonstration: Bedrock with LangChain using a prompt that includes context\n- Structuring documents with indexes\n- Storing and retrieving data with memory\n- Using chains to sequence components\n- Managing external resources with LangChain agents\nModule 8: Architecture Patterns\n\n\n- Introduction to architecture patterns\n- Text summarization\n- Demonstration: Text summarization of small files with Anthropic Claude\n- Demonstration: Abstractive text summarization with Amazon Titan using LangChain\n- Question answering\n- Demonstration: Using Amazon Bedrock for question answering\n- Chatbot\n- Demonstration: Conversational interface \u2013 Chatbot with AI21 LLM\n- Code generation\n- Demonstration: Using Amazon Bedrock models for code generation\n- LangChain and agents for Amazon Bedrock\n- Demonstration: Integrating Amazon Bedrock models with LangChain agents","outline_plain":"Module 1: Introduction to Generative AI \u2013 Art of the Possible\n\n\n- Overview of ML\n- Basics of generative AI\n- Generative AI use cases\n- Generative AI in practice\n- Risks and benefits\nModule 2: Planning a Generative AI Project\n\n\n- Generative AI fundamentals\n- Generative AI in practice\n- Generative AI context\n- Steps in planning a generative AI project\n- Risks and mitigation\nModule 3: Getting Started with Amazon Bedrock\n\n\n- Introduction to Amazon Bedrock\n- Architecture and use cases\n- How to use Amazon Bedrock\n- Demonstration: Setting up Bedrock access and using playgrounds\nModule 4: Foundations of Prompt Engineering\n\n\n- Basics of foundation models\n- Fundamentals of prompt engineering\n- Basic prompt techniques\n- Advanced prompt techniques\n- Model-specific prompt techniques\n- Demonstration: Fine-tuning a basic text prompt\n- Addressing prompt misuses\n- Mitigating bias\n- Demonstration: Image bias mitigation\nModule 5: Amazon Bedrock Application Components\n\n\n- Overview of generative AI application components\n- Foundation models and the FM interface\n- Working with datasets and embeddings\n- Demonstration: Word embeddings\n- Additional application components\n- Retrieval Augmented Generation (RAG)\n- Model fine-tuning\n- Securing generative AI applications\n- Generative AI application architecture\nModule 6: Amazon Bedrock Foundation Models\n\n\n- Introduction to Amazon Bedrock foundation models\n- Using Amazon Bedrock FMs for inference\n- Amazon Bedrock methods\n- Data protection and auditability\n- Demonstration: Invoke Bedrock model for text generation using zero-shot prompt\nModule 7: LangChain\n\n\n- Optimizing LLM performance\n- Using models with LangChain\n- Constructing prompts\n- Demonstration: Bedrock with LangChain using a prompt that includes context\n- Structuring documents with indexes\n- Storing and retrieving data with memory\n- Using chains to sequence components\n- Managing external resources with LangChain agents\nModule 8: Architecture Patterns\n\n\n- Introduction to architecture patterns\n- Text summarization\n- Demonstration: Text summarization of small files with Anthropic Claude\n- Demonstration: Abstractive text summarization with Amazon Titan using LangChain\n- Question answering\n- Demonstration: Using Amazon Bedrock for question answering\n- Chatbot\n- Demonstration: Conversational interface \u2013 Chatbot with AI21 LLM\n- Code generation\n- Demonstration: Using Amazon Bedrock models for code generation\n- LangChain and agents for Amazon Bedrock\n- Demonstration: Integrating Amazon Bedrock models with LangChain agents","summary_plain":"This course is designed to introduce generative artificial intelligence (AI) to software developers interested in using large language models (LLMs) without fine-tuning. The course provides an overview of generative AI, planning a generative AI project, getting started with Amazon Bedrock, the foundations of prompt engineering, and the architecture patterns to build generative AI applications using Amazon Bedrock and LangChain.","skill_level":"Intermediate","version":"2.0","duration":{"unit":"d","value":2,"formatted":"2 jours"},"pricelist":{"List Price":{"DE":{"country":"DE","currency":"EUR","taxrate":19,"price":1250},"SI":{"country":"SI","currency":"EUR","taxrate":20,"price":1250},"AT":{"country":"AT","currency":"EUR","taxrate":20,"price":1250},"SE":{"country":"SE","currency":"EUR","taxrate":25,"price":1250},"IT":{"country":"IT","currency":"EUR","taxrate":20,"price":980},"PL":{"country":"PL","currency":"PLN","taxrate":23,"price":4000},"FR":{"country":"FR","currency":"EUR","taxrate":19.6,"price":1565},"GB":{"country":"GB","currency":"GBP","taxrate":20,"price":2035},"CH":{"country":"CH","currency":"CHF","taxrate":8.1,"price":1770},"US":{"country":"US","currency":"USD","taxrate":null,"price":1390},"CA":{"country":"CA","currency":"CAD","taxrate":null,"price":1920},"AE":{"country":"AE","currency":"USD","taxrate":5,"price":1325},"NL":{"country":"NL","currency":"EUR","taxrate":21,"price":1595}}},"lastchanged":"2026-03-16T13:57:37+01:00","parenturl":"https:\/\/portal.flane.ch\/swisscom\/fr\/json-courses","nexturl_course_schedule":"https:\/\/portal.flane.ch\/swisscom\/fr\/json-course-schedule\/34329","source_lang":"fr","source":"https:\/\/portal.flane.ch\/swisscom\/fr\/json-course\/amazon-dgaia"}}