The illustrations were created in cooperation between humans and artificial intelligence. They show a future in which technology is omnipresent, but people remain at the center.
AI-generated illustration
€ 1.290,-
plus VAT.
€ 1.535,10
incl. VAT.
Booking number
36647
Venue
Online
.svg)
€ 1.290,-
plus VAT.
€ 1.535,10
incl. VAT.
Booking number
36647
Venue
Online
plus VAT.
incl. VAT.
Booking number
Venue
Become a certified
Machine Learning Engineer
Machine Learning Engineer
This course is part of the certified Master Class "Machine Learning Engineer". If you book the entire Master Class, you save over 15 percent compared to booking this individual module.
To the Master Class
In-house training
In-house training just for your employees - exclusive and effective.
Inquiries
In cooperation with
This course is intended to provide an introduction to generative artificial intelligence (AI) for software developers interested in using large language models (LLMs) without fine-tuning.
Contents
The course provides an overview of generative AI, planning a generative AI project, getting started with Amazon Bedrock, the basics of prompt engineering and the architectural patterns for creating generative AI applications with Amazon Bedrock and LangChain.
Day 1
Module 1: Introduction to Generative AI - The Art of the Possible
- Overview of ML
- Basics of generative AI
- Use cases of generative AI
- Generative AI in practice
- Risks and benefits
Module 2: Planning a generative AI project
- Generative AI basics
- Generative AI in practice
- Generative AI in context
- Steps in the planning of a generative AI project
- Risks and damage limitation
Module 3: First steps with Amazon Bedrock
- Introduction to Amazon Bedrock
- Architecture and use cases
- How to use Amazon Bedrock
- Demonstration: Setting up Bedrock access and using Playgrounds
Module 4: Basics of Prompt Engineering
- Basics of foundation models
- Basics of prompt engineering
- Basic probing techniques
- Advanced prompt techniques
- Model-specific prompt techniques
- Demonstration: Fine-tuning a simple text prompt
- Treatment of prompt abuse
- Attenuation of distortions
- Demonstration: Reducing image distortion
Day 2
Module 5: Amazon Bedrock application components
- Overview of the generative AI application components
- Basic models and the FM interface
- Working with data records and embeddings
- Demonstration: Word embeddings
- Additional application components
- Call-off extended generation (RAG)
- Model fine-tuning
- Safeguarding generative AI applications
- Generative AI application architecture
Module 6: Amazon Bedrock basic models
- Introduction to Amazon Bedrock Foundation models
- Use of Amazon Bedrock FMs for inference
- Amazon Bedrock methods
- data privacy and auditability
- Demonstration: Calling the Bedrock model for text generation with zero-shot prompt
Module 7: LangChain
- Optimizing LLM performance
- Use of models with LangChain
- Construct prompts
- Demonstration: Bedrock with LangChain using a prompt that contains context
- Structuring documents with indices
- Saving and retrieving data with memory
- Use of chains for the sequence of components
- Manage external resources with LangChain agents
Module 8: Architectural patterns
- Introduction to architectural patterns
- Text summary
- Demonstration: Text summarization of small files with Anthropic Claude
- Demonstration: Abstract text summary with Amazon Titan using LangChain
- Answering questions
- Demonstration: Using Amazon Bedrock to answer questions
- Chatbot
- Demonstration: Conversational interface - chatbot with AI21 LLM
- Code generation
- Demonstration: Using Amazon Bedrock models for code generation
- LangChain and agents for Amazon Bedrock
- Demonstration: Integration of Amazon Bedrock models with LangChain agents
Learning environment
Your benefit
- Describe generative AI and how it differs from machine learning
- Define the importance of generative AI and explain its potential risks and benefits
- Identifying the business value of generative AI use cases
- Discuss the technical foundations and key terminology for generative AI
- Explain the steps for planning a generative AI project
- Identify some risks and mitigation measures when using generative AI
- Understanding how Amazon Bedrock works
- Familiarization with the basic concepts of Amazon Bedrock
- Recognizing the benefits of Amazon Bedrock
- List of typical use cases for Amazon Bedrock
- Describe the typical architecture associated with an Amazon Bedrock solution
- Understanding the cost structure of Amazon Bedrock
- Implement a demonstration of Amazon Bedrock in the AWS Management Console
- Define prompt engineering and apply general best practices when interacting with Foundation Models (FMs)
- Identify the basic types of prompting techniques, including zero-shot and little-shot learning
- Apply advanced prompting techniques if required for your use case
- Recognize which prompting techniques are best suited for certain models
- Identifying potential prompt abuse
- Analyze potential biases in FM responses and develop prompts that mitigate these biases
- Identify the components of a generative AI application and how to customize an FM
- Describe the Amazon Bedrock Foundation models, inference parameters and the most important Amazon Bedrock APIs
- Identify Amazon Web Services (AWS) offerings that help monitor, secure and manage your Amazon Bedrock applications
- Describe the integration of LangChain with LLMs, prompt templates, chains, chat models, text embedding models, document loaders, retrievers and agents for Amazon Bedrock
- Describe architectural patterns that you can implement with Amazon Bedrock to build generative AI applications.
- Apply the concepts of creating and testing use cases that utilize the various Amazon Bedrock models, LangChain, and the Retrieval Augmented Generation (RAG) approach
trainers
Milo Fels
Methods
This course consists of training training and is led by a trainer who supervises the participants live. Theory and practice are taught with live demonstrations and practical exercises. The video conferencing software Zoom is used.
Final examination
Recommended for
developers developers who want to use LLMs without fine-tuning.
.svg)
