Generative AI with Python – Build AI-Powered Applications 12 Sections70 Lessons4 Days
Curriculum
- 12 Sections
- 70 Lessons
- 4 Days
Expand all sectionsCollapse all sections
- Module 1: Introduction to Generative AI6 ItemsUnderstand Generative AI, common applications, large language models and the differences between traditional programming and generative systems.
- 1.1What Is Artificial Intelligence and Generative AI?
- 1.2Generative AI vs Traditional AI and Machine Learning
- 1.3Understanding Large Language Models (LLMs)
- 1.4How Generative AI Models Generate Text and Content
- 1.5Understanding Tokens, Context Windows and Model Limitations
- 1.6Real-World Applications of Generative AI
- Module 2: Python Frameworks for Generative AI7 ItemsReview the Python concepts and frameworks required for AI development.
- Module 3: Vector DB and Embeddings Fundamentals4 ItemsUnderstand Gen-AI pipeline, data pre-processing, data representation and vectorization.
- Module 4: Prompt Engineering5 ItemsExplore prompt structure, instructions, context, output formats and techniques for improving the usefulness of model responses.
- Module5: Mastering Vector Databases5 ItemsUnderstand how text embeddings represent information and how vector search can help retrieve content that is relevant to a user's question.
- Module 6: Integrating Generative AI APIs with Python8 ItemsLearn how applications send requests to AI services, handle responses, manage errors and incorporate model outputs into application workflows.
- 6.1Introduction to Generative AI APIs
- 6.2API Keys, Authentication and Secure Configuration
- 6.3Sending Requests to a Language Model Using Python
- 6.4Understanding API Parameters and Model Settings
- 6.5Processing and Displaying Model Responses
- 6.6Handling Errors, Timeouts and Rate Limits
- 6.7Managing Token Usage and API Costs
- 6.81. Building a Python Application Using a Generative AI API
- Module 7: Building AI Chatbots and Assistants8 ItemsExplore conversational application design, managing conversation context and developing assistants for defined tasks.
- 7.1Understanding Chatbots, AI Assistants and Conversational AI
- 7.2Designing a Chatbot Workflow and Conversation Structure
- 7.3Connecting a Chatbot to an LLM Using Python
- 7.4Managing Conversation History and Context
- 7.5Designing System Instructions and Assistant Behavior
- 7.6Handling Follow-Up Questions and Contextual Conversations
- 7.7Connecting Chatbots to Documents and Knowledge Sources
- 7.8Practical Project: Build a Python-Powered AI Assistant
- Module 8: Retrieval-Augmented Generation (RAG)10 ItemsExplore how to retrieve information from a selected knowledge source and supply it to an LLM to support context-aware responses and document question-answering applications.
- 8.1Introduction to Retrieval-Augmented Generation
- 8.2Understanding the RAG Architecture and Workflow
- 8.3Preparing and Cleaning Documents for Retrieval
- 8.4Splitting Documents into Chunks
- 8.5Generating Embeddings for Document Content
- 8.6Storing Document Embeddings in a Vector Database
- 8.7Retrieving Relevant Information for User Queries
- 8.8Generating Answers Grounded in Retrieved Sources
- 8.9Handling Missing Information and Hallucination
- 8.10Practical Project: Build a Document Question-Answering Assistant
- Module 9: Testing, Evaluation and Responsible AI6 ItemsExplore methods for checking AI outputs, handling errors, protecting sensitive information and improving the reliability of AI-powered applications.
- 9.1Common Errors and Limitations of Generative AI
- 9.2Understanding Hallucinations and Unsupported Responses
- 9.3Evaluating Answer Relevance, Accuracy and Consistency
- 9.4Testing Prompts and Comparing Model Outputs
- 9.5Monitoring Performance, Latency and Token Costs
- 9.6Responsible AI: Fairness, Transparency and Human Oversight
- Module 10: Mastering OpenAI with Python2 ItemsCreate chatbots, audio transcripts and images using OpenAI GPT models.
- Module 11: Mastering Open Source LLM with Hugging Face8 ItemsUse open-source LLM on Google Colab for building Gen-AI applications.
- 11.1Introduction to Hugging Face and the Open-Source AI Ecosystem
- 11.2Exploring the Hugging Face Model Hub
- 11.3Understanding Model Cards, Licences and Hardware Requirements
- 11.4Setting Up Python and the Transformers Library
- 11.5Loading Pretrained Models and Tokenizers
- 11.6Generating Text with Open-Source Language Models
- 11.7Running Models Locally vs Using Hosted Inference
- 11.8Practical Project: Build an AI Application Using an Open-Source LLM
- Module 12: Final Project1 ItemComplete medical chatbot using LLM, Pinecoce VectorDB, RAG, Flask
Practical Project: Build an AI Application Using an Open-Source LLM
Prev