Building AI Intensive Python Applications

Building AI Intensive Python Applications

Instructor: Packt - Course Instructors

Access provided by Chula Engineering

12 modules

Gain insight into a topic and learn the fundamentals.

Intermediate level

Recommended experience

3 weeks to complete

at 10 hours a week

Flexible schedule

Learn at your own pace

12 modules

Gain insight into a topic and learn the fundamentals.

Intermediate level

Recommended experience

3 weeks to complete

at 10 hours a week

Flexible schedule

Learn at your own pace

What you'll learn

Understand the architecture of the generative AI stack
Explore the role of vector databases in AI applications
Implement Python frameworks for AI development

Skills you'll gain

Tools you'll learn

Details to know

Shareable certificate

Add to your LinkedIn profile

Assessments

12 assignments

Taught in English

See how employees at top companies are mastering in-demand skills

Learn more about Coursera for Business

logos of Petrobras, TATA, Danone, Capgemini, P&G and L'Oreal

There are 12 modules in this course

This course equips learners with the knowledge and skills to build intelligent applications using generative AI. It dives deep into the AI stack, covering large language models (LLMs), vector databases, and Python frameworks. Learners will also explore strategies to enhance AI performance and reliability, critical in today’s rapidly evolving AI landscape.

You will gain hands-on experience by building AI-powered applications, learning how to implement vector databases for data retrieval and enhance models with Python. With a practical, step-by-step approach, you will develop the expertise to create intelligent apps that can adapt to real-world challenges. What sets this course apart is its focus on both theoretical concepts and real-world application. You’ll work on practical use cases, from AI architecture to the integration of LLMs, vector databases, and Python frameworks, giving you the confidence to implement AI solutions in various industries. This course is perfect for software engineers and developers with a basic understanding of Python who want to build intelligent applications using generative AI. It’s designed to provide both foundational knowledge and practical skills to boost AI performance and reliability.

In this section, we explore generative AI fundamentals, including its stack components, Python integration, and ethical considerations, to guide practical web development applications.

What's included

2 videos2 readings1 assignment

In this section, we explore the building blocks of intelligent applications, including LLMs, vector embeddings, and model hosting, to enable context-aware, adaptive software solutions.

What's included

1 video3 readings1 assignment

In this section, we explore n-gram models, artificial neural networks, and Transformer architecture to understand large language models' implementation and applications in natural language processing.

What's included

1 video7 readings1 assignment

1 video Total 1 minute

Large Language Models - Overview Video 1 minute

7 readings Total 125 minutes

Introduction 30 minutes
Machine Learning for Language Modelling 20 minutes
Training an Artificial Neural Network 5 minutes
ANNs for Natural Language Processing 5 minutes
Embedding 30 minutes
Dealing with Sequential Data 30 minutes
The Evolving Field of LLMs 5 minutes

1 assignment Total 10 minutes

Foundations of Transformer Models and NLP 10 minutes

In this section, we explore embedding models, their applications in NLP and data processing, and how to implement them using Python for semantic search and vector analysis.

What's included

1 video4 readings1 assignment

In this section, we cover vector databases, embeddings, and their role in AI search and retrieval systems.

What's included

1 video9 readings1 assignment

1 video Total 1 minute

Vector Databases - Overview Video 1 minute

9 readings Total 160 minutes

Introduction 20 minutes
Exact Versus Approximate Search 5 minutes
Graph Connectivity 5 minutes
How to Search a Navigable Small World 10 minutes
The Need for Vector Databases 10 minutes
Case Studies and Real-World Applications 30 minutes
Data Modeling 20 minutes
Experimentation 30 minutes
Incorporating User Feedback 30 minutes

1 assignment Total 10 minutes

Exploring Vector Database Concepts 10 minutes

In this section, we explore data modeling, storage, and secure data flow for AI/ML applications, emphasizing practical implementation and RBAC principles for efficient and secure system design.

What's included

1 video4 readings1 assignment

In this section, we explore Python-based AI/ML frameworks, libraries, and APIs for building generative AI applications, focusing on real-world data integration and retrieval-augmented generation solutions.

What's included

1 video5 readings1 assignment

In this section, we explore integrating vector search with RAG systems, focusing on efficient data retrieval and enhancing AI application intelligence through practical techniques.

What's included

1 video5 readings1 assignment

1 video Total 1 minute

Implementing Vector Search in AI Applications - Overview Video 1 minute

5 readings Total 120 minutes

Introduction 30 minutes
Building RAG Architecture Systems 10 minutes
Chunking or Document-Splitting Strategies 20 minutes
Prompt 30 minutes
Fashion Recommendations Using Advanced RAG 30 minutes

1 assignment Total 10 minutes

Vector Search and RAG System Fundamentals 10 minutes

In this section, we explore LLM evaluation strategies, focusing on metrics, guardrails, and reliability in intelligent applications to ensure effective and safe AI deployment.

What's included

1 video9 readings1 assignment

1 video Total 1 minute

LLM Output Evaluation - Overview Video 1 minute

9 readings Total 170 minutes

Introduction 30 minutes
Model Benchmarking 10 minutes
Evaluation Datasets 20 minutes
Synthetic Data 20 minutes
Statistical Metrics 20 minutes
LLM as a Judge Evaluations 20 minutes
RAG Metrics 20 minutes
Answer Relevance 20 minutes
Human Review 10 minutes

1 assignment Total 10 minutes

Evaluating AI System Performance 10 minutes

In this section, we explore techniques to refine semantic data models for improved accuracy in retrieval-augmented generation (RAG) applications. Key concepts include embedding model experimentation, metadata optimization, and advanced retrieval systems.

What's included

1 video5 readings1 assignment

1 video Total 1 minute

Refining the Semantic Data Model to Improve Accuracy - Overview Video 1 minute

5 readings Total 140 minutes

Introduction 30 minutes
Fine-tuning Embedding Models 20 minutes
Embedding Metadata 30 minutes
Including Static Metadata 30 minutes
Optimizing Retrieval-Augmented Generation 30 minutes

1 assignment Total 10 minutes

Refining Semantic Data Models for Better Accuracy 10 minutes

In this section, we examine common GenAI failure modes, including hallucinations, sycophancy, data leakage, and performance issues, to improve accuracy and reliability in practical applications.

What's included

1 video6 readings1 assignment

In this section, we explore techniques to improve GenAI application reliability, including baselining, dataset design, and feedback loops for optimized performance and stable outputs.