English | MP4 | AVC 1920×1080 | AAC 44KHz 2ch | 284 lectures (17h 47m) | 9.48 GB
Complete AI Engineer Training: Python, NLP, Transformers, LLMs, LangChain, Hugging Face, APIs
The Problem
AI Engineers are best suited to thrive in the age of AI. It helps businesses utilize Generative AI by building AI-driven applications on top of their existing websites, apps, and databases. Therefore, it’s no surprise that the demand for AI Engineers has been surging in the job marketplace.
Supply, however, has been minimal, and acquiring the skills necessary to be hired as an AI Engineer can be challenging.
So, how is this achievable?
Universities have been slow to create specialized programs focused on practical AI Engineering skills. The few attempts that exist tend to be costly and time-consuming.
Most online courses offer ChatGPT hacks and isolated technical skills, yet integrating these skills remains challenging.
The Solution
AI Engineering is a multidisciplinary field covering:
- AI principles and practical applications
- Python programming
- Natural Language Processing in Python
- Large Language Models and Transformers
- Developing apps with orchestration tools like LangChain
- Vector databases using PineCone
- Creating AI-driven applications
Each topic builds on the previous one, and skipping steps can lead to confusion. For instance, applying large language models requires familiarity with Langchain—just as studying natural language processing can be overwhelming without basic Python coding skills.
So, we created the AI Engineer Bootcamp 2024 to provide the most effective, time-efficient, and structured AI engineering training available online.
This pioneering training program overcomes the most significant barrier to entering the AI Engineering field by consolidating all essential resources in one place.
Our course is designed to teach interconnected topics seamlessly—providing all you need to become an AI Engineer at a significantly lower cost and time investment than traditional programs.
The Skills
1. Intro to Artificial Intelligence
Structured and unstructured data, supervised and unsupervised machine learning, Generative AI, and foundational models—these familiar AI buzzwords; what exactly do they mean?
Why study AI? Gain deep insights into the field through a guided exploration that covers AI fundamentals, the significance of quality data, essential techniques, Generative AI, and the development of advanced models like GPT, Llama, Gemini, and Claude.
2. Python Programming
Mastering Python programming is essential to becoming a skilled AI developer—no-code tools are insufficient.
Python is a modern, general-purpose programming language suited for creating web applications, computer games, and data science tasks. Its extensive library ecosystem makes it ideal for developing AI models.
Why study Python programming?
Python programming will become your essential tool for communicating with AI models and integrating their capabilities into your products.
3. Intro to NLP in Python
Explore Natural Language Processing (NLP) and learn techniques that empower computers to comprehend, generate, and categorize human language.
Why study NLP?
NLP forms the basis of cutting-edge Generative AI models. This program equips you with essential skills to develop AI systems that meaningfully interact with human language.
4. Introduction to Large Language Models
This program section enhances your natural language processing skills by teaching you to utilize the powerful capabilities of Large Language Models (LLMs). Learn critical tools like Transformers Architecture, GPT, Langchain, HuggingFace, BERT, and XLNet.
Why study LLMs?
This module is your gateway to understanding how large language models work and how they can be applied to solve complex language-related tasks that require deep contextual understanding.
5. Building Applications with LangChain
LangChain is a framework that allows for seamless development of AI-driven applications by chaining interoperable components.
Why study LangChain?
Learn how to create applications that can reason. LangChain facilitates the creation of systems where individual pieces—such as language models, databases, and reasoning algorithms—can be interconnected to enhance overall functionality.
6. Vector Databases
With emerging AI technologies, the importance of vectorization and vector databases is set to increase significantly. In this Vector Databases with Pinecone module, you’ll have the opportunity to explore the Pinecone database—a leading vector database solution.
Why study vector databases?
Learning about vector databases is crucial because it equips you to efficiently manage and query large volumes of high-dimensional data—typical in machine learning and AI applications. These technical skills allow you to deploy performance-optimized AI-driven applications.
What you’ll learn
- The course provides the entire toolbox you need to become an AI Engineer
- Understand key Artificial Intelligence concepts and build a solid foundation
- Start coding in Python and learn how to use it for NLP and AI
- Impress interviewers by showing an understanding of the AI field
- Apply your skills to real-life business cases
- Harness the power of Large Language Models
- Leverage LangChain for seamless development of AI-driven applications by chaining interoperable components
- Become familiar with Hugging Face and the AI tools it offers
- Use APIs and connect to powerful foundation models
Table of Contents
Intro to AI Module Getting started
1 What does the course cover
2 Natural vs Artificial Intelligence
3 Brief history of AI
4 Demystifying AI Data science Machine learning and Deep learning
5 Weak vs Strong AI
Intro to AI Module Data is essential for building AI
6 Structured vs unstructured data
7 How we collect data
8 Labelled and unlabelled data
9 Metadata Data that describes data
Intro to AI Module Key AI techniques
10 Machine learning
11 Supervised Unsupervised and Reinforcement learning
12 Deep learning
Intro to AI Module Important AI branches
13 Robotics
14 Computer vision
15 Traditional ML
16 Generative AI
Intro to AI Module Understanding Generative AI
17 The rise of Gen AI Introducing ChatGPT
18 Early approaches to Natural Language Processing NLP
19 Recent NLP advancements
20 From Language Models to Large Language Models LLMs
21 The efficiency of LLM training Supervised vs Semisupervised learning
22 From NGrams to RNNs to Transformers The Evolution of NLP
23 Phases in building LLMs
24 Prompt engineering vs Finetuning vs RAG Techniques for AI optimization
25 The importance of foundation models
26 Buy vs Make foundation models vs private models
Intro to AI Module Practical challenges in Generative AI
27 Inconsistency and hallucination
28 Budgeting and API costs
29 Latency
30 Running out of data
Intro to AI Module The AI tech stack
31 Python programming
32 Working with APIs
33 Vector databases
34 The importance of open source
35 Hugging Face
36 LangChain
37 AI evaluation tools
AI job positions
38 AI strategist
39 AI developer
40 AI engineer
Looking ahead
41 AI ethics
42 Future of AI
Python Module Why Python
43 Programming Explained in a Few Minutes
44 Why Python
Python Module Setting Up the Environment
45 Jupyter Introduction
46 Jupyter Installing Anaconda
47 Jupyter Introduction to Using Jupyter
48 Jupyter Working with Notebook Files
49 Jupyter Using Shortcuts
50 Jupyter Handling Error Messages
51 Jupyter Restarting the Kernel
Python Module Python Variables and Data Types
52 Python Variables
53 Types of Data Numbers and Boolean Values
54 Types of Data Strings
Python Module Basic Python Syntax
55 Basic Python Syntax Arithmetic Operators
56 Basic Python Syntax The Double Equality Sign
57 Basic Python Syntax Reassign Values
58 Basic Python Syntax Add Comments
59 Basic Python Syntax Line Continuation
60 Basic Python Syntax Indexing Elements
61 Basic Python Syntax Indentation
Python Module More on Operators
62 Operators Comparison Operators
63 Operators Logical and Identity Operators
Python Module Conditional Statements
64 Conditional Statements The IF Statement
65 Conditional Statements The ELSE Statement
66 Conditional Statements The ELIF Statement
67 Conditional Statements A Note on Boolean Values
Python Module Functions
68 Functions Defining a Function in Python
69 Functions Creating a Function with a Parameter
70 Functions Another Way to Define a Function
71 Functions Using a Function in Another Function
72 Functions Combining Conditional Statements and Functions
73 Functions Creating Functions Containing a Few Arguments
74 Functions Notable Builtin Functions in Python
Python Module Sequences
75 Sequences Lists
76 Sequences Using Methods
77 Sequences List Slicing
78 Sequences Tuples
79 Sequences Dictionaries
Python Module Iteration
80 Iteration For Loops
81 Iteration While Loops and Incrementing
82 Iteration Creatie Lists with the range Function
83 Iteraion Use Conditional Statements and Loops Together
84 Iteration Conditional Statements Functions and Loops
85 Iteration Iterating over Dictionaries
Python Module A Few Important Python Concepts and Terms
86 Introduction to Object Oriented Programming OOP
87 Modules Packages and the Python Standard Library
88 Importing Modules
89 What is Software Documentation
90 The Python Documentation
NLP Module Introduction
91 Introduction to the course
92 Course materials and notebooks
93 Introduction to NLP
94 NLP in everyday life
95 Supervised vs unsupervised NLP
NLP Module Text Preprocessing
96 The importance of data preparation
97 Lowercase
98 Removing stop words
99 Regular expressions
100 Tokenization
101 Stemming
102 Lemmatization
103 Ngrams
104 Practical task
NLP Module Identifying Parts of Speech and Named Entities
105 Text tagging
106 Parts of Speech POS tagging
107 Named Entity Recognition NER
108 Practical task
NLP Module Sentiment Analysis
109 What is sentiment analysis
110 Rulebased sentiment analysis
111 Pretrained transformer models
112 Practical task
NLP Module Vectorizing Text
113 Numerical representation of text
114 Bag of Words model
115 TFIDF
NLP Module Topic Modelling
116 What is topic modelling
117 When to use topic modelling
118 Latent Dirichlet Allocation LDA
119 LDA in Python
120 Latent Semantic Analysis LSA
121 LSA in Python
122 How many topics
NLP Module Building Your Own Text Classifier
123 Building a custom text classifier
124 Logistic regression
125 Naive Bayes
126 Linear support vector machine
NLP Module Categorizing Fake News Case Study
127 Introducing the project
128 Exploring our data through POS tags
129 Extracting named entities
130 Processing the text
131 Does sentiment differ between news types
132 What topics appear in fake news Part 1
133 What topics appear in fake news Part 2
134 Categorizing fake news with a custom classifier
NLP Module The Future of NLP
135 What is deep learning
136 Deep learning for NLP
137 NonEnglish NLP
138 Whats next for NLP
LLMs Module Introduction to Large Language Models
139 Introduction to the course
140 Course materials and notebooks
141 What are LLMs
142 How large is an LLM
143 General purpose models
144 Pretraining and fine tuning
145 What can LLMs be used for
LLMs Module The Transformer Architecture
146 Deep learning recap
147 The problem with RNNs
148 The solution attention is all you need
149 The transformer architecture
150 Input embeddings
151 Multiheaded attention
152 Feedforward layer
153 Masked multihead attention
154 Predicting the final outputs
LLMs Module Getting Started With GPT Models
155 What does GPT mean
156 The development of ChatGPT
157 OpenAI API
158 Generating text
159 Customizing GPT output
160 Key word text summarization
161 Coding a simple chatbot
162 Introduction to LangChain in Python
163 LangChain
164 Adding custom data to our chatbot
LLMs Module Hugging Face Transformers
165 Hugging Face package
166 The transformer pipeline
167 Pretrained tokenizers
168 Special tokens
169 Hugging Face and PyTorchTensorFlow
170 Saving and loading models
LLMs Module Question and Answer Models With BERT
171 GPT vs BERT
172 BERT architecture
173 Loading the model and tokenizer
174 BERT embeddings
175 Calculating the response
176 Creating a QA bot
177 BERT RoBERTa DistilBERT
LLMs Module Text Classification With XLNet
178 GPT vs BERT vs XLNET
179 Preprocessing our data
180 XLNet Embeddings
181 Fine tuning XLNet
182 Evaluating our model
LangChain Module Introduction
183 Introduction to the course
184 Business applications of LangChain
185 What makes LangChain powerful
186 What does the course cover
LangChain Module Tokens Models and Prices
187 Tokens
188 Models and Prices
LangChain Module Setting Up the Environment
189 Setting up a custom anaconda environment for Jupyter integration
190 Obtaining an OpenAI API key
191 Setting the API key as an environment variable
LangChain Module The OpenAI API
192 First steps
193 System user and assistant roles
194 Creating a sarcastic chatbot
195 Temperature max tokens and streaming
LangChain Module Model Inputs
196 The LangChain framework
197 ChatOpenAI
198 System and human messages
199 AI messages
200 Prompt templates and prompt values
201 Chat prompt templates and chat prompt values
202 Fewshot chat message prompt templates
203 LLMChain
LangChain Module Message History and Chatbot Memory
204 Chat message history
205 Conversation buffer memory Implementing the setup
206 Conversation buffer memory Configuring the chain
207 Conversation buffer window memory
208 Conversation summary memory
209 Combined memory
LangChain Module Output Parsers
210 String output parser
211 Commaseparated list output parser
212 Datetime output parser
LangChain Module LangChain Expression Language LCEL
213 Piping a prompt model and an output parser
214 Batching
215 Streaming
216 The Runnable and RunnableSequence classes
217 Piping chains and the RunnablePassthrough class
218 Graphing Runnables
219 RunnableParallel
220 Piping a RunnableParallel with other Runnables
221 RunnableLambda
222 The chain decorator
223 Adding memory to a chain Part 1 Implementing the setup
224 RunnablePassthrough with additional keys
225 Itemgetter
226 Adding memory to a chain Part 2 Creating the chain
LangChain Module Retrieval Augmented Generation RAG
227 How to integrate custom data into an LLM
228 Introduction to RAG
229 Introduction to document loading and splitting
230 Introduction to document embedding
231 Introduction to document storing retrieval and generation
232 Indexing Document loading with PyPDFLoader
233 Indexing Document loading with Docx2txtLoader
234 Indexing Document splitting with character text splitter Theory
235 Indexing Document splitting with character text splitter Code along
236 Indexing Document splitting with Markdown header text splitter
237 Indexing Text embedding with OpenAI
238 Indexing Creating a Chroma vectorstore
239 Indexing Inspecting and managing documents in a vectorstore
240 Retrieval Similarity search
241 Retrieval Maximal Marginal Relevance MMR search
242 Retrieval Vectorstorebacked retriever
243 Generation Stuffing documents
244 Generation Generating a response
LangChain Module Tools and Agents
245 Introduction to reasoning chatbots
246 Tools toolkits agents and agent executors
247 Fixing the GuessedAtParserWarning
248 Creating a Wikipedia tool and piping it to a chain
249 Creating a retriever and a custom tool
250 LangChain hub
251 Creating a tool calling agent and an agent executor
252 AgentAction and AgentFinish
Vector Databases Module Introduction
253 Introduction to the course
254 Database comparison SQL NoSQL and Vector
255 Understanding vector databases
Vector Databases Module Basics of Vector Space and HighDimensional Data
256 Introduction to vector space
257 Distance metrics in vector space
258 Vector embeddings walkthrough
Vector Databases Module Introduction to The Pinecone Vector Database
259 Vector databases comparison
260 Pinecone registration walkthrough and creating an Index
261 Connecting to Pinecone using Python
262 Assignment
263 Creating and deleting a Pinecone index using Python
264 Upserting data to a pinecone vector database
265 Getting to know the fine web data set and loading it to Jupyter
266 Upserting data from a text file and using an embedding algorithm
Vector Databases Module Semantic Search with Pinecone and Custom Case Study
267 Introduction to semantic search
268 Introduction to the case study smart search for data science courses
269 Getting to know the data for the case study
270 Data loading and preprocessing
271 Pinecone Python APIs and connecting to the Pinecone server
272 Embedding Algorithms
273 Embedding the data and upserting the files to Pinecone
274 Similarity search and querying the data
275 How to update and change your vector database
276 Data preprocessing and embedding for courses with section data
277 Assignment 2
278 Upserting the new updated files to Pinecone
279 Similarity search and querying courses and sections data
280 Assignment 3
281 Using the BERT embedding algorithm
282 Vector database for recommendation engines
283 Vector database for semantic image search
284 Vector database for biomedical research
Resolve the captcha to access the links!