
Course Introduction.
Hello.
My name is André Vieira and I will guide you on this learning journey.
You can find me on Linkedin André Vieira de Lima
Understand business needs through Storytelling.
Learn basic concepts of Artificial Intelligence, Machine Learning, Data Science and Natural Language Processing.
Preconditions for learning and technologies used.
Discover which development tools are used in this training. Understand how our project will be structured.
Creating the project in Pycharm.
This module is optional. If you do not intend to use Pycharm and want to install the libraries and dependencies manually, just follow the guide provided.
This module is optional. Libraries and dependencies will be installed during the development of the project. If you are interested in installing it in advance, just follow the guide provided.
Data used for learning.
Datasets used for learning.
Learn Repository: a centralized storage location for software, digital artifacts, data, and metadata.
Optional module.
Understanding and analyse the dataset.
Learn Data cleaning: a process that identifies and corrects errors, inconsistencies, and incomplete data in a dataset.
Learn how to remove records with missing data.
Learn how to remove records with anomalies
Learn how to remove outiers
Learn how to remove irrelevant words from your records for queries.
Learn how to reduce the words in your records, making it easier to search for synonyms.
Learn how to convert texts to lowercase letters, making it easier to search for synonyms.
Learn how to clean texts, making it easier to search for synonyms.
Learn how to refactor code by organizing the implemented content.
Learn how to compact the data source.
Learn how to pre-process records before creating the text search engine.
Learn concepts about Flask, web framework and APIs.
Create your first Flask application
Learn what is URI and Rest API
Learn Routing, Get Method and Swagger.
Learn Routing, Post Method and Swagger
Learn what is Vector Embeddings
Learn how to calculate the similarity of embeddings.
The evolution of Vector Embeddings.
Learn word embeddings to Semantic Search
Learn how to generate word embeddings.
Dimensionality Reduction
Learn what is Search Engine.
Learn what is Semantic Search
Learn what is Transformers.
Reading and Transforming Embeddings File
BERT and S-BERT
Semantic Search Engine with S-BERT
Refactoring code to use APIs: Data Preprocessing
Refactoring code to use APIs - Word Embeddings
Refactoring Code to use APIs - Semantic Search
PyTorch and Huggin Faces
S-BERT - Result Assessment
Discover what Generative AI is.
Discover what LLMs is.
Discover what is LLMs Agents, OpenAI and ChatGPT API.
Discover what is RAG, LangChain and Fine Tuning.
Read data and generate embeddings.
RAG - Retrieve data and OpenAI envirionment variable
Develop an API to Search Text with RAG - Template, RAG and API
Diferences between RAG and Semantic Search
Project Avaliable for Download
Credits and Acknowledgemengts
In a rich Artificial Intelligence Bootcamp, learn S-BERT and RAG(LLM) through Natural Processing Language (NLP) with Python, and develop a semantic text search engine API by solving a real problem of a purchasing analysis system.
As content:
Fundamentals.
Learn the fundamentals of Data Science;
Learn the fundamentals of Machine Learning;
Learn the fundamentals of Natural Language Processing;
Learn the fundamentals of Data Cleaning, Word Embendings, Stopwords, and Lemmatization;
Learn the fundamentals of text search by keywords and semantic text search;
Practice Data Science to understand the problem, prepare the database and statistical analysis;
Practical project.
This course is divided into two modules where you will learn concepts and build a text search application in a practical way.
BERT
In this module, you will work with:
Python to develop the application;
Data cleaning techniques to prepare the database;
Using the SpaCy library for Natural Language Processing;
Generating Word Embeddings and calculating similarity for data recovery;
Transformers model for data recovery by context;
S-BERT as a semantic text search tool;
Flask and Flassger for developing APIs.
Retrieval-augmented generation (RAG)
In this module you will work with:
Python to develop the application;
Large Language Models (LLMs). Advanced AI models that understand and generate natural language;
Using the OpenAI API to build AI products
LangChain to build applications that use LLMs;
Flask and Flassger for developing APIs.
Optional module: learn how to develop API with Flask.
Welcome and have fun.