No-code AI applications with ChatGPT, OpenAI, Flowise & LLMs

Course Curriculum

Chapter 1: Introduction to this course and Udemy Platform

Lecture 1: How to get the most out of the course

Chapter 2: Introduction to Language Models

Lecture 1: Introduction to Language Models

Lecture 2: What are Language Models

Lecture 3: Types of Language Models

Chapter 3: Introduction to ChatGPT

Lecture 1: OpenAI, the company behind the ChatGPT algorithm

Lecture 2: Introduction to ChatGPT

Lecture 3: Advantages of ChatGPT and difference with conventional ChatBots

Lecture 4: Limitations of ChatGPT

Chapter 4: Tools for LLM and NLP

Lecture 1: Tools for working with LLMs and NLPs

Lecture 2: Open AI API

Lecture 3: Hands-on Lab: OpenAI API

Lecture 4: Hugging Face Fundamentals

Lecture 5: LangChain Fundamentals

Lecture 6: Open-source LLM models

Chapter 5: AI Application Development with ChatGPT with LangChain

Lecture 1: Introduction to LangChain

Lecture 2: Different LangChain model types and requirements

Lecture 3: LLM input management with LangChain's Prompts Module

Lecture 4: Combination of LLM with other components through chains

Lecture 5: Providing access to external data through LangChain Indexes

Lecture 6: Giving ChatGPT the ability to memorize through the LangChain Memory

Lecture 7: Providing access to tools through LangChain's Agents module

Chapter 6: Application Development with ChatGPT without code with Flowise

Lecture 1: Developing state-of-the-art LLMs

Lecture 2: Flowise Features

Lecture 3: Installation of Flowise

Lecture 4: Getting started with Flowise

Chapter 7: Flowise components

Lecture 1: Flowise components

Lecture 2: Flowise Modeling Component

Lecture 3: Flowise Prompts Component

Lecture 4: Vector Stores, Indices, Embeddings and Document Loaders of Flowise

Lecture 5: Flowise Memory Component

Lecture 6: Flowise Chain Component

Lecture 7: Flowise Agents and Tools

Chapter 8: Flowise Practical Project (Part I)

Lecture 1: Practical Exercise: Designing the customized wizard

Lecture 2: Solution: Customized wizard design

Lecture 3: Practical Exercise: Basic ChatFlow Development

Lecture 4: Solution: Basic ChatFlow Development

Lecture 5: Practical Exercise: Development of an Assistant

Lecture 6: Solution: Development of an Assistant

Chapter 9: LLM Model Training

Lecture 1: Different variants of LLMs and how to select them

Lecture 2: Data privacy in ChatGPT training

Chapter 10: LLM training with your own documents

Lecture 1: Fundamentals of LLM training with documents

Lecture 2: Lab: Adding the QA Chain, Vector Store and PDF Loader

Lecture 3: Lab: Adding Text Splitter and OpenAI Embeddings

Chapter 11: Vector Databases

Lecture 1: Introduction to vector databases and importance for LLMs

Lecture 2: Characteristics of vector databases

Lecture 3: Different Vector Databases

Lecture 4: Pinecone Fundamentals

Lecture 5: Adding Pinecone Vector Estore

Lecture 6: Loading Embeddings and Indexes from Pinecone

Chapter 12: Flowise Practical Project (Part II)

Lecture 1: Practical Exercise: Developing Indexes and Embeddings for Pinecone

Lecture 2: Solution: Creating Vectors and Indexes in Pinecone

Lecture 3: Practical Exercise: Development of a Customized LLM

Lecture 4: Solution: Development of a customized LLM

Lecture 5: Practical Exercise: Putting into Production

Lecture 6: Solution: Production deployment of the Custom LLM

Chapter 13: Multi-stage reasoning

Lecture 1: Multi-step reasoning

Lecture 2: Linking two large language models (LLM)

Lecture 3: Chaining a third language model

Chapter 14: Hugging Face and the integration of Hugging Face in Flowise

Lecture 1: Introduction to Hugging Face and its components

Lecture 2: Hugging Face interface and model and dataset selection

Lecture 3: Tokenizer and Hugging Face Models

Lecture 4: Hugging Face Datasets

Lecture 5: Practical Lab: Use of models from Hugging Face

Lecture 6: Practical Lab: Consuming the Hugging Face model from Python

Lecture 7: Practical Laboratory: Using Hugging Face models from Flowise

Chapter 15: Open-source Large Language Models (LLMs)

Lecture 1: Benefits of open-source LLM models

Lecture 2: Different open-source LLM models and comparative analysis

Lecture 3: Fundamentals of the Llama model

Lecture 4: Alpaca model fundamentals

Lecture 5: Fundamentals of the Vicuña model

Lecture 6: Downloading and initialization of the model with Docker, LocalAI and GPT4All

Lecture 7: Using the LLM Open Source model from Flowise

Lecture 8: Advanced Project with Local AI LLama2, Faiss and Local AI Embeddings

Chapter 16: Falcon: the most powerful Open-Source model to date

Lecture 1: Fundamentals of the Falcon model

Lecture 2: Practical Lab: Using the Falcon 7b model from Flowise

Lecture 3: Practical Lab: Using the Falcon 40b model from Flowise

Chapter 17: Open-Source Cloud Models with Replicate

Lecture 1: Replicate Basics

Lecture 2: Using LLM Open-source_Llama, Vicuna and Falcon through Replicate

Lecture 3: Use of Replicate's Llama2 model through Flowise

Chapter 18: Flowise Credentials

Lecture 1: Credential management in Flowise

Chapter 19: Auto-GPT the AI that outperformed ChatGPT

Lecture 1: Introduction to Auto-GPT