What you’ll learn
The foundations of GPT and generative text – Large Language Models (LLM), Prompt Engineering
Receiver Augmented Generation (RAG) for Question Answering – its use cases and challenges, and real world implementation
Finetuning GPT models and their best practices, when and when not to fine tune.
Best practice strategies for troubleshooting issues with OpenAI APIs
Semantic Search – theory and Implementation
Vector databases, Pinecone – how they work, code samples
How to choose the right GPT model for completion and classification tasks
Understand how to use OpenAI’s APIs and their production best practices
Tackling the LLM hallucination problem – what the problem is, and specific strategies to mitigate it.
Note: This course assumes that you have gotten the basics of Python and Pandas down. You don’t need to be an experienced Python and Pandas developer, but the ability to follow along and understand syntax is needed.
Take your AI development skills to the next level with this course!
In this course, you will learn how to build an AI assistant powered by OpenAI’s GPT technology, HuggingFace, and Streamlit. In addition, you will learn the foundational concepts of GPT and generative AI, such as Large Language Models, Prompt Engineering, Semantic Search, Finetuning, and more. You will also understand how to use OpenAI’s APIs and their best practices, with real world code samples.
Unlike other courses, you will learn by doing. You will start with a blank app, and add features one at a time. Before adding a new feature, you will learn just enough theory to confidently build your app.
You will get all the code samples, including Google colab notebooks, and access to the Q&A forum if you get stuck. You don’t need a powerful PC or Mac that has GPUs to take this course. By the end of the course, you will be able to deploy and create your first app using OpenAI’s technology, and be confident about the theoretical knowledge behind this technology. So sign up today and start building your AI powered app!
What you will learn:
- Creating an AI chatbot with Streamlit
- IntentClassifiers – what they are, how to build it.
- Prompt Engineering: different ways of crafting the perfect prompt
- How to evaluate and choose the best prompt
- The concept of word embeddings
- How to use word embeddings to quantify semantic similarity
- How to use a vector database to store word embeddings
- How to create a search engine that searches based on word embeddings
- How to perform entity resolution for documents
- Sentiment extraction using GPT
- How to clean a finance dataset for use in a semantic search
- How to embed finance documents and upload them to a vector database
- How to use a language model to generate answers to questions
- How to use fine-tuning to ensure the language model does not hallucinate
- How to deploy a Q&A bot and a custom action system.
Who this course is for:
- Python developers with some Pandas experience who are eager to build their first AI app using GPT library