This courseware is designed for beginners who want to learn about generative AI. It is a collection of tutorials and hands-on exercises that will help you learn how to use generative AI to create new content. The courseware is divided into three parts:

• Introduction to Generative AI - This part introduces you to Hugging Face's Transformers library and the basics of generative AI. You will learn how to use the library and Hugging Face's pre-trained models to generate text, Text Question answering, Visual Q&A, and image captioning.
• Langchain, VectorDB, RAG and Agents - This part introduces you to the basics of Langchain, VectorDB, RAG and Agents. You will learn how to use the langchain library for prompting, chaining, and vectorizing text. You will also learn how to use the VectorDB library to vectorize text. you will learn how to use the RAG library to answer question from documents. Finally, you will learn how to use the Agents.
• Further exploration - This sections is a list of resources that you can use to further explore generative AI.

• You can use the "Open in Colab" button in this notebook to open them in Google Colab.
• Alternatively, you can clone this Repository

git clone https://github.com/rkandas/LLMCourseware.git

• Open the repository in Google Colab
  • Open Google Colab
  • Click on File > Open Notebook
  • Click on GitHub tab
  • Paste the URL of this repository [https://github.com/rkandas/LLMCourseware] in the search box and hit Enter
  • Click on Part-1-Huggingface_AI_Sample_Scripts.ipynb to open the notebook
• Once the notebook is open in Google Colab,
  • Click on File > Save a copy in Drive to save a copy of the notebook in your Google Drive. This will allow you to edit and save your changes.
  • Click on Runtime > Change runtime type and select GPU as the hardware accelerator
  • you can run the cells by clicking on the Run button on the left of each cell.

Google Colab is a free cloud service that provides GPU and TPU for training machine learning models. It is a great tool for learning and experimenting with machine learning. You can use it to run the notebooks in this courseware.

If you are new to colab, you can watch the following video to learn how to use it.

Hugging Face's Transformers library is a python library that provides an easy-to-use API to access a large number of pre-trained models for Natural Language Processing (NLP). It also provides an easy-to-use API to train custom models. This notebook introduces you to the basics of the library and shows you how to use it to generate text, Text Question answering, Visual Q&A, and image captioning.

Use the "Open in Colab" button above to open the notebook in Google Colab.

Langchain is a python library that provides an easy-to-use API to chain and vectorize text. Retrieval Augmented Generation (RAG) is a method to answer question from documents using VectorDB and LLM. Agents is a concept that uses LLM, Tools and langchain to complete a given goal. This notebook introduces you to the basics of langchain, VectorDB, RAG and Agents.

Use the "Open in Colab" button above to open the notebook in Google Colab.

This section is a list of resources that you can use to further explore generative AI.

• Neural Networks: Zero to Hero - This is a highly recommended course by Andrej Karpathy, Director of AI @ Tesla and Founding member of Open AI https://karpathy.ai/zero-to-hero.html. In this course Karpathy deep dives into the fundamentals of neural networks and LLMs and shows how to build a GPT model from scratch.

  

• Generative AI Learning Path from Google. https://www.cloudskillsboost.google/paths/118

• Langchain Cookbook by Data Independent This is a series of videos by Data Independent that shows detailed usecases of Langchain.

  • Fundamentals of Langchain
  

  Use the "Open in Colab" button above to open the notebook in Google Colab.

  • Usecases for Langchain
  

  Use the "Open in Colab" button above to open the notebook in Google Colab.

  • Video Course

  

• Building LLM applications for production - https://huyenchip.com/2023/04/11/llm-engineering.html
• The Practical Guides for Large Language Models -

• ChromaDB - https://docs.trychroma.com/getting-started
• Langchain - https://python.langchain.com/en/latest/getting_started/getting_started.html
• Hugginface Transformers - https://huggingface.co/docs/transformers/index