Group Introduction and Discussion on RAG for domain specific conversation

Key take aways from the session:
1. Basic understanding of LLMs
2. How to use LLMs for chat / QA
3. Implement RAG based chat application

Agenda:
1. LLM Basics
2. Text Generation tunables (Prompts and model parameters) (Hands-On)
3. Introduction to RAG (Hands-On)
4, Building a chat application for a domain specific Question and Answers (Hands-On)

Pr-requisites for the session:

1. Knowledge / Experience in AI and Machine learning.
2. Programing skills using Python and similar programing languages
3. This is a hands on session. We are expecting all participants bring their laptop with dongle device to connect to internet
4. Tools to be installed for executing hands on project in local laptop.
5. Podman Desktop
   Ref. https://podman-desktop.io/docs/installation
6. Python 3.11 version
   For mac: Ref. https://github.com/pyenv/pyenv
   For windows: Ref. https://github.com/pyenv-win/pyenv
7. Register in watsonx.ai to avail free services for embedding and LLM models.
8. Sign up for personal account.
   Ref. https://dataplatform.cloud.ibm.com/docs/content/wsj/getting-started/signup-wx.html?context=wx&audience=wdp#personal
9. Create an API Key for your ID.
   Ref.: "Creating an API key in the console" section in https://cloud.ibm.com/docs/account?topic=account-userapikey&interface=ui#create_user_key