## Agenda of talk

- LLMs and its limitation

- RAG

- Gemma

- Disussions & developments

- Q&A

## Breif description of the talk

Our focus will be on Google's cutting-edge LLM, Gemma, augmented with additional capabilities drawn from the Retrieval-Augmented Generation (RAG) framework. We will also leverage robust ecosystem of tools such as the Hugging Face transformers library, LangChain, and the Faiss vector database to build a RAG bot with Varsity(by Zerodha) knowledge DB.