Workshop on “Working with Open-Source Large Language Models (LLMs) and Knowledge Grounding using RAG

Workshop on “Working with Open-Source Large Language Models (LLMs) and Knowledge Grounding using RAG

This workshop provides participants with practical knowledge of developing AI applications using Open-Source Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG). Participants will learn how LLMs function, explore popular open-source models such as Llama, Mistral, Gemma, and DeepSeek, and understand how RAG enhances AI systems by grounding responses with external knowledge sources. The workshop includes hands-on sessions covering document ingestion, text embedding, vector databases, semantic search, prompt engineering, and building intelligent question-answering systems using frameworks such as LangChain and Ollama. By the end of the workshop, participants will be able to design and implement domain-specific AI assistants capable of providing accurate, context-aware, and reliable responses using their own datasets.