11-04, 14:30–15:00 (Asia/Jerusalem), Red Track
In this talk we’ll dive into how the LLM model fine tuning vs RAG approaches differ, what you need to know when employing each of these methods, and why reproducibility is important for both fine tuning and using RAG. This will be demoed through a real code example of the popular Python LangChain tool, Hugging Face Embeddings, Ollama’s LLM, and the critical pieces that impact reproducibility––code and environment as well as data and model.
Anyone in the data engineering space has been watching the development around LLMs (large language models). While LLMs represent a huge leap in AI capabilities, It’s a rare case that they can provide commercial value without any additional work. Organizations can make the most of these models by adding their own data by using RAG or fine-tuning a model.
In this talk we’ll dive into how the LLM model fine tuning vs extending with RAG approaches differ, what you need to know when employing each of these methods, and why reproducibility is important for both fine tuning and using RAG. This will be demoed through a real code example of the popular Python LangChain tool, Hugging Face Embeddings, Ollama’s LLM, and the critical pieces that impact reproducibility––git (code and environment) as well as lakeFS (data and model).
Isan Rivkin is R&D Team Leader in Treeverse, the company behind lakeFS, an open source platform that delivers resilience and manageability to object-storage based data lakes. Isan engineered and maintained petabyte-scale data infrastructure at analytics giant SmilarWeb.