2023-12-01 –, Main stage
In this presentation, we will introduce a recent proposal in AI that is called Retrieval-Augmented Generation (RAG).
This technique is able to leverage the natural language capabilities of Large Language Model (LLM) such as ChatGPT in order to query a private database. You can literally ask question about your data, without the need to fine-tune an LLM with all your private data. We will show also an example of RAG using Langchain, an open source framework for writing applications for LLM. We will execute a demo with a few lines of Python to chat with private data using a vector database like Chroma or Elasticsearch.
Enrico is a Tech Lead and Principal Software Engineer at Elastic, a Silicon Valley company. He it also an Adjunct Professor of computer science at the University of Turin and teacher of programming at ITS-ICT Piemonte. He has been a programmer since 1996 and has worked on several open source projects, including Zend Framework with more than 500 million downloads. TEDx and International speaker at more than 120 conferences. He recently gave a workshop about LLM and ChatGPT at ReactJsDay 2023 and a talk at PHPDay 2023 on how to integrate ChatGPT with Elasticsearch to solve queries expressed in natural language. More information can be found at zimuel.it