Dan Gibson - An Introduction to Retrieval Augmented Generation - PyData London 2024

How do you build chatbots that answer questions using your organisation's data? The answer is Retrieval Augmented Generation (RAG). In this session you'll be introduced to RAG and build a simple RAG powered chatbot in Python.
Until very recently, if an organisation wanted a bespoke chatbot application, they had to spend millions of pounds and fund highly specialised teams, often training and hosting their own sophisticated AI models. Retrieval Augmented Generation (RAG) allows organisations of any size, and developers who haven't got specialised AI skills, to build capable chatbots, that can answer questions based on data that you control.
This session is designed to get you started on you RAG journey. You'll be introduced to RAG and then taken though a guided exercise to build a very simple RAG powered chatbot. We've designed this session to be suitable for participants with basic Python skills, but also be a good overview for those who consider themselves capable Python developers, but haven't tried out RAG.
Participants can get ahead and set their machines up by downloading:
github.com/Personify-AI/rag_s...
Then reading the README.md.
www.pydata.org
PyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R.
PyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases.
Want to help add timestamps to our KZbin videos to help with discoverability? Find out more here: github.com/numfocus/KZbinVi...