09-19, 13:40–14:30 (Europe/Amsterdam), Mondriaan
This session is a GenAI talk, where you will learn how Knowledge Graphs, Vectors and Retrieval Augmented Generation (RAG) can support your projects.
GenAI and Large Language Models (LLMs) have the potential to increase productivity and provide access to data, but they need grounding and good context to be truly useful.
How can you securely give LLMs access to your own private data?
How do you stop LLMs "making things up"?
How can you integrate LLMs into your applications and workflow?
In this practical, live coding, talk, you will learn:
- About Large Language Models (LLMs), hallucination, and practical skills for integrating them into your solutions
- The role Retrieval Augmented Generation (RAG) has in grounding LLM-generated content
- How you can use vector indexes and embeddings to perform similarity and keyword search
- How graphs can can support you in understanding relationship in your data
- How to implement an RAG agent using Python and open-source software including LangChain and Neo4j community edition
After attending this session, you will have the knowledge to create LLM-based applications using Python and LangChain and insight on controlling and integrating LLMs in your projects.
Martin is an experienced computer science educator and open source software developer.
Martin creates educational content for Neo4j and supports developers in using graph technology to understand their data.
As a child he wanted to be either a Computer Scientist, Astronaut or Snowboard Instructor.