This session offers valuable insights from our experience transforming a RAG (Retrieval Augmented Generation) Proof of Concept, which using a Neo4j knowledge graph, into a fully-fledged cloud application. This session is designed to provide practical guidance on enhancing your development practices and optimizing Neo4j-based applications for the cloud environment.
During the workshop, the team will delve into several key areas, including:
- Prioritizing Development: Discover strategies for efficiently prioritizing development tasks to ensure your project advances smoothly from concept to production.
- Moving Code out of Jupyter Notebooks: Learn the best practices for transitioning code from Jupyter Notebooks to a more structured and scalable environment suitable for cloud application development.
- Creating Ingestion Pipelines: Gain insights into designing and implementing effective ingestion pipelines that streamline data flow into your Neo4j knowledge graph, enhancing data reliability and availability.
- Refactoring the Graph Data Model: Explore techniques for refining and optimizing your graph data model to better support cloud applications' scalability and performance requirements.
Slides: https://drive.google.com/file/d/19fEYYuCDTQeckdXAO7yNPPyN-zMB38FJ/view?usp=sharing
Needle Design Kit: https://bit.ly/3W71PP0
GenAI Ecosystem: https://bit.ly/4cpAY6D
Graph Data Science with Generative AI Workshop: https://youtube.com/live/SUhM5SOYcd4
Tomaz Bratanic Blog: https://medium.com/@bratanic-tomaz
Going Meta Series: https://development.neo4j.dev/video/going-meta-a-series-on-graphs-semantics-and-knowledge/
LangSmith: https://www.langchain.com/langsmith
Neo4j Developer Blog: https://bit.ly/3LcYx6q
NeoDash: https://bit.ly/3L8ecEh
Trainers: Daniel Bukowski, Alex Gilmore & Alexander Fournier
#neo4j #graphdatabase #genai #llm #knowledgegraph #deployment #cloud