Fanghua Yu, a.k.a. Joshua Yu, is an IT professional with over 20 years of experience. He is fascinated with information and data visualization. He is also passionate about computer education for the younger generations. Joshua currently lives in Sydney, Australia.
Low-code Threat Investigation Using Neo4j AuraDB and BloomPintasan Saloma Bridge in KL, Malaysia by the authorWhy Open-Source Cyber Intelligence?Open-source Cyber Threat Intelligence (OSCTI) has become popular among security professionals and organizations due to its accessibility,... read more
Experiment on PDF Document Ingestion PipelineChildren’s Gallery Melbourne made of Lego bricks. Photo taken at LEGOLAND® by author.In this article, I will demonstrate and share the procedures to use unstructured.io for PDF document parsing, extracting, and ingestion into the Neo4j... read more
Transitioning from SQL to GQL — Image generated by DALL-E by authorThis article has minor changes since its first publish, thanks to suggestions from Philip Rathle on SQL 2023 and GQL as a new language standard.The Birth of New Query Language StandardSince the last major... read more
Combining the power of LlamaParse and Neo4j for better RAG applications.Image generated by DALL-E.A month ago, LlamaIndex announced the launch of LlamaCloud, a pioneering managed parsing, ingestion, and retrieval service aimed at enhancing production-grade context augmentation for LLM and RAG... read more
The GenAI Stack — A Brief OverviewSince the release of Neo4j’s GenAI Stack, the platform has garnered significant attention for its innovative approach to Generative AI (GenAI) application development.The GenAI Stack is a pre-built development environment created by... read more
What LLM & Graph May Bring to the Future of Knowledge GraphsNight light at Federation Square in Melbourne, photo by AuthorAbstractIn the last several decades, when people consider building a knowledge-related solution, they tend to look into two distinct directions based on whether data is... read more
A multi-modal model use case.Image generated by DALL-E by authorIn this tutorial, we’ll demonstrate how easy it is to use Google’s Gemini Pro to extract entities, relationships, and fields from an entity-relationship (ER) diagram, which are then transformed into assets of a... read more
Experiments on AWS, Azure, and GCPAn exhibition at NGV, Melbourne, Australia. Photo by author.AbstractIn many GenAI solutions built today, e.g., RAG, doing similarity searches over embeddings of text, images, and other data becomes more and more popular. There are quite some approaches... read more
A Step-by-step Walkthrough With GenAI-Stack and OpenAISculptures of lifeguards at Geelong Beach, Victoria, Australia. Photo by author.AbstractIn this article, I will walk through all the required steps for building a RAG application from PDF documents, based on the thoughts and... read more
Exploring the Shortcomings of Text Embedding Retrieval for LLM GenerationLoch Awe in Scotland, photo by author.AbstractExternal knowledge is the key to resolving the problems of LLMs such as hallucination and outdated knowledge, which can make LLMs generate more accurate and reliable responses... read more
Editor’s Note: This presentation was given by Fanghua Joshua Yu at NODES 2019. Presentation Summary Fanghua Joshua Yu. I'm a Neo4j Pre-Sales & Field Engineering Lead in the APAC region. Today's session theme is based on a question. The question is: Have you ever complained... read more
Summary Data profiling is a widely used methodology in the relational database world to analyse the structure, contents and metadata of a data source. Generally, data profiling consists a series of jobs executed upon the data source to collect statistics and produce informative summaries about... read more
