Australian National University

Qingqin Fang

Transformative Advances in Language Models through External Knowledge Integration

Author: Qingqin Fang (

 ORCID:

0009–0003–5348–4264)

 Introduction

In the dynamic field of natural language processing, the integration of external knowledge has emerged as a pivotal strategy for enhancing the performance of language models.

Deeper understanding of In-Context Retrieval-Augmented Language Models

Wendi Fan

Let’s explore GR-2 together. Author Wendi Fan (

 ORCID: 0000–0003–0284–9166

) Introduction GR-2 is a cutting-edge generative model designed for versatile and generalisable robot manipulation, developed by the Robotics Research Team at ByteDance Research. It represents a significant step forward in robotics, enabling robots to execute a wide range of manipulation tasks in various environments.

GR-2: A Generative Video-Language-Action Model for Robot Manipulation

Vaibhav Khobragade

From Naive to Modular: Tracing the Evolution of Retrieval-Augmented Generation

Author · Vaibhav Khobragade (

 ORCID:

0009–0009–8807–5982) Introduction Large Language Models (LLMs) have achieved remarkable success.

Three Paradigms of RAG

Wenyi Pi

Exploring innovative Strategies in Combating Misinformation with Enhanced Multimodal Understanding Author Wenyi Pi (

 ORCID

: 0009–0002–2884–2771) Introduction Misinformation refers to false or inaccurate information that is often given to someone in a deliberate attempt to make them believe something that is not true. This has a significantly negative impact on public health, political stability and social trust and harmony.

Multimodal Large Language Models for Misinformation Detection and Reasoning

Amanda Kau

Techniques to integrate Knowledge Graphs into Language Models

 Author

Amanda Kau

 (ORCID:


 0009–0004–4949–9284


 )

Introduction Both knowledge graphs (KGs) and pre-trained language models (PLMs) have gained popularity due to their ability to comprehend world knowledge and their broad applicability.

A Deep Dive Into Knowledge Graph Enhanced Pre-trained Language Models

Dhruv Gupta

Understanding the Power and Applications of Natural Language Processing

 Author

Dhruv Gupta (

 ORCID:

0009–0004–7109–5403) Introduction We are living in the era of generative AI. In an era where you can ask AI models almost anything, they will most certainly have an answer to the query. With the increased computational power and the amount of textual data, these models are bound to improve their performance.

NLU vs. NLG: Unveiling the Two Sides of Natural Language Processing

Zijian Yang

Le Chat by Mistral: Access ChatGPT-Like Features, Image Generation, Canvas, Artifact, and More for Free


 Discover Le Chat: Free ChatGPT Alternatives with Canvas, Internet Search, and Flux.1 Image Generation


 Author

Zijian Yang (

 ORCID:

0009–0006–8301–7634)

 Introduction

Imagine accessing premium ChatGPT features — Canvas, internet search, and PDF

Le Chat by Mistral: Access ChatGPT-Like Features, Image Generation, Canvas, Artifact, and More for…

Enhancing Data Interactivity with LLMs and Neo4j Knowledge Graphs Author Wenyi Pi (

 ORCID

: 0009–0002–2884–2771) Introduction Since OpenAI launched ChatGPT, a

 large language model (LLM)

based chatbot, in 2023, it has set off a technological wave.

The integration of large language models (LLMs) with Neo4j-based knowledge graphs

Xuzeng He

Latest findings in multiple research directions for tackling reasoning and common sense challenges Author: Xuzeng He (

 ORCID:

0009–0005–7317–7426) Knowledge Graphs, such as Wikidata, contain rich relational information between entities and have been widely used as a structured format for storing and representing relational information.

Large Language Models and Knowledge Graphs: Ways to combine them

Swinburne University of Technology

Nakul Nambiar

Aishwarya Nambissan

A novel approach to improving the efficiency of text search in graph databases utilizing Neo4j, OpenAI, and Typesense. Authors  Nakul Nambiar (ORCID: 0009–0009–9720–9233) Aishwarya Nambissan (ORCID: 0009–0003–3823–6609)  The ability to use cutting-edge tools and frameworks is essential for staying ahead in the ever-changing field of technology.

Typesense and Neo4j in a hybrid information retrieval solution

Exploring the OpenAlex Data Structure and Visualization Author: Qingqin Fang (

 ORCID:

0009–0003–5348–4264)

 Introduction to OpenAlex

In today’s world, the realm of research papers is brimming with countless hot topics, and the sheer volume of publications can be overwhelming.

Unveiling Research Trends through OpenAlex Visualization

Neo4j APOC Library Use Case

 Author

Wenyi Pi (

 ORCID:

0009–0002–2884–277)

 Introduction

In the realm of Neo4j, the APOC (Awesome Procedures on Cypher) library stands as a powerful tool. Previously, We have talked about the importance of APOC in optimising Cypher queries and improving query efficiency in our article Exploring Methods of Cypher Query Optimisations.

Introduction to APOC: Enhancing Neo4j Capabilities

Unlocking the Future of AI: The Transformative Journey of Large Language Models Author · Vaibhav Khobragade (

 ORCID:

0009–0009–8807–5982)

 Introduction

Human language development is innate and evolves throughout life. Machines lack this ability to evolve without advanced AI algorithms.

The Journey of Large Language Models: Evolution, Application, and Limitations

Unlocking the Power of Questions — A deep dive into Question Answering Systems

Author:

 Amanda Kau (ORCID:


 0009–0004–4949–9284


 )

Virtual assistants have popped up on numerous websites over the years.

Harnessing The Power of Knowledge Graphs in Question Answering

Dhruv Gupta

Improving the performance of Large Language Models Author  Dhruv Gupta (ORCID: 0009-0004-7109-5403)  ChatGPT, which first came out in late 2022, took the world by storm. Since then, various LLM models and LLM based products such as Meta’s Llama and Google’s Gemini have emerged, demonstrating the power of LLMs.

RAG: The next big thing after LLMs?

Amir Aryani

Authors  Nakul Nambiar (ORCID: 0009-0009-9720-9233) Amir Aryani (ORCID: 0000-0002-4259-9774)  Knowledge graphs, which offer a structured representation of data and its relationships, are revolutionising how we organise and access information.

Mini RAG using Neo4j

Author  Amir Aryani (ORCID: 0000-0002-4259-9774) Introduction   In this article we look at Research Graph as an information model , and an approach to connect and capture the connections between research outputs, researchers and research activities. We explore the metadata model, and we discuss how to capture this graph in a Neo4j Graph Database.

Research Graph 101

Aland Astudillo

How to use GROBID to extract text from PDF  Author  Aland Astudillo (ORCID: 0009-0008-8672-3168)  GROBID is a powerful and useful tool based on machine learning that can extract text information from PDF files and other files to a structured format. One of the key challenges in knowledge mining from academic articles is reading the content of PDF files.

How to use GROBID

Unlocking the power of language models: A deep dive into BERT


 Author:


 Dhruv Gupta (ORCID:


 0009–0004–7109–5403


 )

Clive Humby, in 2006 rightly said, “Data is the new oil”. With data being present everywhere, it has never been more valuable.

Language Models: Deep Dive into BERT

An introduction to tools supporting PubMed Author: Xuzeng He (

 ORCID:

0009–0005–7317–7426) PubMed is a free Web literature search service developed and maintained by the National Center for Biotechnology Information (

 NCBI

), and it is also a part of NCBI’s Entrez retrieval system that provides access to a diverse set of 38 databases.

Enhancing PubMed: from a Medical Database to beyond

Exploring the potentials and limitations of Vision Language Models

Author:

 Amanda Kau (ORCID:


 0009–0004–4949–9284


 )

The human brain is more extraordinary than any machine we could build. From an early age, many of us gain the ability to comprehend what our eyes tell us and articulate it. Furthermore, we combine evidence from all our senses to reason.

How Much Can Vision Language Models Really “See”?

How to efficiently retrieve information for different applications

Author Wenyi Pi (ORCID: 0009-0002-2884-2771) This article aims to explore various ways in which Retrieval-Augmented Generation (RAG) can be utilised to retrieve information and generate responses effectively within the dialogue system. The rationale behind utilising RAG as well as potential ways in which it can be employed effectively will be covered.

Efficient Information Retrieval and Response Generation with Retrieval-Augmented Generation (RAG)

Addressing Misinformation, Bias, and Privacy Concerns

Author:

 Wenyi Pi (ORCID:


 0009–0002–2884–2771


 )

Recently, the spread of false or misinformation has become an important concern for people all over the world, especially in the era of big data and multimedia, where people are faced with a flood of information that makes it difficult to determine its authenticity.

The Ethical and Social Impact of Artificial Intelligence

Science in the age of large language models

Generative AI entails a credit–blame asymmetry

Exploring AI’s Ethical Terrain: Addressing Bias, Security, and Beyond

Author: Vaibhav Khobragade (

 ORCID:

0009–0009–8807–5982) Large language models (LLMs) like OpenAI’s GPT-4, Meta’s LLaMA, and Google Gemini (previously called Bard) have showcased their vast capabilities, from passing bar exams and crafting articles to generating images and website code.

Ethics and AI: Confronting the Challenges Ahead

The AI Helper Turning Mountains of Data into Bite-Sized Instructions

Author Aland Astudillo (ORCID: 0009-0008-8672-3168) LLMs have been changing the way the entire world deals with problems and day-by-day tasks. To make them better for specific applications, they need huge amounts of data and complex and expensive approaches to training them.

What is LLMLingua?

Zhuochen Wu

Authors:  Nakul Nambiar (ORCID: 0009-0009-9720-9233) Zhuochen Wu (ORCID: 0009-0000-5642-5348)  Research Graph is a structured representation of research objects that captures information about entities and the relationships between Researcher, Organisation, Publication, Grant and Research Data.

How to use GPT API to export a research graph from PDF publications

Tools and Platform for Integration of Knowledge Graph with RAG pipelines.

Authors Aland Astudillo (ORCID: 0009-0008-8672-3168) Aishwarya Nambissan (ORCID: 0009-0003-3823-6609) Many users of chatbots such as ChatGPT, have encountered the problem of receiving inappropriate or incompatible responses. There are several reasons why this might happen.

Unveiling the Synergy: Retrieval Augmented Generation (RAG) Meets Knowledge Graphs

Amir Aryani

A brief overview of different types of clustering techniques and their algorithms. Authors Aishwarya Nambissan (ORCID: 0009-0003-3823-6609) Amir Aryani (ORCID: 0000-0002-4259-9774)

 Background

Clustering is a fascinating technique used in machine learning, where patterns or data points are grouped based on their similarities. It’s like finding hidden connections among different data points without predefined labels.

19 Clustering Techniques

Unlocking the power of knowledge graphs in research catalogues: A deep dive into OpenAlex


 Author:


 Dhruv Gupta (ORCID:


 0009–0004–7109–5403


 )

Clive Humby, in 2006 rightly said, “Data is the new oil”. With data being present everywhere, it has never been more valuable.

Knowledge Graphs: Deep Dive into OpenAlex

Improving the performance and application of Large Language Models

Author Amanda Kau (ORCID: 0009-0004-4949-9284) Large language models (LLMs) like GPT-4, the engine of products like ChatGPT, have taken centre stage in recent years due to their astonishing capabilities. Yet, they are far from perfect.

Understanding Retrieval Pitfalls: Challenges Faced by Retrieval Augmented Generation (RAG) models

Yunzhong Zhang

Efficient creation of a stoplight report with data dashboard images

Author: Yunzhong Zhang (ORCID: 0009–0002–8177–419X) Comparing data dashboards is crucial for understanding trends and performance differences. Traditionally, this task required manual effort, which was slow and sometimes inaccurate. Now, thanks to OpenAI’s GPT-4 with Vision (GPT-4V), we are able to automate and improve this process.

How to use GPT-4V For Stoplight Report

Author Dhruv Gupta (

 ORCID

: 0009–0004–7109–5403) Introduction Large Language Models (LLMs) have become the new face of Natural language processing (NLP). With their generative power and ability to comprehend human language, the human reliance on these models is increasing every day. However, the LLMs have been known to hallucinate and thus produce wrong outputs.

Prompt engineering: A Way to Smartly Use AI

Recent Advances in Using Machine Learning with Graphs — Part 2 Latest findings in multiple research directions for handling graph construction and network security issues Author · Xuzeng He (

 ORCID:

0009–0005–7317–7426) Introduction A graph, in short, is a description of items linked by relations, where the items of a graph are called nodes (or vertices) and their relations are called edges (or links). Examples of

Recent Advances in Using Machine Learning with Graphs — Part 2

Bridging Human Perception and AI’s Future: The Convergence of Visual Understanding and Semantic Networks Author · Vaibhav Khobragade (

 ORCID:

0009–0009–8807–5982)

 Introduction

The fusion of Vision-Language Models (

 VLMs

), Generative Models, and Knowledge Graphs (

 KGs

) is reshaping how artificial intelligence (AI) understands and interacts with the world.

Tuning Vision-Language Models and Generative Models with Knowledge Graph

Using intelligence to use artificial Intelligence: A deep dive into Prompt Engineering


 Author


 Dhruv Gupta (ORCID:


 0009–0004–7109–5403


 )

Introduction Large Language Models (LLMs) have become the new normal in the field of Natural Language Processing (NLP). With their improved performance and generative power, people around the world are relying on it for

Prompt Engineering

An Overview of Constructing a Knowledge Graph Author · Qingqin Fang (

 ORCID:

0009–0003–5348–4264) 1. Introduction 1.1 What is a Knowledge Graph Knowledge Graphs are structured semantic knowledge bases used to rapidly describe concepts and their relationships in the physical world.

Unlocking Intelligence: The Journey from Data to Knowledge Graph

Boosting Performance for Knowledge Graphs with Neo4j APOC Library

 Author

Wenyi Pi (ORCID: 0009–0002–2884–2771) Introduction A

 knowledge graph

(graph database) captures information about main entities in a domain and the relationships between them. It was an augmented feature store for connected data which gave access to compute, access and operationalise structure features.

Exploring Methods of Cypher Query Optimisations

Aditya Iyengar

How AI is Transforming Medicine and Improving Lives
 
 AI in the Healthcare Domain
 


 Author

Aditya Iyengar (ORCID: 0009–0005–1959–9724)

 Introduction

The rapid integration of Artificial Intelligence (AI) into healthcare is no longer just a futuristic vision — it is happening now and at an extraordinary pace.

The Future of Healthcare

The Most Recent Cutting-Edge Models


 Author

Aditya Iyengar (ORCID: 0009–0005–1959–9724)

 Introduction

The past 6 months marked significant technological leaps in the field of artificial intelligence (AI), especially in the realm of image generation. In this six-month window, multiple innovations redefined the capabilities of text-to-image, video generation, and multimodal AI systems.

The New Era of AI Image Generation

Mingrui Gao

Working Examples


 Author

Mingrui Gao (

 ORCID

: 0009–0005–7271–2677)

 Introduction

Machine learning has revolutionised countless industries, but deploying ML models remains a significant challenge for many data scientists and developers.

What is Cog?

Let’s explore MLflow together. Author Wendi Fan (

 ORCID: 0000–0003–0284–9166

) Introduction MLflow is an open-source platform designed to manage the entire lifecycle of machine learning projects. It helps developers and data scientists streamline their workflows by tracking experiments, managing models, and deploying them efficiently.

MLflow Beginner’s Guide: How to Get Started with MLflow

Tarun Krishnan

Unleashing FLUX1.1 with the BFL API


 Author

Tarun Krishnan (

 ORCID

: 0009–0006–6647–127X)

 Introduction

With the growing demand for

 image generation models

in various applications, the need for

 APIs

that seamlessly integrate these models into developers’ workflows has skyrocketed.

The Fast Lane of Image Generation

Tohfa Siddika

The Godfather of AI Author Tohfa Siddika Barbhuiya (

 ORCID

: 0009–0007–2976–4601) In a monumental moment for the world of Artificial Intelligence (AI), Geoffrey Hinton, known as the “Godfather of AI,” has been awarded the Nobel Prize for his pioneering work in neural networks and deep learning. He has been awarded the 2024 Nobel Prize in physics by the Royal Swedish Academy of Sciences.

Geoffrey Hinton Wins Nobel Prize

Evaluating the Role of Self-Reflection in AI: Innovation or Overcomplication?

Author Tohfa Siddika Barbhuiya (

 ORCID

: 0009–0007–2976–4601) Introduction Artificial Intelligence (AI) has made remarkable strides over the past decade, with new advancements pushing the boundaries of what machines can achieve. One of the latest developments in the field is the introduction of “reflection” within AI models.

The Idea of Reflection Models

OpenAI Canvas and DevDay: Advancing AI Collaboration with Voice Realtime API, Model Distillation, and More Explore OpenAI’s latest tools and features — Canvas, Realtime API, Prompt Cache, Visual Fine-Tuning Author Zijian Yang (

 ORCID:

0009–0006–8301–7634) Introduction OpenAI recently introduced a new feature called Canvas, which is designed to provide ChatGPT users with a more powerful writing and coding collaboration

OpenAI Canvas and DevDay: Advancing AI Collaboration with Voice Realtime API, Model Distillation…

Working Examples Author Mingrui Gao (

 ORCID

: 0009–0005–7271–2677) Introduction In the rapidly evolving landscape of artificial intelligence, Large Language Models (LLMs) have emerged as powerful tools capable of understanding and generating human-like text. While cloud-based services offer convenient access to these models, there’s a growing demand for local, hands-on experimentation.

What is LM Studio?

A novel compression technique ensuring comparable performance with 70% less parameters

Author Amanda Kau (

 ORCID

: 0009–0004–4949–9284) Introduction The sizes of large language models (LLMs) have been steadily increasing over the last few years.

CompactifAI: Large Language Models Don’t Actually Have To Be Large

Let’s explore ChatGPT’s Advanced Voice Mode Author Wendi Fan (

 ORCID: 0000–0003–0284–9166

) Introduction In today’s fast-paced world, where convenience and efficiency are paramount, OpenAI’s latest addition to ChatGPT, the

 Advanced Voice Mode

, sets a new standard for human-computer interaction.

Unlocking the Power of ChatGPT’s Advanced Voice Mode

Automated Knowledge Graph Construction with Large Language Models — Part 2

 Harvesting the Power and Knowledge of Large Language Models

Author Amanda Kau (

 ORCID

:

 0009–0004–4949–9284

) Introduction Knowledge graphs (KGs) are a structured representation of data in a graphical format, in which entities are represented by nodes and are connected by edges representing relationships

Automated Knowledge Graph Construction with Large Language Models — Part 2

Understanding the Evolutionary Journey of LLMs Author Wenyi Pi (

 ORCID

: 0009–0002–2884–2771) Introduction When we talk about large language models (LLMs), we are actually referring to a type of advanced software that can communicate in a human-like manner. These models have the amazing ability to understand complex contexts and generate content that is coherent and has a human feel.

Brief Introduction to the History of Large Language Models (LLMs)

An improvement architecture superior to the Transformer, proposed by Meta Author · Qingqin Fang (

 ORCID:

0009–0003–5348–4264) Introduction Recently, researchers from Meta and the University of Southern California have introduced a model called Megalodon. They claim that this model can expand the context window of language models to handle millions of tokens without overwhelming your memory.

The longer the context, the better? Unlimited Context Length in Megalodon

Attention mechanism not getting enough attention Author Dhruv Gupta (

 ORCID

: 0009–0004–7109–5403) Introduction As discussed in this article, RNNs were incapable of learning long-term dependencies. To solve this issue both LSTMs and GRUs were introduced. However, even though LSTMs and GRUs did a fairly decent job for textual data they did not perform well.

Transformers Models in NLP

The Three Oldest Pillars of NLP

Author Dhruv Gupta (

 ORCID

: 0009–0004–7109–5403) Introduction Natural Language Processing (NLP) has almost become synonymous with Large Language Models (LLMs), Generative AI, and fancy chatbots. With the ever-increasing amount of textual data and exponential growth in computational knowledge, these models are improving every day.

RNNs vs GRUs vs LSTMs

Large Language Models for Fake News Generation and Detection Author Amanda Kau (

 ORCID

: 0009–0004–4949–9284) Introduction In recent years, fake news has become an increasing concern for many, and for good reason. Newspapers, which we once trusted to deliver credible news through accountable journalists, are vanishing en masse along with their writers.

Are Large Language Models Our Allies or Enemies in the Fight Against Fake News?

A Unified and Collaborative Framework for LLM Author · Qingqin Fang (

 ORCID:

0009–0003–5348–4264) Introduction In today’s rapidly evolving field of artificial intelligence, large language models (LLMs) are demonstrating unprecedented potential. Particularly, the Retrieval-Augmented Generation (RAG) architecture has become a hot topic in AI technology due to its unique technical capabilities.

RAG 2.0 is Coming?

Exploring the Potential of Temporal Feature-Logic Embedding (TFLEX) in Complex Query Resolution

Author · Vaibhav Khobragade (

 ORCID:

0009–0009–8807–5982)

 Introduction

Artificial intelligence (AI) and knowledge representation in the field of temporal knowledge graphs are rapidly gaining interest.

Harnessing Temporal Dynamics: Advanced Reasoning using Temporal Knowledge Graphs

Integrating temporal data into static knowledge graphs

 Author

Amanda Kau

 (ORCID:


 0009–0004–4949–9284


 )

Introduction Knowledge graphs (KGs) have proven to be an effective method of data representation that is increasingly popular. In KGs, entities and concepts are represented as nodes, while the relationships between nodes are depicted as edges.

Dynamic Knowledge Graphs: A Next Step For Data Representation?

Understanding the Balance between Internal Knowledge and External Sources

Author Qingqin Fang (

 ORCID:

0009–0003–5348–4264) Introduction Previous research often emphasized the limitations of LLM’s information acquisition pathways, focusing on enhancing its capabilities in this regard.

When RAG and LLM Conflict: Who Will AI Listen to?

Exploring the Boundaries of Creativity and Responsibility in the Age of AI-Driven Media

 Author

Vaibhav Khobragade (

 ORCID:

0009–0009–8807–5982)

 Introduction

In 2024, the discipline of Generative AI takes a big step forward with the launch of revolutionary models that convert text into dynamic films, altering the landscape of digital content creation.

Generative AI’s Leap into Video in 2024 and its Ethical Horizon

Author  Amir Aryani: (ORCID: 0000-0002-4259-9774) Definition   A research collaboration network is a group of researchers, and practitioners, or both, working together on joint research activities. These networks often span across disciplines, geographic boundaries, and sectors, enabling participants to share resources, expertise, and data to address common research goals more effectively than they could individually.

Research Collaboration Network

Understanding Sequential Data Modelling with Keras for Time Series Prediction

 Author

Wenyi Pi (

 ORCID

: 0009–0002–2884–2771) Introduction Recurrent Neural Networks (RNNs) are a special type of neural networks that are suitable for learning representations of sequential data like text in Natural Language Processing (NLP). We will walk through a complete example of using RNNs for time series prediction, covering

Beginner’s Guide to Recurrent Neural Networks (RNNs) with Keras

Incorporating Knowledge Graphs to explain reasoning processes


 Author

Amanda Kau (

 ORCID:

0009–0004–4949–9284) Introduction Large language models (LLMs) like GPT-4 possess remarkable language abilities, allowing them to function as chatbots, translators, and much more.

Combining Knowledge Graphs With Language Models for Interpretability

Latest findings in multiple research directions for handling graph prediction and optimization Author · Xuzeng He (

 ORCID:

0009–0005–7317–7426) A graph, in short, is a description of items linked by relations, where the items of a graph are called

 nodes

(or vertices) and their relations are called

 edges

(or links). Examples of graphs can include social networks (e.g. Instagram) or knowledge

Recent Advances in using Machine Learning with Graphs

Prompt Engineering — Part 2


 Using intelligence to use artificial Intelligence: A deep dive into Prompt Engineering

Author Dhruv Gupta

 (ORCID:

0009–0004–7109–5403

 )

Introduction In the previous article we discussed what prompt engineering and some of the techniques used for prompt engineering.

Prompt Engineering — Part 2

Using Mistral for Data tagging Author · Xuzeng He (

 ORCID:

0009–0005–7317–7426) Introduction Data tagging, in simple terms, is the process of assigning labels or tags to your data so that they are easier to retrieve or analyse.

How to use Large Language Models to tag your data: A complete tutorial

Ministral — The World’s Best Edge Language Model
 


 Revolutionising On-Device AI: High-Performance, Low-Resource Language Models for Edge Computing


 Author

Tarun Krishnan (

 ORCID

: 0009–0006–6647–127X)

 Introduction

In recent years, there’s been a notable shift in the AI landscape, with many companies moving away from developing massive,

Ministral — The World’s Best Edge Language Model

Author: Vaibhav Khobragade (

 ORCID:

0009–0009–8807–5982) Introduction Large language models (LLMs) are becoming increasingly popular in natural language processing for their superior competence in various applications.

Enhancing Language Models: The Role of Knowledge Graph Augmentation in Overcoming LLM Challenges

An Introduction to RA-CM3, MuRAG and RACE Author  Xuzeng He (ORCID: 0009-0005-7317-7426)  Generative Artificial Intelligence (GAI) has demonstrated impressive performances in tasks such as text generation and text-to-image generation.

Recent Advances in using Retrieving Multimodal Information for Augmented Generation

Understanding Knowledge Networks From A Graph Perspective


 Author:


 Amanda Kau (ORCID:


 0009–0004–4949–9284


 )

Since 2020, over ten million scholarly articles have been published annually. To put that into perspective, say all ten million articles were released on the first day of the year.

Uncovering The Secrets Behind The Most Influential Scholarly Publications With AceMap

Latest effort in assessing the security of the code generated by large language models Author · Xuzeng He (

 ORCID:

0009–0005–7317–7426) Introduction With the surge of Large Language Models (LLMs) nowadays, there is a rising trend among developers to use Large Language Models to assist their daily code writing. Famous products include GitHub Copilot or simply ChatGPT.

Large Language Models for Code Writing: Security Assessment

Harvesting the Power and Knowledge of Large Language Models


 Author

Amanda Kau

 (ORCID:

0009–0004–4949–9284

 )

Introduction Knowledge Graphs are networks that represent data in a graphical format. The beauty of Knowledge Graphs lies in their representation of concepts, events and entities as nodes, and the relationships between them as edges.

Automated Knowledge Graph Construction with Large Language Models

Understanding how RNNs work and its applications


 Author

Wenyi Pi (

 ORCID

: 0009–0002–2884–2771) Introduction In the ever-evolving landscape of artificial intelligence (AI), bridging the gap between humans and machines has seen remarkable progress. Researchers and enthusiasts alike have tirelessly worked across numerous aspects of this field, bringing about amazing advancements.

An Introduction to Recurrent Neural Networks (RNNs)

Latest findings for the use of Knowledge Graph in the field of QA in multiple research directions Author: Xuzeng He (

 ORCID:

0009–0005–7317–7426) Question Answering (QA), the ability to interact with data using natural language questions and obtaining accurate results, has been a long-standing challenge in computer science dating back to the 1960s.

Question Answering enhanced by Knowledge Graph

Latest findings in pre-training graphs and using them for link recommendation Author · Xuzeng He (

 ORCID:

0009–0005–7317–7426) Introduction A graph, in short, is a description of items linked by relations, where the items of a graph are called nodes (or vertices) and their relations are called edges (or links). Examples of graphs can include social networks (e.g. Instagram) or knowledge graphs (e.g. Wikipedia). In Instagram

Working with Graphs: Pre-training and Application

Anthropic’s Groundbreaking AI, Claude 3.5, Uses Computers Like a Human and Becomes a Game-Changer in Automation


 Author

Zijian Yang (

 ORCID:

0009–0006–8301–7634)

 Introduction

Claude 3.5 Receives a Major Upgrade Overnight! As anticipated, Anthropic AI made a significant move this week with the launch of Claude 3.5 Haiku.

New Claude 3.5 Can Control Computer: Outsmarts o1 in Coding and Redefines Agent Capabilities

Solutions to Enhance LLM Performance in Long Contexts Author · Qingqin Fang (

 ORCID:

0009–0003–5348–4264) Introduction In the era of AI breakthroughs, large language models (LLMs) are not just advancements; they are revolutions, transforming how we interact with technology, from casual conversations with chatbots to the intricate mechanisms behind sophisticated data analysis tools.

Navigating the Long Context Conundrum: Challenges in Language Models’ Information Processing

Supervised Fine-tuning, Reinforcement Learning from Human Feedback and the latest SteerLM Author · Xuzeng He (

 ORCID:

0009–0005–7317–7426) Introduction Large Language Models (LLMs), usually trained with extensive text data, can demonstrate remarkable capabilities in handling various tasks with state-of-the-art performance. However, people nowadays typically want something more personalised instead of a general solution.

Fine-tuning Large Language Models: A Brief Introduction

How Apple’s Research Exposes AI’s Inability to Reason and OpenAI Highlights ChatGPT’s Name-Based Biases


 Author

Zijian Yang (

 ORCID:

0009–0006–8301–7634)

 Introduction

As artificial intelligence continues to evolve, the capabilities and limitations of large language models (LLMs) are under increasing scrutiny.

ChatGPT’s Name Bias and Apple’s Findings on AI’s Lack of Reasoning: Major Flaws Revealed

Working Examples


 Author

Mingrui Gao (

 ORCID

: 0009–0005–7271–2677)

 Introduction

In the fast-paced world of artificial intelligence, a new platform is gaining attention by making AI-powered content creation more accessible.

What is Glif?

Stability AI’s latest release offering New Models and Features


 Author

Tohfa Siddika Barbhuiya (

 ORCID

: 0009–0007–2976–4601)

 Stable Diffusion 3.5

by

 Stability AI

marks a major step forward in AI-driven image generation.

Stable Diffusion 3.5

Research Graph

Google’s Groundbreaking AI Model Explained

Introduction In the rapidly evolving landscape of artificial intelligence, Google continues to stand at the forefront, consistently pushing the boundaries of what these technologies can achieve. One of their latest advancements, GEMMA2, represents a significant leap in AI capabilities. Let’s delve into the details of this new AI model by Google.

What is Gemma2?

Enhancing Open-Domain Conversational Question Answering with Knowledge-Enhanced Models and Knowledge Graphs


 How knowledge-enhanced language models and knowledge graphs are advancing open-domain conversational question answering

Author:

 Wenyi Pi (ORCID:


 0009-0002-2884-2771


 )

When searching for information on the website, it is common to come across a flood of

Enhancing Open-Domain Conversational Question Answering with Knowledge-Enhanced Models and…

Refining AI Vision: How Retrieval-Augmented Generation Transforms Image Captioning in Large Language Models   Leveraging External Knowledge to Enhance the Descriptive Capabilities of AI Systems Author  Vaibhav Khobragade (ORCID: 0009–0009–8807–5982) Introduction   Large Language Models (LLMs) are artificial intelligence models that are trained on massive amounts of text data in order to generate human-like language and produce coherent

Refining AI Vision: How Retrieval-Augmented Generation Transforms Image Captioning in Large…

An Introduction to Retrieval Augmented Generation (RAG) and Knowledge Graph

Author Qingqin Fang (ORCID: 0009–0003–5348–4264)

 Introduction

Large Language Models (LLMs) have transformed the landscape of natural language processing, demonstrating exceptional proficiency in generating text that closely resembles human language.

Hallucination in Large Language Models and Two Effective Alleviation Pathways

Stories by Research Graph on Medium

#### Neo4j APOC Library Use Case

<figure>
<img src="https://cdn-images-1.medium.com/max/978/0*rIcW439yt0M1I_TQ" />
<figcaption>Image created in <a
href="https://www.canva.com/">https://www.canva.com/</a></figcaption>
</figure>

### **Author**

- Wenyi Pi (**ORCID:**
 [0009--0002--2884--277](https://orcid.org/0009-0002-2884-2771))

### **Introduction**

In the realm of Neo4j, the APOC (Awesome Procedures on Cypher) library
stands as a powerful tool. Previously, We have talked about the
importance of APOC in optimising Cypher queries and improving query
efficiency in our article [Exploring Methods of Cypher Query
Optimisations](https://medium.com/@researchgraph/exploring-methods-of-cypher-query-optimisations-7b03e08b24c4).
This article delves deeper into some important functions available
within the APOC library.

Developed as a core library supported by Neo4j, APOC serves as a
standard utility library, offering access to various common procedures
and functions. Beyond simply improving query efficiency, APOC extends
Cypher queries' scope into broader areas such as data integration, graph
algorithms, and data conversion.

### **Installation**

1. Neo4j Desktop

after creating a Project and a DBMS(Database Management System), click
on the DBMS and you will find the **Plugins** tab. Look for the
**APOC **tab

<figure>
<img
src="https://cdn-images-1.medium.com/max/1000/0*B0JC1RggnURFLJnO" />
</figure>

Then click on APOC to expand more and click the install button

<figure>
<img src="https://cdn-images-1.medium.com/max/692/0*VZazDX5Y7UllMOQ4" />
</figure>

2\. Neo4j Server

APOC depends on the internal API for Neo4j. In Neo4j, you need to use
the **matching APOC version** to ensure that the first two version
numbers between Neo4j and APOC match.

<figure>
<img src="https://cdn-images-1.medium.com/max/924/0*GXKgOzgnfw1uE_kG" />
</figure>

Choose the right version and install.

For more details, please check the [APOC
Installation](https://neo4j.com/labs/apoc/4.1/installation/?utm_source=Google&utm_medium=PaidSearch&utm_campaign=Evergreenutm_content=APAC-Search-SEMCE-DSA-None-SEM-SEM-NonABM&utm_term=&utm_adgroup=DSA-use-cases&gad_source=1&gclid=Cj0KCQjwqdqvBhCPARIsANrmZhNexhzMDuQzOnqxnhd9EluIJm1SCZsVDgw1UCTZTHPeU8_uA63GVpcaAgQDEALw_wcB)
documentation.

### **Common features**

With over 450 standard procedures, APOC provides rich functionality
covering utilities, conversions, graph updates, and more. These
procedures are well-supported and highly deployable, whether used as
separate functions or integrated into Cypher queries.

You can find an introduction guide in [APOC User
Guide](https://neo4j.com/docs/apoc/current/) documentation

#### **Import and export**

The APOC library supports importing various data formats including JSON,
HTML, XML, CSV, and XLS to the Neo4j database. It also supports
exporting data into various data formats, including JSON, CSV, GraphML,
Excel, Gephi, and Cypher script.

#### **Data integration**

The APOC library supports integration with other databases, including
relational databases (via JDBC ***apoc.load.jdbc***), MongoDB, Elastic,
and Couchbase. It also supports importing data from LDAP directories
(via ***apoc.load.ldap***) and executing queries against other Neo4j
databases such as bolt procedures via bolt protocol. It also allows for
database modelling (via ***apoc.model.jdbc***) to extract metadata
information by any JDBC compatible database.

#### **Data structure**

The APOC library provides functions and procedures for operating data
structures, which are mainly divided into three types, namely Conversion
Functions, Map Functions, and Collection Functions. The conversion
function is used to cast the "Any" value to a specific type, it is
mainly located under the ***apoc.convert*** package.

The mapping function is used to operate the map type, it mainly resides
in the ***apoc.map*** package. The collection function is used to
operate collections and lists, mainly under the ***apoc.coll*** package.

#### **Temporal (Date Time)**

APOC library adds support for formatting time types, timestamps, and
date string values, mainly under the ***apoc.temporal*** and
***apoc.date*** packages.

#### **Mathematical**

APOC provides functions and procedures for mathematical operations,
including math functions (including rounding, maximum and minimum
values, etc.), exact math, number format conversion functions, and
bitwise operation functions. The mathematical operation function is
mainly located in the ***apoc.math*** package, the exact math
calculation function is located in the ***apoc.number.exact*** package,
the number format conversion function is located in the
***apoc.number*** package, and the bitwise operation is located in the
***apoc.bitwise*** package

#### **Advanced Graph Querying**

The advanced graph query provided by APOC library includes: path
expander (***apoc.path****)*, neighbour function (***apoc.neighbors***),
path manipulation (***apoc.path****)*, relationship querying
(***apoc.rel****)*, node querying (***apoc.nodes***), parallel node
search (***apoc.search****)*, etc.

#### **Cypher Execution**

- **Running Cypher fragments**: provide a safe, graph-aware, partially
 compiled scripting Cypher language within APOC (***apoc.cypher***)
- **Conditional Cypher Execution**: simulate an if / else structure.
- **Timeboxed Cypher statements**: terminate a cypher statement with a
 given threshold.
- **Run multiple Statements**: run each semicolon separated statement
- **Run Cypher Script Files**: run each statement in the file / each
 file, separated by semicolons
- **Parallel Cypher Execution**: provide parallel execution of Cypher
 statements

### **Examples**

The APOC library showcases its adaptability and effectiveness in real
world application. From node and relationship creation to batch
transactions, APOC offers indispensable functionalities for optimising
workflows and maximising efficiency.

#### **Help Command**

To access the APOC supported procedures and functions：

 call apoc.help('apoc')

#### **Create Nodes and Relationships**

1. Use ***apoc.create*** to create nodes.

- Create a node with dynamic labels:

**apoc.create.node**(\['Label'\], {key:value,...​})

- For example:



 CALL apoc.create.node(["Person", "Actor"], {name: "Tom Hanks"});

<figure>
<img src="https://cdn-images-1.medium.com/max/610/0*Z00M16_STJWDA15s" />
<figcaption>Create a Node Result</figcaption>
</figure>

This will create a **Node** with **Label** "*Person*" and "*Actor*",
**Attribute** "*name*" : "*Tom Hanks*".

- Create multiple node with dynamic labels:

**apoc.create.nodes**(\['Label'\],
\[{key:value,...​},{key:value,...}...\])

2\. Use ***apoc.create.relationship*** to create relationships.

- Create relationship with dynamic rel-type:

**apoc.create.relationship**(person1,'KNOWS',{key:value,...​}, person2)

- For example:



 MATCH (p:Person {name: "Tom Hanks"})
 MATCH (m:Movie {title:"You've Got Mail"})
 CALL apoc.create.relationship(p, "ACTED_IN", {roles:['Joe Fox']}, m)
 YIELD rel
 RETURN rel;

<figure>
<img src="https://cdn-images-1.medium.com/max/692/0*X7y8TtzArKlpjnPU" />
<figcaption>Create Relationship Result</figcaption>
</figure>

This will create a relationship of type "**ACTED_IN**" between the node
representing Tom Hanks (matched as a **Person** node with the name "*Tom
Hanks*") and the movie "*You've Got Mail*" (matched as a **Movie** node
with the title "*You've Got Mail"*). This relationship means that *Tom
Hanks* acted in the movie "*You've Got Mail*" and played the role of
"*Joe Fox*".

#### **Merge Nodes and Relationships**

1. Use ***apoc.merge*** to create nodes.

- Merge nodes with dynamic labels:

**apoc.merge.node**(\['Label'\], identProps:{key:value, ...​},
onCreateProps:{key:value,...​}, onMatchProps:{key:value,...​}})

- For example:



 CALL apoc.merge.node(
 ["Person", "Actor"],
 {name: "Tom Hanks"},
 {created: datetime()},
 {lastSeen: datetime()}
 );

<figure>
<img
src="https://cdn-images-1.medium.com/max/1000/0*Nqo_IDU3GnMsPkX2" />
<figcaption>Merge Result to Create node</figcaption>
</figure>

This will merge an existing node labelled as "*Person*" and "*Actor*"
with the name "*Tom Hanks*" and add properties created and lastseen time
or create a new node with these labels and properties if one does not
already exist.

2\. Use ***apoc.create.relationship*** to merge relationships.

- Create relationship with dynamic rel-type:

**apoc.merge.relationship**(startNode, relType,
identProps:{key:value, ...​}, onCreateProps:{key:value, ...​}, endNode,
onMatchProps:{key:value, ...​})

- For example:



 MATCH (p:Person {name: "Tom Hanks"})
 MATCH (m:Movie {title:"You've Got Mail"})
 CALL apoc.merge.relationship(p, "ACTED_IN",
 {roles:['Joe Fox']},
 {created: datetime()},
 m,
 {lastSeen: datetime()}
 )
 YIELD rel
 RETURN rel;

<figure>
<img src="https://cdn-images-1.medium.com/max/888/0*Uod7ExxBNvpqMfnE" />
</figure>

<figure>
<img src="https://cdn-images-1.medium.com/max/570/0*Mt_1DFB0GdmCFVBi" />
<figcaption>Merge Result with added properties</figcaption>
</figure>

This will merge a relationship between the node representing *Tom Hanks*
and the movie "*You've Got Mail*" with the relationship type
"**ACTED_IN**'' and the role "*Joe Fox* '', adding properties created
and lastseen time.

3\. Use ***apoc.refactor.mergeNodes***

- Merge nodes and relationships together:

**apoc.refactor.mergeNodes**(nodes LIST\<NODE\>, config MAP\<STRING,
ANY\>)

\- Merges the given **LIST\<NODE\>** onto the first **NODE** in the
**LIST\<NODE\>**. All **RELATIONSHIP** values are merged onto that
**NODE** as well.

Supported config properties:

- **Discard**: If a node's property is already set, no changes are made.
 If the node's property is not set yet, the first property in the list
 is written.
- **Override / Overwrite**: The last property in the list is written
 regardless of whether the node's property is already set, overriding
 any existing value.
- **Combine**: If there is only one property in the list, it is set as
 the node's property. If there are multiple properties in the list, an
 array is created, and an attempt is made to combine these values
 together. This may involve value transformation or type coercion.
- **mergeRels**: This parameter controls whether to allow merging
 relationships with the same type and direction. If set to true,
 relationships with the same type and direction will be merged. If set
 to false, these relationships will not be merged.
- **produceSelfRel:** If set to true (default value), any new
 self-relationship will be inserted into the target node. If set to
 false, no new self-relationship will be inserted. Note that this
 parameter is independent of the **mergeRels** configuration and does
 not affect existing self-relationships.
- **preserveExistingSelfRels**: This parameter is only effective when
 mergeRels is set to true. If set to true (default value), existing
 self-relationships in the target node will be preserved; otherwise,
 they will be deleted.
- **singleElementAsArray**: If set to false (default value) and the type
 is combine, setting to true ensures that the result remains as an
 array when merging two arrays, while setting to false makes the result
 a single value when the array size is 1.

#### **Batch Transactions**

1. Use ***apoc.periodic*** to perform periodic or batch operations.

- Run the second statement for each item returned by the first
 statement:

**apoc.periodic.iterate**('statement returning items', 'statement per
item',
{batchSize:1000,iterateList:true,parallel:false,params:{},concurrency:50,retries:0})
YIELD batches, total

- For example:



 CALL apoc.periodic.iterate(
 "MATCH (p:Person) WHERE (p)-[:ACTED_IN]->() RETURN p",
 "SET p:Actor",
 {batchSize:10000, parallel:true})

This will iterate over batches of nodes labelled as "*Person*" who have
acted in any movie, adding the label "*Actor*" to each node in batches
of 10,000 nodes and processing them in parallel.

2\. Use ***apoc.periodic.commit*** to execute a write operation.

- runs the given statement in separate transactions until it returns 0:

**apoc.periodic.commit**(statement,params)

- For example:



 CALL apoc.periodic.commit(
 "MATCH (person:Person)
 WHERE exists(person.city)
 WHERE person limit $limit
 MERGE (person:City {name:person.city})
 MERGE (person)-[:LIVES_IN]->(city)
 REMOVE person.city
 RETURN count(*)",
 {limit:1000});

This will merge a **City** node for each **Person** node with a city
property, create a **LIVES_IN** relationship, remove the city property
from each **Person** node, and return the count of processed nodes,
executed in batches of 1000 nodes until completion.

### **Practical Use Case**

I will use the APOC library to merge duplicate nodes.

Firstly create nodes and relationships:

 CALL apoc.create.nodes(["Dataset"], [{doi:'10.1001/965111',key:'orcid/001',title:'Environmental Impact on Agriculture',source:'orcid.org'},{doi:'10.1001/965111',key:'orcid/002',title:'Environmental Impact on Agriculture',source:'orcid.org'},{doi:'10.1001/965111',key:'orcid/003',title:'Environmental Impact on Agriculture',source:'orcid.org'}]);
 CALL apoc.create.node(["Researcher"], {name: "Amy Jamison"});
 CALL apoc.create.node(["Publication"], {title: "Environment"});
 CALL apoc.create.node(["Grant"], {title: "Research Institution"});

 MATCH (d1:Dataset {key:'orcid/001'})
 MATCH (g:Grant {title: "Research Institution"})
 CALL apoc.create.relationship(d1, "HAS", null, g)
 YIELD rel
 RETURN rel;

 MATCH (d2:Dataset {key:'orcid/002'})
 MATCH (g:Grant {title: "Research Institution"})
 CALL apoc.create.relationship(d2, "HAS", null, g)
 YIELD rel
 RETURN rel;

 MATCH (d3:Dataset {key:'orcid/003'})
 MATCH (g:Grant {title: "Research Institution"})
 CALL apoc.create.relationship(d3, "HAS", null, g)
 YIELD rel
 RETURN rel;

 MATCH (p:Publication {title: "Environment"})
 MATCH (d1:Dataset {key:'orcid/001'})
 CALL apoc.create.relationship(p, "PUBLICATED", null, d1)
 YIELD rel
 RETURN rel;

 MATCH (p:Publication {title: "Environment"})
 MATCH (d2:Dataset {key:'orcid/002'})
 CALL apoc.create.relationship(p, "PUBLICATED", null, d2)
 YIELD rel
 RETURN rel;

 MATCH (p:Publication {title: "Environment"})
 MATCH (d3:Dataset {key:'orcid/003'})
 CALL apoc.create.relationship(p, "PUBLICATED", null, d3)
 YIELD rel
 RETURN rel;

 MATCH (r:Researcher {name: "Amy Jamison"})
 MATCH (d1:Dataset {key:'orcid/001'})
 CALL apoc.create.relationship(r, "OWNED", null, d1)
 YIELD rel
 RETURN rel;

 MATCH (r:Researcher {name: "Amy Jamison"})
 MATCH (d2:Dataset {key:'orcid/002'})
 CALL apoc.create.relationship(r, "OWNED", null, d2)
 YIELD rel
 RETURN rel;

 MATCH (r:Researcher {name: "Amy Jamison"})
 MATCH (d3:Dataset {key:'orcid/003'})
 CALL apoc.create.relationship(r, "OWNED", null, d3)
 YIELD rel
 RETURN rel;

This creates six nodes with three **Dataset** nodes having the same
**doi**, title, and source but different key, along with one
**Researcher**, one **Publication**, and one **Grant** node, and
establishes nine relationships between them.

<figure>
<img
src="https://cdn-images-1.medium.com/max/1000/0*o8xNhjMjJ_des8og" />
<figcaption>Create Node and Relationship</figcaption>
</figure>

Then use the ***apoc.refactor.mergeNodes*** to merge the duplicate
nodes:

 MATCH (n:Dataset)
 WITH n.doi AS doi, collect(n) as nodes
 CALL apoc.refactor.mergeNodes(nodes, {properties: {
 title:'combine',
 source:'combine',
 key:'combine',
 `.*`: 'discard'
 },mergeRels:TRUE})
 YIELD node
 RETURN node

This merges nodes based on their **doi** property while combining
specified properties and discarding all other properties. Any
relationships associated with the merged nodes will also be merged

<figure>
<img
src="https://cdn-images-1.medium.com/max/1000/0*fcozFqWDrTlWJHy2" />
<figcaption>Merge Node and Relationship</figcaption>
</figure>

<figure>
<img
src="https://cdn-images-1.medium.com/max/1000/0*YCa-tZ6IjqgnrsI2" />
<figcaption>Merge table</figcaption>
</figure>

Since I set the key attribute property as combine, that if multiple
nodes being merged have different values for the key property, those
values will be combined into an array and as set **mergeRels** to true
that relationships of the same type and direction will be merged.

If **mergeRels** not set to *True*, the result is like this:

<figure>
<img
src="https://cdn-images-1.medium.com/max/1000/0*0_uNfqOYUD_rbUtZ" />
<figcaption>Merge Result without mergeRels</figcaption>
</figure>

### **Conclusion**

In summary, the APOC library is the cornerstone of Neo4j users, whether
optimising queries, integrating data sources, or performing advanced
graphical analysis. APOC is an important asset in every Neo4j
practitioner's toolkit. It greatly simplifies the development process
and saves a lot of time and effort, providing users with more
flexibility and scalability.

### **References**

- APOC User Guide for neo4j 5 --- APOC documentation (2024) Neo4j Graph
 Data Platform. Available at: <https://neo4j.com/docs/apoc/current/>
- Introduction --- APOC documentation (2024) Neo4j Graph Data Platform.
 Available at: <https://neo4j.com/docs/apoc/current/introduction/>
- Neo4j-contrib (2024) NEO4J-contrib/NEO4J-APOC-procedures: Awesome
 procedures on Cypher for Neo4j --- codenamed 'APOC' . Available at:
 <https://github.com/neo4j-contrib/neo4j-apoc-procedures>.
- Merge nodes --- APOC documentation (2024) Neo4j Graph Data Platform.
 Available at:
 <https://neo4j.com/docs/apoc/current/graph-refactoring/merge-nodes/#_examples> .

![](https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=dab999c490b8){width="1"
height="1"}

Boosting Performance for Knowledge Graphs with Neo4j APOC Library

<figure>
<img
src="https://cdn-images-1.medium.com/max/1000/0*_E8Qac9I9JtIk2bX" />
<figcaption>Image created in <a
href="https://www.canva.com/">https://www.canva.com/</a></figcaption>
</figure>

#### **Author**

- Wenyi Pi (ORCID:
 [0009--0002--2884--2771](https://orcid.org/0009-0002-2884-2771))

### Introduction

A **knowledge graph** (graph database) captures information about main
entities in a domain and the relationships between them. It was an
augmented feature store for connected data which gave access to compute,
access and operationalise structure features. Unlike traditional
databases that use tabular structures, knowledge graph utilise graphs to
organise data into nodes and edges, creating a flexible model. **Neo4j**
is a graph database management system. It embraces a graph-based model,
organising data base nodes, properties and relationships. **Cypher** is
Neo4j's declarative query language to extract useful information from
the knowledge graph. It is like SQL for graphs and was inspired by SQL
so it allows you to focus on what data you want out of the graph.

<figure>
<img
src="https://cdn-images-1.medium.com/max/1000/0*aKhXBjOAOai2mKo_" />
<figcaption>Neo4j graph database. image from
Neo4j website.</figcaption>
</figure>

**Query optimisation** refers to the process of using optimised query
execution to improve database query performance. Simply put, it involves
finding the most efficient way to retrieve data from a database. The
optimisation process includes analysing the query, identifying the most
efficient query and executing the query to retrieve data, therefore
maximising database performance.

Query optimisation is important which has a significant impact on the
database application especially when you have lots of nodes and
relationships in the database. If the query is poor, it can take a long
time to get the data which leads to poor application performance and bad
user experience.

This article aims to explore various ways in which query can be
optimised to perform on the database effectively. It will particularly
focus on the APOC methods and delve into its relevant use case.

### **Background**

#### The lifecycle of a Cypher query

<figure>
<img src="https://cdn-images-1.medium.com/max/976/0*lcjHldBz3D2JbIPh" />
<figcaption>Cypher Query lifecycle. Image from Neo4j,2024 <a
href="https://neo4j.com/docs/cypher-manual/current/planning-and-tuning/execution-plans/">https://neo4j.com/docs/cypher-manual/current/planning-and-tuning/execution-plans/</a></figcaption>
</figure>

A Cypher query starts as a declarative query string which describes the
graph pattern to match in the database. The query string goes through
parsing and rewriting processes. During parsing, the query is broken
down into its constituent parts and validated syntactically. Rewriting
involves optimisations or transformations to the query for efficiency or
correctness. Then the parsed and rewritten query string passes through
the query optimizer (planner) which will produce an optimal plan
(logical plan) in the given current database state. Finally, the logical
plan is turned into a physical plan which specifies the actual
operations and steps that will be executed by the database to retrieve
the data and get the results.

Three things to help understanding Cypher execution:

1. Neo4j database maps the data files from disk to the Page Cache. When
 you execute a query and the data is not in Cache the data will be
 loaded from disk. Query in page cache is faster compared to query
 in disk.
2. When Cypher receives a query, it will compile an execution plan that
 is stored in the Query Cache which will be reused when the same
 query is executed again. However, if the cache exceeds its limits or
 if the data in the database has changed significantly, the plan will
 be removed from the cache.
3. Query runned the first time will be slower than the second time.

Four factors that may slow down query performance:

1. Big results sets: when a query returns a lot of data, it will take
 longer time to finish.
2. Locking: database places locks on nodes and relationships when
 change node values or relationships. when queries writing on the
 same node/relationship, they need to wait for other writes to
 complete.
3. Query load: query load may also be slow if the server has too many
 queries to process at the same time because they have to wait for
 cpu-resources execution.
4. Turning queries: Queries may be slow because the Cypher statement is
 not optimal. The goal of query tuning is to get the lowest possible
 amount of db hits.

#### **Ways to optimise the query**

1. **Using parameters:** Constructing a Cypher query for each request
 every time can lead to suboptimal performance. The problem is the
 Neo4j desktop app crashing after around 1500 requests. When a new
 query is sent to the Neo4j database, it needs to be transformed into
 an execution plan. But Neo4j caches the last 1000 queries for reuse
 so if sending a query that is cached, the optimization can be
 skipped. To solve this problem is to make one query with parameters
 and reuse it for multiple requests. Instead of using the Python for
 loop, this method uses Cypher Unwind and the Python f-string with
 Cypher parameters. The new method does not need to empty the
 database or restart it. This means only the first time the query
 needs to be optimised, after that the cached query could be used.
 This method represents a significant improvement. Constructing a new
 query per request proved to be inefficient and problematic. Using
 the backend function in conjunction with the new method, we can
 successfully process more than 5000 requests that previously crashed
 with the old method.
2. **Not have errors in variable names**: If a Cypher query references
 a variable that has not been properly initialised or defined, it can
 lead to unexpected behaviour like scanning the entire node space,
 searching for matches. This can severely impact query performance,
 especially in large databases.
3. **Try to reduce query working set as soon as possible**: The main
 idea involves using queries that are small enough and constant in
 their shape for caching. Thereby, each query can update from a
 single property to a whole subgraph. Some of this methods are
 described here:

- One method is to use the UNWIND method that turns a batch of data into
 individual rows to achieve this. We can use it to create nodes with
 properties, to merge nodes with properties and lookup relationships.
 For the lookup, we can lookup by id and use a map format to put in the
 id where keys are nodes or relationship-ids. This is more compact and
 faster for id lookup.
- We can also use FOREACH which is used to iterate over all items and
 execute updates for each of them. This can help create data
 dynamically based on inputs.
- Another method is utilising the APOC procedures. The APOC procedure
 library has lots of useful applications, including creating nodes or
 relationships with dynamic labels and properties, batched transactions
 or iteration of updates, functions for creating and manipulating maps
 to be set as properties.

### **Use case of using APOC**

#### Introduction to APOC

APOC library consists of about 450 procedures and it is widely used in
various areas like data integration, graph algorithms or data
conversion.

For apoc library installation: [APOC
Installation](https://neo4j.com/labs/apoc/4.1/installation/?utm_source=Google&utm_medium=PaidSearch&utm_campaign=Evergreenutm_content=APAC-Search-SEMCE-DSA-None-SEM-SEM-NonABM&utm_term=&utm_adgroup=DSA-use-cases&gad_source=1&gclid=Cj0KCQjwqdqvBhCPARIsANrmZhNexhzMDuQzOnqxnhd9EluIJm1SCZsVDgw1UCTZTHPeU8_uA63GVpcaAgQDEALw_wcB)

An introduction guide to: [APOC
User Guide](https://neo4j.com/docs/apoc/current/)

There are some built in procedures in APOC:

<figure>
<img
src="https://cdn-images-1.medium.com/max/1000/0*iBGBeK9wvFr3PNuQ" />
<figcaption>APOC Built in procedures. Source APOC
documentation.</figcaption>
</figure>

I will focus on the periodic method of APOC, built in periodic
procedures of APOC:

<figure>
<img
src="https://cdn-images-1.medium.com/max/1000/0*--BzyROb9Y6nPOvd" />
<figcaption>APOC Built in Periodic procedures. Source APOC
documentation.</figcaption>
</figure>

#### Efficiently Updating and Inserting Data With apoc.periodic.iterate {#efficiently-updating-and-inserting-data-with-apoc.periodic.iterate}

Understand the Cypher query (create 100000 person node)

*Cypher query to create Person:*

 CALL apoc.periodic.iterate(
 "UNWIND range(1,100000) as id RETURN id",
 "CREATE(p:Person{id:id})",
 {batchSize:10000, iterateList:true,parallel:true})

The first statement is the input that is worked on in the second
statement, the second statement is doing the work like updating the
graph, changing the graph or removing things from the graph. "Batch
size" means size of transactions, "iterate list" indicates whether each
batch is executed as a single Cypher transaction or not, "parallel"
means whether to enable parallel execution of batches or not.

To analyse the query result, I will use the PROFILE method which will
execute the query and return results. This can help keep track of how
many rows pass through each operator, and how much each operator needs
to interact with the storage layer and retrieve the necessary data. To
use the PROFILE method in Cypher, simply put a PROFILE word in front of
the query.

Compare the execute time using original method and apoc procedure:

We can find the execution time of APOC is less compared with
old methods.

<figure>
<img
src="https://cdn-images-1.medium.com/max/1000/0*PcAvZNG8pGVkvzYQ" />
<figcaption>Cypher query result with unwind.</figcaption>
</figure>

<figure>
<img
src="https://cdn-images-1.medium.com/max/1000/0*qjOtanFc206ZxFHc" />
<figcaption>Cypher query result with APOC
and Unwind.</figcaption>
</figure>

<figure>
<img
src="https://cdn-images-1.medium.com/max/887/1*3iyOX-SFTICEK2KrpP73pQ.png" />
<figcaption>Execution plan</figcaption>
</figure>

<figure>
<img
src="https://cdn-images-1.medium.com/max/1000/0*LUGSKhfUr_ToJhx0" />
<figcaption>Cypher query result with APOC
and match.</figcaption>
</figure>

<figure>
<img src="https://cdn-images-1.medium.com/max/410/0*jRJAxNb3B9wHLS_s" />
<figcaption>Cypher query result with match.</figcaption>
</figure>

<figure>
<img
src="https://cdn-images-1.medium.com/max/1024/1*skIXdiwKru48d1kKHYPI6g.png" />
<figcaption>Execution plan.</figcaption>
</figure>

The Estimated Rows column details the number of rows that are expected
to be produced by each operator. They are calculated or estimated from
graph statistics and are usually important for the query planner when
formulating and comparing plans. DB hits stand for the work of storage
when trying to get data from the Neo4j database.The main metric
considered is db hits. Execution time is important but that is generally
a result of administrative factors, like bandwidth, memory, and traffic
volume. From these examples, We can see that the APOC method is better
as it has less db hits.

### **Conclusion**

In conclusion, optimising Cypher queries is crucial for improving
database performance, especially in scenarios with large datasets.
Through careful analysis and implementation of optimisation techniques,
we can enhance the efficiency of database applications.

#### **References**

- Apoc.periodic.iterate --- APOC extended documentation (no date) Neo4j
 Graph Data Platform. Available at:
 <https://neo4j.com/labs/apoc/4.3/overview/apoc.periodic/apoc.periodic.iterate/>
- *Basic query tuning example --- cypher manual* (no date) *Neo4j Graph
 Data Platform*. Available at:
 <https://neo4j.com/docs/cypher-manual/current/appendix/tutorials/basic-query-tuning/>
- *Execution plans and query tuning --- cypher manual* (2024) *Neo4j
 Graph Data Platform*. Available at:
 <https://neo4j.com/docs/cypher-manual/current/planning-and-tuning/>
- Hunger, M. (2020) *5 tips & tricks for fast batched updates of graph
 structures with neo4j and cypher*, *Medium*. Available at:
 <https://medium.com/neo4j/5-tips-tricks-for-fast-batched-updates-of-graph-structures-with-neo4j-and-cypher-73c7f693c8cc>
- Shoukat , M. (2024) *Graph data modeling: Building knowledge graph
 from unstructured data using neo4j*, *LinkedIn*. Available at:
 <https://www.linkedin.com/pulse/graph-data-modeling-building-knowledge-from-unstructured-using-tve0f/?trk=article-ssr-frontend-pulse_more-articles_related-content-card>
- Tom, N*.* (2023) *Optimising cypher query using parameters*, *Graph
 Database & Analytics*. Available at:
 <https://neo4j.com/developer-blog/optimize-cypher-query-parameters/>
- Vegter, K. (2018) *Cypher query optimisations*, *Medium*. Available
 at: <https://medium.com/neo4j/cypher-query-optimisations-fe0539ce2e5c>

![](https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=7b03e08b24c4){width="1"
height="1"}