Exploring RAG Pipelines for Enhanced NLP Applications

Introduction  Haystack, an open-source framework from deepset, is transforming how we build production-ready large language model (LLM) applications, retrieval-augmented generative (RAG) pipelines, and state-of-the-art search systems. It simplifies creating powerful search and question-answering systems that handle large volumes of text with ease. Traditional search systems often struggle with understanding complex natural language queries.

A Technical Guide to Haystack AI

How a 15-Member Startup is Empowering Millions to Turn Imagination into Reality with AI-Driven Visual Content

Introduction  Viggle AI, a startup known for its eponymous video generation service, recently announced the completion of a $19 million early-stage investment, led by Andreessen Horowitz. The company’s founder and CEO, Chu Hang has worked at Google, NVIDIA, Facebook, and Autodesk. You might not be familiar with Viggle AI, but you’ve probably seen its viral memes online.

Viggle AI Revolutionising Digital Creativity with Controllable Video Generation

Introduction   In today’s competitive market, small business owners need to make quick, informed decisions to stay ahead. Artificial Intelligence (AI) offers powerful tools to analyse data and uncover insights, helping owners understand their businesses’ needs. One such technique, Retrieval-Augmented Generation (RAG), combines data retrieval with natural language generation to provide accurate, context-specific answers.

How AI Helps Business Owners Understand Their Businesses’ Needs Through RAG and Automation

🎮 Introduction: Why Game Asset Creation Is the Hidden Bottleneck in Development Game development is an intricate and deeply creative endeavour—a fusion of

 interactive systems

,

 emotional storytelling

,

 mechanical precision

, and

 visual immersion

. Whether you’re building a cosy farming simulator, a cyberpunk platformer, or an open-world RPG,

 visual

How to Revolutionise Game Asset Creation Using AI Image Generation Models

Introduction  In today’s rapidly evolving AI landscape, conversational agents have become increasingly sophisticated, transitioning from simple text-based interactions to more natural, voice-enabled experiences. This blog post explores how to create an intelligent chatbot that not only understands and responds to text input but also speaks its responses aloud – all without writing a single line of code.

From Text to Talk: Building a Voice-Enabled AI Chatbot with n8n

Introduction  Code generation powered by large language models is reshaping how developers write software. OpenAI’s GPT series and Meta’s open-source Llama 4 are two leading options in this space.

Code Generation: GPT vs Llama 4

Understanding its Capabilities and Design

Introduction  Baidu, a leading Chinese technology has been a significant player in artificial intelligence (AI) since it began developing its Enhanced Representation through Knowledge Integration (ERNIE) models in 2019. On March 16, 2025, Baidu introduced ERNIE X1, a specialised deep-thinking reasoning model, alongside ERNIE 4.5, a multimodal foundation model.

Baidu's ERNIE X1

Reasoning, Coding, and Conversation: Evaluating Claude’s Evolution as a Thinking Partner

Introduction  In February 2025, Anthropic released Claude 3.7 Sonnet as their advanced reasoning model with a unique hybrid approach to AI assistance.

Beyond the Benchmark: A Hands-On Evaluation of Claude 3.7 Sonnet

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

Introduction  Large Language Models (LLMs) have achieved remarkable success. But, they still face significant limitations, especially in domain-specific or knowledge-intensive tasks such as question answering, producing “hallucinations” where the models generate responses that sound plausible but are actually incorrect when handling queries beyond their training data or requiring current information.

Three Paradigms of RAG

How QwQ-32B Is Redefining Efficiency and Reasoning in Open-Source AI

Introduction  In the rapidly evolving field of artificial intelligence, Alibaba’s Qwen team has introduced QwQ-32B, a 32-billion-parameter reasoning model designed to tackle complex tasks such as mathematical problem-solving and coding. Launched in March 2025, QwQ-32B stands out for its compact size and open-source availability, offering performance comparable to much larger models like DeepSeek-R1, which boasts 671 billion parameters.

Exploring QwQ-32B: Alibaba’s Compact Reasoning Model

How to Enhance Disaster Early Warnings with Tech Tools

Introduction Natural disasters have become more frequent and intense, causing significant threats to the society.

 Early-warning systems (EWS)

are critical for mitigating these impacts by providing timely alerts, allowing time for preparation and evacuation. The United Nations’ Early Warnings for All Initiative, launched to ensure every person on Earth is protected by EWS by 2027, tells the urgency of this issue.

AI to the&nbsp;Rescue

This article is based on the paper Contrastive Chain-of-Thought Prompting by Yew Ken Chia and others.

Introduction  In recent years, Large Language Models (LLMs) have demonstrated remarkable performance across a variety of natural language processing tasks. However, their ability to perform complex reasoning remains a key challenge. Unlike humans, who can reason step by step and learn from both correct and incorrect examples, LLMs often struggle with logical consistency and generalisation beyond seen data.

Contrastive Chain of Thought

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

Introduction Imagine accessing premium ChatGPT features — Canvas, internet search, and PDF analysis — completely free of charge. Thanks to Mistral AI’s latest updates to their platform,

 Le Chat

, this is now a reality.

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

Stability AI’s latest release offering New Models and Features

Introducing Stable Diffusion 3.5  Stable Diffusion 3.5 is an open release that includes multiple model variants, each designed for specific use cases. These include Stable Diffusion 3.5 Large, Stable Diffusion 3.5 Large Turbo, and Stable Diffusion 3.5 Medium (to be released on October 29th). These models are designed to run on consumer hardware, providing greater accessibility, flexibility, and performance.

Stable Diffusion 3.5

Introduction  Machine learning has revolutionised countless industries, but deploying ML models remains a significant challenge for many data scientists and developers. The process often involves wrestling with complex dependencies, managing environment configurations, and navigating the intricacies of containerisation. Enter Cog, an open-source tool designed to simplify the packaging and deployment of machine learning models.

What is Cog?

Introduction  In the rapidly evolving landscape of artificial intelligence, developers and businesses face a common challenge: bridging the gap between cutting-edge AI models and practical, real-world applications. As the complexity and computational demands of AI continue to grow, so does the need for efficient, scalable, and user-friendly platforms that can harness the power of these models.

What is Fal AI?

Let’s explore ChatGPT’s Advanced Voice Mode

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. Simply, ChatGPT’s Advanced Voice Mode is a powerful new feature that enables real-time, natural voice interactions.

Unlocking the Power of ChatGPT’s Advanced Voice Mode

Solutions for Text and Visual Intelligence

Introduction  Molmo AI on PixMo Dataset is a state-of-the-art, open-source multimodal model developed by the Allen Institute for AI (Ai2). Designed to rival proprietary models like GPT-4 and Claude, Molmo offers powerful image and text comprehension capabilities at a fraction of the cost and complexity of its competitors.

Molmo AI: Revolutionising Open-Source Multimodal Intelligence

A Step-by-Step Guide to Running Llama 3.2 and Other Large Models on Android Using Ollama

Introduction At the recently concluded Meta Developer Conference, Llama 3.2 made a dazzling debut. This time, not only does it boast

 multimodal capabilities

, but it has also partnered with companies like Arm to launch a “mobile” version optimised specifically for Qualcomm and MediaTek hardware.

How to Run Llama 3.2 on Android Phone

Introduction to Llama 3.2 Llama 3.2 is Meta’s first open-source AI model capable of processing

 both text and images

. This collection ranges from lightweight versions for edge devices to powerful multimodal models capable of sophisticated reasoning tasks.Key Features and Improvements Multimodal Capabilities For the first time in the Llama series, the

 11B and 90B models

support

Llama 3.2: Meta’s Groundbreaking Multimodal AI Model

Swinburne University of Technology

Definition  A research collaboration network is a group of researchers, and practitioners, or both, working together on joint research activities.

Research Collaboration Network

Discover How GPT-4o Mini Balances Power and Efficiency for Everyday AI Tasks

Introduction

 ChatGPT-4o Mini

is a streamlined version of OpenAI’s GPT-4, designed to offer powerful language processing capabilities with lower resource consumption and cost. It was developed in response to the growing demand from small businesses, educational institutions, and individual developers for affordable AI tools.

Introducing GPT-4o Mini: The Future of Lightweight AI Models

Introduction  Flowise is an open-source, low-code tool tailored for developers to build customised orchestration flows and AI agents for Large Language Models (LLMs). It simplifies the development cycle, enabling quick iterations and a smooth transition from testing to production.

How to use Flowise locally

Techniques to integrate Knowledge Graphs into Language Models

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. KGs are instrumental in applications like search engines, evident from Google’s Knowledge Graph. On the other hand, popular PLMs like BERT and GPT excel in a variety of natural language tasks.

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

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?

Improving the performance and application of Large Language Models

Introduction  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. Many of us have since learnt — perhaps when asking ChatGPT a question or employing it to write our reports — that LLMs can hallucinate.

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

Australian National University

Dhruv Gupta

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

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

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

Introduction  Virtual assistants have popped up on numerous websites over the years. These assistants utilise question answering (QA) systems, which are gaining traction as we continue to automate response generation, thereby improving QA applications like search engines and chatbots. As the name implies, QA involves users posing queries to machines which in turn, provide relevant, well-crafted answers.

Harnessing The Power of Knowledge Graphs in Question Answering

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?

This article summarises research from "Tree of Thoughts: Deliberate Problem Solving with Large Language Models" by Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Thomas L. Griffiths, Yuan Cao, and Karthik Narasimhan.

Introduction

Large language models like GPT-4 have become remarkably capable at solving a wide range of problems, but they still face a fundamental limitation: they generate text token by token, making decisions linearly without the ability to explore multiple paths or backtrack when needed.

Tree of Thoughts: A New Way to Unlock Problem-Solving in Large Language Models

Latest findings in multiple research directions for handling graph prediction and optimisation

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). Nowadays, there is a rising trend in the research of using Machine Learning techniques on graphs to solve

Recent Advances in using Machine Learning with Graphs

Evaluating Llama 3.1–405B and GPT-4o Across Key Performance Metrics to Determine the Superior AI Model for Users and Developers.

Introduction To compare the strengths and intelligence of Llama-3.1–405B and GPT-4o from a practical usage perspective, this article designed test cases covering five scenarios:

 mathematics, coding, tool usage, JSON extraction

,

 and creative writing.

We conducted a comparison test between the strongest open-source and closed-source models.

Llama 3.1 405B vs GPT-4o: Which model is better?

Bridging the Gap Between Visuals and Language in AI

Introduction  In today’s digital age, we’re constantly interacting with images and text together — whether it’s scrolling through social media, searching for products online, or using virtual assistants. But have you ever wondered how computers understand the relationship between what we see and what we read?

What is BLIP?

A Step-by-Step Guide to Creating Versatile AI Assistants Using OpenAI’s Assistants API

Introduction  The Assistants API is a powerful new offering that enables developers to integrate AI assistants directly into their applications. These assistants are designed to handle a wide range of user queries by utilising models, tools, and files.

How to Use OpenAI Assistants API to Build Your Own Custom ChatGPT

Introduction  Gorilla is an innovative open-source project that enhances Large Language Models (LLMs) by linking them to a wide range of APIs. This allows LLMs to generate and execute API calls for tasks like creating CLI commands, scheduling meetings, and ordering services. Gorilla features include Open Functions, both local and hosted inference options, and third-party library integration, making it versatile for developers and businesses.

How to use Gorilla on MacOS: A Comprehensive Guide

In the field of Artificial Intelligence, large language models (LLMs) are transforming the landscape of what machines can achieve. These sophisticated models excel at tasks like summarising text, generating human-like content, translating languages, and answering complex questions. However, the computational resources required to run such models can be prohibitive for many individuals and small teams. Let’s enter the world of Google Colab.

Using Google Colab to run LLM Models

A Step-by-Step Guide to try Mistral models

Introduction  Mistral is an open-source large language model (LLM) series developed by Mistral AI, designed to assist with various natural language processing (NLP) tasks. Mistral is renowned for its transparent, portable, customisable, user-friendly, and cost-effective models, which require less computational power when used on local systems.

Running Mistral Models with Hugging Face or Ollama

A Comprehensive Guide to Quick Start and Practical Implementation

Introduction  Dify is an open-source large language model (LLM) application development platform. It combines the concepts of Backend-as-a-Service and LLMOps to enable developers to quickly build production-grade generative AI applications. Even non-technical people can participate in the definition and data operations of AI applications.

Getting Started with Dify: No-Code AI Application Development

Integrating an AI model with Chainlit in your application

Introduction  Chainlit is an open-source, Python-based framework for creating and managing conversational applications. While Chainlit does not include Large Language Models (LLMs) by itself, it provides a variety of convenient tools and interfaces. These enable developers to build complex dialogue systems and seamlessly integrate LLMs into their applications without worrying about the underlying implementation details.

How to use Chainlit

How Diffusion Models Transform AI Image Generation

Introduction  In recent years, artificial intelligence (AI) has made significant advancements in generating images from text descriptions, a capability once thought to be science fiction. Among the various techniques driving this progress, diffusion models have emerged as a particularly powerful approach.

Exploring Diffusion Models

Getting started to join the Hugging Face community

Introduction  The Hugging Face Hub is a collaborative open-source platform that hosts a vast array of models, datasets, and demos for the machine learning community. With its diverse range of accessible models, it caters to various daily work needs.

How to use Hugging Face API

Introduction  Large Language Models (LLMs) have been rapidly adopted across various scenarios due to their versatile capabilities. However, issues such as privacy and security have often been overlooked. For instance, most LLMs require an internet connection to process data, which can expose user information to potential security risks.

Creating a MacOS Chatbot with a Private LLM

Optimal Information Extraction and case study in agriculture

Introduction  Artificial Intelligence (AI) has broken into our lives causing the new industrial revolution in the digital space.

The combined use of Retrieval-Augmented Generation (RAG) and Fine-tuning to improve LLM pipelines

Latest effort to improve the quality of code generated by Large Language Models

Introduction  As Large Language Models (LLMs) are getting more popular than ever these days, 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: Performance Boosting

How Diffusion Models Are Transforming Generative AI and Outshining GANs and VAEs

Introduction

Over the past decade, generative models have advanced significantly. Initially capable of simple tasks like generating digits (0–9), they have progressed to sophisticated capabilities, such as creating a wide range of realistic images of humans and animals, and imaginative depictions like hybrid human-animal forms and beyond.

Diffusion Models: A Comprehensive High-Level Understanding

Meet the General Specialist: Where AI Generalists Harness Specialist Tools for Unmatched Precision

Introduction

Humans are different from other animals because we make and use tools to help us do specific jobs and understand things better. When solving complex real-world challenges, we use a diverse set of tools because problems rarely depend on a single area of expertise.

ChatHuman: Revolutionizing 3D Human Understanding with RAG

Exploring whether OpenAI’s O1 models represent a true breakthrough in AI reasoning or just incremental progress

Introduction  OpenAI’s recently released O1 series models signify a significant step forward in the field of artificial intelligence, particularly in complex reasoning. The O1 model series not only handles more intricate problems but also introduces human-like thought processes, elevating the model’s reasoning capabilities to new heights. In this article, we will delve into the core features of the O1 series models.

How OpenAI’s O1 Series Stands Out Redefining AI Reasoning

Supervised Fine-tuning, Reinforcement Learning from Human Feedback and the latest SteerLM

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. For example, one may want LLMs to assist in code writing while the other may seek models that are specialised in medical knowledge.

Fine-tuning Large Language Models: A Brief Introduction

Introduction  REST APIs are essential for modern web applications, enabling seamless communication between frontend and backend services. Building them from scratch can be time-consuming, but with the right tools, we can streamline the process.

Developing a REST API in Python and Flask Using Cursor Editor and AI

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

How to create a functional documentation assistant without writing code

Introduction  Large Language Models (LLMs) have transformed how we build intelligent applications, but implementing production-ready AI systems often requires navigating complex infrastructure, managing model deployments, and building custom interfaces. Many developers face a challenging choice: use simple but limiting no-code platforms that hide the complexity, or build everything from scratch with code-heavy frameworks.

The 30-Minute Guide to Your First AI Application: Dify.ai + Ollama/ChatGPT on Mac

Qingqin Fang

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

Wenyi Pi

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)

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 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

An introduction to tools supporting PubMed

Introduction 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. PubMed currently includes citations and abstracts from over 5000 life science journals for biomedical articles dating back to 1948.

Enhancing PubMed: from a Medical Database to beyond

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?

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

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

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

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

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)

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

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

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

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

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

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

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

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?

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)

This article explores and analyses the paper "A Survey on In-Context Learning" by Dong et al. (2024)

Introduction In the rapidly evolving field of natural language processing (NLP),

 In-Context Learning (ICL)

has emerged as a transformative capability of large language models (LLMs). The paper

 "A Survey on In-Context Learning"

by Dong et al. (2024) offers a comprehensive exploration of this paradigm, which enables LLMs to adapt to tasks using only a few examples provided in the input prompt [1]. This survey is a

Understanding In-Context Learning

Introduction  In today's data-driven research landscape, the ability to connect, query, and extract insights from interconnected research data is more valuable than ever. In this blog post, we'll explore how to build REST APIs using Flask and Neo4j to expose research network data in an accessible way.

How to use new Research Graph API? Finding Researchers and Organisations

Introduction  In February 2025, xAI unveiled Grok 3, a highly anticipated AI model touted as the “smartest AI in the world” (xAI). Developed to advance scientific discovery and deepen our understanding of the universe, Grok 3 promises superior reasoning, real-time data processing, and versatile applications.

Exploring Grok 3: xAI’s homebrew Artificial Intelligence

Introduction  Vision-enabled AI models have rapidly evolved to become essential tools across numerous applications, from content moderation to image analysis and multimodal reasoning. Cohere's recent entry into this space with their Aya Vision model promises to deliver competitive capabilities in the increasingly crowded market of multimodal AI systems.

Exploring Aya Vision: Cohere's Multimodal Model and Its Comparison with GPT

Seamless image compositing with SDXL and ComfyUI

Introduction  AI-generated images have become an important tool in the design field, but how to naturally merge people into the landscape background to make the picture look realistic and artistic has always been a challenge. From movie special effects to social media content creation, the technology of seamless synthesis is becoming more and more important.

Research Graph

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

What is LLMLingua?

How to use GROBID to extract text from PDF files

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

Mini RAG using Neo4j

Typesense and Neo4j in a hybrid information retrieval solution

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

19 Clustering Techniques