Knowledge Hub

Just like Row is the physical content in a Relational Database, Knowledge Graph (KG) is the physical content in a Graph Database.

Knowledge Graph (KG) integrates closely with Graph Theory, MetaGraph, Taxonomies, and Ontologies, acting as a unifying framework that bridges these concepts.

Let’s decode…..

A Knowledge Graph is a structured representation of knowledge, where entities (nodes) and their relationships (edges) are stored and queried in a graph format.

In a relational database, the schema (tables, columns, constraints) is empty until you populate it with rows (data). Similarly, the Knowledge Graph is the populated version of Graph Theory (structure), MetaGraph (metadata), Taxonomies (classification), and Ontologies (rules).

In Relational Database, Table Orders with columns OrderID, CustomerID, OrderDate having Rows with actual order records.

In Knowledge Graph, Nodes represent Customers and Orders; edges represent Purchases in this way i.e., (Customer: Alice) -[:Purchases {Date: '2023-12-12'}]-> (Order: #12345)

Let’s start here: traditional AI predicts. Agentic AI acts.

Instead of just answering your questions or generating text, Agentic AI can pursue goals, make decisions, use tools, and even coordinate with other agents to get things done. It’s not a passive model waiting for instructions. It’s a collaborator, a kind of digital teammate.

That’s what “agentic” means: having agency. The ability to decide, adapt, and operate with autonomy in a live environment.

So, while older AI models were smart calculators, Agentic AI is more like a strategist who:

• • Understands your goal (not just your prompt)
  • Makes a plan
  • Takes action, sometimes with improvisation
  • Learns and adjusts along the way

How Does It Work?

Most agentic systems follow a process called the Agent Loop:

• 1. Observe: Take in input from users or systems
  2. Plan: Break the goal into steps
  3. Act: Use tools, APIs, or sub-agents to perform tasks
  4. Reflect: Evaluate what worked (or didn’t)
  5. Adjust: Update plan or memory and repeat

Multi-modal data refers to data that comes in multiple formats or modalities. A modality simply means a type or form of data. In traditional systems, most data was structured text or numbers stored in tables. Today, organizations deal with text, images, audio, video, sensor readings, and more. When different types of data are combined and analyzed together, this is called multi-modal data.

For example, a social media post may include written text, an image, location information, and user reactions. Each of these is a different modality. When analyzed together, they provide richer insights than analyzing just one type alone.

Multi-modal data has become especially important in artificial intelligence and machine learning. Modern AI systems are designed to process text, images, speech, and structured data simultaneously. For instance, a customer service system may analyze a voice recording, convert it to text, examine sentiment, and combine it with customer transaction history. This is a multi-modal approach because it uses more than one type of data to understand the situation.

Embeddings are numerical representations of data that capture meaning, context, or relationships in a form that machines can understand. Instead of storing words, images, or other data types as raw symbols, embeddings convert them into vectors, which are lists of numbers.

These numbers are not random. They are generated in a way that preserves relationships. If two words or objects are similar in meaning, their embeddings will be mathematically close to each other in vector space.

In simple terms, embeddings translate meaning into numbers.

Why Embeddings Matter

Computers cannot understand language or images the way humans do. They process numbers. Embeddings allow complex data such as text, audio, or images to be transformed into mathematical form while preserving semantic meaning.

For example, the words “king” and “queen” will have embeddings that are close to each other. The words “apple” and “car” will be farther apart. This distance represents similarity.