Ideas, experiments, project notes, and practical work in AI & Data.
Shannon HubA knowledge base allows an AI application to access external information. But what happens when the application needs to remember something about a user? For example, imagine an AI shoppi…
Shannon HubUnderstanding what a knowledge base does is useful, but how do we actually build one? Platforms such as Coze simplify the process by providing tools for importing documents, organizing co…
Shannon HubFunction Calling allows AI applications to use external tools. But as an application grows, managing tool integrations can become complicated. Imagine building an AI assistant that needs …
Shannon HubLarge Language Models are good at understanding language and generating responses. However, they cannot automatically access every external system or perform every action a user requests.…
Shannon HubWhen people first start using Large Language Models (LLMs), they usually begin with a simple prompt. They ask a question, provide some instructions, and wait for an answer. But modern AI …
Shannon HubWhen an LLM gives you a bad answer, it is easy to assume that the model is simply not good enough. But that is not always the case. Before changing the model, we should first understand w…
Shannon HubWhen people first think about fine-tuning a Large Language Model, one question often comes up immediately: How many GPUs do I need? It sounds like an important question. Large models requ…
Shannon HubThe difference between RAG and fine-tuning becomes much clearer when we look at real applications. Instead of asking which technology is "better," we can break an AI product into individu…
Shannon HubWhen building an LLM application, one common question is: Should I use RAG or fine-tuning? They can both improve an AI system, but they solve different types of problems. A simple way to …
Shannon HubTraditional RAG usually relies on vector search. A user asks a question, the system converts it into an embedding, searches a vector database, retrieves several similar chunks, and gives …
Shannon HubLarge Language Models know a lot, but they do not automatically know everything inside your private documents, company files, or newly updated data. For example, imagine that your company…
Shannon HubOnce an Agent has access to tools, it still needs a strategy for using them. Should it plan the entire task first? Or should it think, take one action, observe the result, and then decide…
Shannon HubLarge Language Models are good at understanding questions, generating text, and reasoning about information. But an AI Agent needs to do more than simply generate an answer. An Agent may …
Shannon Hub## The Problem of Catastrophic Forgetting Fine-tuning a model on specialized data may improve its performance in a specific domain while reducing some of its original general capabilities…
Shannon HubLarge Language Models are trained on enormous amounts of general-purpose data. This gives them broad knowledge and allows them to handle many different tasks. But a general-purpose model …
Shannon HubLarge Language Models are good at answering questions, generating text, and reasoning about information. But many real-world tasks require more than generating an answer. An AI system may…
Shannon HubRAG and fine-tuning are sometimes treated as competing approaches. But in practice, they can solve different parts of the same problem. The real question is not which one is better. Inste…
Shannon HubWhen building an LLM application, there is usually a point where prompt engineering is no longer enough. You may need the model to know information it has never seen before. Or you may wa…
Shannon HubA real RAG system also needs to decide which information should actually be sent to the LLM. This is where RAG becomes an engineering problem rather than simply an LLM problem. ## From Re…
Shannon Hub## How RAG Works: From Documents to Better LLM Answers Large Language Models are powerful, but they have an important limitation that they do not automatically know your private or up-to-…
Shannon HubSo far, we have built an LLM application with several parts. RAG gives the model external knowledge. Tools allow it to interact with external systems. But what happens when the LLM can de…
Shannon HubImagine your company has 10,000 documents. They might include product manuals, company policies, research reports, customer support documents and other internal knowledge. Now a user asks…
Shannon HubAn LLM is very good at understanding and generating language. But what if we want it to do something outside the model? For example: What is the current price of Product A? The LLM should…
Shannon HubWhen people first start working with Large Language Models (LLMs), it is easy to think that an AI application is simply: User → LLM → Answer. For a basic chatbot, this may be enough. But …