Mid-career life crisis? Learn AI in very simple language from a Google Developer Expert in AI
Mid-career life crisis? Learn AI in very simple language from a Google Developer Expert in AI
Reading Time: 3 minutesPrompt Caching A prompt is an integral part of any Gen AI application. However, the problem occurs when the prompt becomes too large. As then we start incurring more cost. What if we can cache the prompt…
Reading Time: < 1 minuteDelhi vs Mumbai? We have seen this debate multiple times. Can AI agents also debate on this topic? Namaste and Welcome to Build It Yourself. In this tutorial, we will build a Multi AI Agent Debating…
Reading Time: 2 minutesIt has been almost 20 months since ChatGPT emerged and the world got introduced to LLMs. Since then they have grown leaps and bounds. Initially, these models could only process text, but now they have multi-modal capabilities,…
Reading Time: 5 minutesWhile everyone talks about how to build LLM applications, not many people talk about how easy it is to hack one. Prompt injection is a way to trick or manipulate an LLM into doing something it wasn’t…
Reading Time: 2 minutesJobseekers often get this advice that they should create a separate customized resume for every Job description. The idea is to add those keywords/ skills that are mentioned in the JD. This would increase the chances of…
Reading Time: 5 minutesDisclaimer: This article intends to highlight some of the top AI tools for Senior professionals and Entrepreneurs. The list is not in any particular order. The whole idea of doing research in AI was to make computers/…
Reading Time: 4 minutesPreviously we built many multi-AI Agent systems for debate, to customize a resume and content creation automation. In this tutorial, we will build a Multi AI Agent System for Customer Support Automation. We will build 2 Agents…
Reading Time: 3 minutesNamaste and Welcome to Build It Yourself. In this tutorial, we will build a Text-to-Image tool using an opensource model from Huggingface You will see how easy it is to access a model from Huggingface. You can…
Reading Time: 3 minutesBy now, many of us know how to perform RAG (Retrieval Augmented Generation) on a PDF. The RAG pipeline consists of loading the document first and then dividing the large document into smaller chunks. Embeddings are created…
Reading Time: 6 minutesLLM makers are running out of training data. Llama3 was pre-trained on 15 trillion tokens, almost 7 times more than Llama2. To further increase LLM’s capabilities, we need more data but the problem is current training sets…