RAG and its evolution
Retrieval Augmented Generation (RAG) is becoming a platform in its own right. In this and the following post, we explore the foundations and more importantly,… Read More »RAG and its evolution
Home
ajitjaokar
Based in London, Ajit's work spans research, entrepreneurship, and academia relating to artificial intelligence (AI) with Cyber-Physical systems. He is the course director of the course: Artificial Intelligence: Cloud and Edge Implementations at the University of Oxford. He is also a visiting fellow in Engineering Sciences at the University of Oxford. Besides this, he also conducts the University of Oxford courses: Digital Twins, Cybseecurity, and Agtech. Ajit works as a Data Scientist through his company, feynlabs - focusing on building innovative early-stage AI prototypes for complex AI applications. Besides the University of Oxford, Ajit has also conducted AI courses at the London School of Economics (LSE), Universidad Politécnica de Madrid (UPM), and as part of The Future Society at the Harvard Kennedy School of Government.
Introduction to autonomous agents from a developer perspective – Part one
What are autonomous AI agents? Autonomous AI agents are systems capable of performing tasks without human intervention. Agents have been around in various incarnations. Most… Read More »Introduction to autonomous agents from a developer perspective – Part one
Cognitive robotics – Part one
In this three-part series, we will explore cognitive robotics – a fascinating subject that promises to play a major role in the evolution of AI.… Read More »Cognitive robotics – Part one
Understanding GraphRAG – 1: The challenges of RAG
Background Retrieval Augmented Generation(RAG) is an approach for enhancing existing LLMs with external knowledge sources, to provide more relevant and contextual answers. In a RAG,… Read More »Understanding GraphRAG – 1: The challenges of RAG
Understanding GraphRAG – 2 addressing the limitations of RAG
Background We follow on from the last post and explore the limitations of RAG and how you can overcome these limitations using the idea of… Read More »Understanding GraphRAG – 2 addressing the limitations of RAG
Understanding GraphRAG – 3 Implementing a GraphRAG solution
In this third part of the solution, we discuss how to implement a GraphRAG. This implementation needs an understanding of Langchain which we shall also… Read More »Understanding GraphRAG – 3 Implementing a GraphRAG solution
The EU’s AI act: A measured approach to innovation and regulation
AI regulatory measures often stir mixed reactions. We reached a regulatory milestone this week- with the final passing of the AI ACT in the European… Read More »The EU’s AI act: A measured approach to innovation and regulation
Future of LLM application development – impact of Gemini 1.5 Pro with a 1M context window
Image source https://blog.google/technology/ai/google-gemini-next-generation-model-february-2024/ Current LLM applications are mostly based on LangChain or LlamaIndex. LangChain and LlamaIndex are frameworks designed for LLM development. They each cater to… Read More »Future of LLM application development – impact of Gemini 1.5 Pro with a 1M context window
Open source LLMs – no more than a marketing term?
Image source: Dall-e This week, the tech community has been abuzz with the announcement of the latest model from Mistral being closed source. This revelation… Read More »Open source LLMs – no more than a marketing term?
The AI radiologists replacement saga: Don’t be misled by the scaremongering – science v.s. science fiction
Seven years ago, an unexpected nationwide shortage of radiologists was triggered by a single statement from Professor Geoffrey Hinton. The statement was:“I think if you… Read More »The AI radiologists replacement saga: Don’t be misled by the scaremongering – science v.s. science fiction