• AI/ML - Code

    Tutorial: A basic plugin using Semantic Kernel

    Below source code are for Creating a basic plugin (testplugin.cs), and see how it is being called using prompt from Program.cs. This example uses Weather finding, such as “What is the weather in London on 18th June 2024?”, and it will always return a hard coded value of “29” degrees celsius. You can modify the function to do complex logic. testplugin.cs This is a very basic plugin, which I purposefully did not include any logic. Comments are added inline to explain what each line/function does. Program.cs appsettings.json I used this file to avoid hardcoding sensitive information in the source code…

  • AI/ML - Architecture - Articles - General

    Why you should use FastAPI?

    If you are building an AI-powered application today, the way you expose your models through APIs can make a big difference in scalability and developer experience. FastAPI has become one of the most popular choices for creating robust, production-ready APIs, especially for AI and LLM-based workloads. It is fast, type-safe, asynchronous, and easy to work with, which makes it ideal for developers who want both speed and clarity. While Flask, Django, BentoML, and Ray Serve are all valid alternatives, FastAPI provides a good balance between simplicity and performance. For enterprise-level applications, however, more powerful frameworks like Ray Serve or BentoML…

  • AI/ML - Articles

    In the era of Gen AI, should we still learn statistics and ML?

    With the rise of Generative AI, many professionals wonder if learning the old school foundations of statistics, classical machine learning, and data science is still relevant. After all, tools today can generate insights, code, and even models with just a few prompts. It is tempting to skip the basics and focus only on leveraging Gen AI platforms. But the reality is, foundational knowledge still holds significant value, especially depending on who you are and what you do. For Data Scientists and Analysts If you are building models, validating results, or making sense of patterns in data, a strong foundation is…

  • AI/ML

    DeepSeek chat vs ChatGPT – an attempt to compare in action

    Since the launch of #DeepSeek, I have been evaluating different use cases across various domains and technology stacks. However, as of writing this post, I must say I am disappointed with its chat portal—though I am amazed by the R1 capabilities described in the paper. Now, coming to a sample comparison with #ChatGPT GPT-4o—I am still impressed with OpenAI’s efficiency. My query was: “Write a C# program in the most complex way possible to find the sum of two numbers.” DeepSeek Chat, as has been the case recently, showed busy servers, and after several attempts, I finally received a response…

  • AI/ML - Articles - Enterprise Architecture

    Alternative thoughts on Retrieval-Augmented Generation (RAG)

    Solutions are always tailored to specific problems. There’s no one-size-fits-all approach. The techniques vary depending on needs like the level of customization, available data sources, and system complexity. The strategy should be based on these factors. Here are a few alternative approaches we can consider, if RAG is optional: Embedding-Based Search with Pretrained Models: This is a relatively easy approach to implement, but it doesn’t offer the same capabilities as RAG. It works well when simple retrieval is enough and there’s no need for complex reasoning. – Knowledge Graphs with AI Integration: Best for situations where structured reasoning and relationships…