Tell me and I forget. Teach me and I remember. Involve me and I learn. - Benjamin Franklin
This portfolio demonstrates my journey to gain a diverse range of skills and knowledge in AI-related areas, including cloud computing, machine learning, natural language processing. Projects could range from simple WebApp hosting, ML models solving specific problems to more complex applications integrating AI capabilities. Demonstrating practical experience with popular AI tools and frameworks, and cloud platforms like Azure or AWS.
Transform GenAI Concepts into Reality
Use the Nvidia Jetson Orin Nano developer kit to run sophisticated AI tasks locally, without cloud dependency.
This is a practical platform for learning and exploring AI at the edge.
Develop this website helps me to document my technological expertise and projects, it serves as my digital portfolio and understanding of various technologies.
I have learned to use basic HTML, CSS and Javascript, with help from ChatGPT.
Manage MLOps with cloud and pipeline automation
Adapt an open source pipeline that applies supervised fine-tuning on an LLM to better answer user questions.
Learn best practices, including versioning your data and your models, and pre-process large datasets inside a data warehouse.
Apply the methods learned to tune own LLM for other use cases.
Techstack: Google Cloud Platform, Vertex AI, Kubeflow, Kubernetes, Kubectl.
Build image2audio simple AI App
I have learnt how to use Hugging Face to create an AI app that takes an image and converts it into an audio story. This involves using an image-to-text model, a language model (GPT), and a text-to-speech model.
Understand how to obtain an API token from Hugging Face to access their services and demonstrates the code for implementing each step of the AI app.
Build personal assistant applications that help managing schedules and find information quickly. I have learned how to define the scope, choose the right AI model, integrate with a user interface by leveraging ChatGPT API and Flask web framework.
Unlock the potential of LLM and build a customizable prompt that delivers personalized learning expereinces based on GPT-3.5 r GPT-4.
Below video is a simple demo to use ChatGPT API and Python ML UI libary Gradio to create webapp GPT assistant.
Techstack:Python, OpenI API, Gradio.
Building Generative AI Applications with Gradio
Build GenAI App based on Huggingface models such as summarization, image-to-text, text-to-image, LLM.
Build AI data assistant with Streamlit, LangChain and OpenAI
Streamlit and LangChain are part of a broader trend in the AI community to create tools and libraries that democratize access to advanced AI technologies. In this project, I have learned how to setup the environment, import necessary package, develop user interface and interface with LLM.
Streamlit has become popular among data scientists, ML engineers, and analysts for its ability to quickly turn data scripts into interactive app interfaces without requiring in-depth knowledge of web development frameworks.
Create and deploy a computer vision model
The emergence of large vision models marks a significant shift, LVMs are getting pupular because they can leverage massive image datasets to learn visual patterns and features, and perform various vision tasks. It is paving the way for a new era of AI.
I have experienced platform such as LandingLens, Azure AI studio and believe that the technology value is substantial, it analyzes and interprets visual data at a scale and accuracy that was previously unatainable.
AI development with Python
Development environment setup, explore and cleanup data with Pandas.
Train machine learning model with Python, use model hubs and Huggingface.
Use API for AI development, from LLM, Speech recognition and image generation.
