👨💻 Personal Learning Journey
I am currently learning and documenting my progress through this comprehensive 5-Day Gen AI Intensive Course. This repository serves as my learning journal and resource collection as I work through the course materials.
KISHAN PATEL — Ideas to REALITY | OSS Contributor
-
🚀 Passionate about turning ideas into impactful software, automating workflows, and driving innovation in open-source communities.
-
💡 Currently building AI Agents and Generative AI Projects with a focus on real-world usability and scalability.
-
🧠 Exploring the frontier of Generative AI, Autonomous Agents, and LLM-driven systems, while sharpening my expertise in full-stack web development — from pixel-perfect UIs to resilient backend APIs.
-
🤝 Active contributor to Rocket.Chat and Openlit, with a commitment to collaborative problem-solving and continuous learning.
-
🧰 Favorite tools & tech: TypeScript, Node.js, MongoDB, Express, LLMs, and LangGraph frameworks.
🌐 Let's connect:
GitHub || LinkedIn || X (Twitter)
I'm excited to share that I've completed a Kaggle AI Certification 🎓, which highlights my skills in the field of AI! This certification aligns with my work on this project and demonstrates my expertise in generative models and machine learning techniques.
.png)
🏆 Kaggle AI Certification: Kishan Patel
- Day 1: Foundational Models & Prompt Engineering
- Day 2: Embeddings and Vector Stores/Databases
- Day 3: Generative AI Agents
- Day 4: Domain-Specific LLMs
- Day 5: MLOps for Generative AI
As part of the course, I've developed several innovative projects that demonstrate the practical application of Generative AI:
- Project: SwipeWise - Intelligent credit card recommendation system
- Features: Real-time reward optimization, privacy-focused design
- Tech Stack: Gemini API, ChromaDB, Python
- View Project
- Project: ADA 1.0 - AI-powered Ayurvedic health assessment
- Features: Symptom analysis, personalized recommendations
- Tech Stack: Gemini API, LangChain, Python
- View Project
- Project: GenAI-Enhanced Legal Document Analyzer
- Features: Document understanding, clause extraction, fact verification
- Tech Stack: Gemini API, spaCy, Python
- View Project
- Project: TherapyAI - AI-powered mental health companion
- Features: Emotion detection, empathetic responses, safety protocols
- Tech Stack: Gemini API, Speech Recognition, Python
- View Project
- Project: AI-Powered Learning Path Generator
- Features: Customized learning paths, progress tracking
- Tech Stack: Gemini API, LangChain, Python
- View Project
Our 2025 new course is currently open for registration! Learn more and register here: https://rsvp.withgoogle.com/events/google-generative-ai-intensive_2025q1
Welcome to our 5-Day Gen AI Intensive Course with Google! This was a live event from 31st March to 4 April 2025, now made available as a self-paced learning guide for anyone interested in learning more about the fundamental technologies and techniques behind Generative AI.
- Day 1: 🤖 Foundational Models & Prompt Engineering - Explore the evolution of LLMs, from transformers to techniques like fine-tuning and inference acceleration. Get trained with the art of prompt engineering for optimal LLM interaction.
- Day 2: 🔢 Embeddings and Vector Stores/Databases - Learn about the conceptual underpinning of embeddings and vector databases, including embedding methods, vector search algorithms, and real-world applications with LLMs, as well as their tradeoffs.
- Day 3: 🤝 Generative AI Agents - Learn to build sophisticated AI agents by understanding their core components and the iterative development process.
- Day 4: 🎯 Domain-Specific LLMs - Delve into the creation and application of specialized LLMs like SecLM and Med-PaLM, with insights from the researchers who built them.
- Day 5: ⚙️ MLOps for Generative AI - Discover how to adapt MLOps practices for Generative AI and leverage Vertex AI's tools for foundation models and generative AI applications.
Best of Luck! 🍀
- brought to you by Anant Nawalgaria, Mark McDonald, Paige Bailey, and many other contributors from Google.
Follow the following steps to get set up before diving into the daily assignments:
- 📝 Sign up for a Kaggle account and learn how Notebooks work. Make sure to phone verify your account, it's necessary for the course's code labs.
- 🔑 Sign up for an AI Studio account and ensure you can generate an API key.
- 💬 Sign up for a Discord account and join us on the Kaggle Discord server. Check out #5dgai-general-chat to find official course announcements and livestream recordings.
- Youtube Playlist
Please note that if you would like to post on other channels on the Kaggle discord you will need to link your Kaggle account to discord here: https://kaggle.com/discord/confirmation.
Welcome to Day 1.
Today you'll explore the evolution of LLMs, from transformers to techniques like fine-tuning and inference acceleration. You'll also get trained in the art of prompt engineering for optimal LLM interaction.
The code lab will walk you through getting started with the Gemini API and cover several prompt techniques and how different parameters impact the prompts.
-
Complete the Intro Unit: "Foundational Large Language Models", which is:
- 🎧 [Optional] Listen to the summary podcast episode for this unit (created by NotebookLM).
- 📄 Read the "Foundational Large Language Models & Text Generation" whitepaper.
-
Complete Unit 1 – "Prompt Engineering", which is:
- 🎧 [Optional] Listen to the summary podcast episode for this unit (created by NotebookLM).
- 📄 Read the "Prompt Engineering" whitepaper.
- 💻 Complete this code lab on Kaggle where you'll learn prompting fundamentals. Make sure you phone verify your account before starting, it's necessary for the code labs.
- 📊 [Optional] Read this case study to learn how a leading bank leveraged advanced prompt engineering and other contents discussed in assignments of day 1 to automate their financial advisory workflows, achieving significant productivity gains.
-
🎥 Watch the YouTube livestream recording. Paige Bailey will be joined by expert speakers from Google - Mohammadamin Barekatain, Lee Boonstra, Logan Kilpatrick, Daniel Mankowitz, Majd Merey Al, Anant Nawalgaria, Aliaksei Severyn and Chuck Sugnet to discuss today's readings and code labs.
Welcome to Day 2.
Today you will learn about the conceptual underpinning of embeddings and vector databases and how they can be used to bring live or specialist data into your LLM application. You'll also explore their geometrical powers for classifying and comparing textual data.
-
Complete Unit 2: "Embeddings and Vector Stores/Databases", which is:
- 🎧 [Optional] Listen to the summary podcast episode for this unit (created by NotebookLM).
- 📄 Read the "Embeddings and Vector Stores/Databases" whitepaper.
- 💻 Complete these code labs on Kaggle:
-
🎥 Watch the YouTube livestream recording. Paige Bailey will be joined by expert speakers from Google - Omid Fatemieh, Jinhyuk Lee, Alan Li, Iftekhar Naim, Anant Nawalgaria, Yan Qiao, and Xiaoqi Ren to discuss embeddings and vector stores/databases.
Welcome to Day 3.
Learn to build sophisticated AI agents by understanding their core components and the iterative development process. The code labs cover how to connect LLMs to existing systems and to the real world. Learn about function calling by giving SQL tools to a chatbot, and learn how to build a LangGraph agent that takes orders in a café.
-
Complete Unit 3: "Generative Agents", which is:
- 🎧 [Optional] Listen to the summary podcast episode for this unit (created by NotebookLM).
- 📄 Read the "Generative AI Agents" whitepaper.
- 📊 [Optional] Read a case study which talks about how a leading technology regulatory reporting solutions provider used an agentic generative AI system to automate ticket-to-code creation in software development, achieving a 2.5x productivity boost.
- 💻 Complete these code labs on Kaggle:
-
🎥 Watch the YouTube livestream recording. Paige Bailey will be joined by expert speakers from Google - Steven Johnson, Julia Wiesinger, Alan Blount, Patrick Marlow, Wes Dyer, Anant Nawalgaria to discuss generative AI agents.
Welcome to Day 4.
In today's reading, you'll delve into the creation and application of specialized LLMs like SecLM and MedLM/Med-PaLM, with insights from the researchers who built them.
In the code labs you will learn how to add real world data to a model beyond its knowledge cut-off by grounding with Google Search. You will also learn how to fine-tune a custom Gemini model using your own labeled data to solve custom tasks.
-
Complete Unit 4: "Domain-Specific LLMs", which is:
- 🎧 [Optional] Listen to the summary podcast episode for this unit (created by NotebookLM).
- 📄 Read the "Solving Domain-Specific Problems Using LLMs" whitepaper".
- 💻 Complete these code labs on Kaggle:
-
🎥 Watch the YouTube livestream recording. Paige Bailey will be joined by expert speakers from Google - Scott Coull, Antonio Gulli, Anant Nawalgaria, Christopher Semturs, and Umesh Shankar. to discuss domain specific models.
Welcome to Day 5.
Discover how to adapt MLOps practices for Generative AI and leverage Vertex AI's tools for foundation models and generative AI applications.
-
Complete Unit 5: "MLOps for Generative AI", which is:
- 🎧 [Optional] Listen to the summary podcast episode for this unit (created by NotebookLM).
- 📄 Read the "MLOps for Generative AI" whitepaper.
- 💻 No code lab for today! We will do a code walkthrough and live demo of goo.gle/e2e-gen-ai-app-starter-pack, a resource created for making MLOps for Gen AI easier and accelerating the path to production. Please go through the repository in advance.
-
🎥 Watch the YouTube livestream recording. Paige Bailey will be joined by expert speakers from Google - Advait Bopardikar, Sokratis Kartakis, Gabriela Hernandez Larios, Veer Muchandi, Anant Nawalgaria, Elia Secchi, and Olivia Wiles to discuss MLOps practices for generative AI.
There's more!
This bonus notebook walks you through a few more things you can do with the Gemini API that weren't covered during the course. This material doesn't pair with the whitepapers or podcast, but covers some extra capabilities you might find useful when building Gemini API powered apps.