Welcome to my repo! 🎉 This is where I’ve collected practice code from the LLMOps course offered by DeepLearning.AI in collaboration with Google Cloud.
The course gave me hands-on experience with how to work with Large Language Models (LLMs) in a practical, safe, and scalable way.
- How to clean and structure datasets for LLMs.
- Why high-quality data matters so much for good results.
- Building ML pipelines to automate repetitive steps.
- Orchestrating workflows so things run smoothly at scale.
- Deploying LLMs to serve predictions in real-world settings.
- Measuring, monitoring, and improving model outputs.
- Writing effective prompts to guide LLMs.
- Experimenting with prompt engineering techniques.
- Understanding risks with LLMs (bias, misuse, etc.).
- Adding guardrails for safer and more responsible AI.
- Python 🐍
- Google Cloud ☁️ (for deployment and orchestration)
- APIs & libraries for LLM experimentation
- Prompt engineering techniques and frameworks
Huge thanks to DeepLearning.AI and Google Cloud for creating such a clear, practical, and fun course. 💙 It made learning about the LLMOps approachable and directly useful for real-world projects.