📘 DeepLearning.AI – Short Courses Collection

A curated collection of DeepLearning.AI short courses, organized into individual folders for easy navigation, practice, and revision. This repository is ideal for learners looking to master modern AI, ML, and Generative AI concepts through hands-on notebooks and structured lessons.

📂 Repository Structure

Each folder represents one DeepLearning.AI short course and typically contains:

• 📓 Jupyter notebooks
• 🧠 Concept notes
• 🧪 Exercises & experiments
• 📄 Supporting resources (if any)

📊 Courses Overview

Course Name	Description	Folder
ChatGPT Prompt Engineering for Developers	Learn prompt engineering fundamentals and build LLM-powered applications using the OpenAI API, including summarization, classification, text transformation, and chatbots.	ChatGPT-Prompt-Engineering-for-Developers
Building Systems with the ChatGPT API	Learn to build multi-step, production-style LLM systems using prompt chains, Python integration, and the ChatGPT API.
LangChain for LLM Application Development	Build advanced LLM applications using LangChain, including chains, memory, document Q&A, and agent-based reasoning.
LangChain: Chat with Your Data	Build RAG-based chatbots with LangChain using embeddings, vector stores, retrieval, and document-based question answering.
Evaluating and Debugging Generative AI Models Using Weights and Biases	Track, version, and manage ML and LLM experiments using Weights & Biases with a complete MLOps workflow.
Large Language Models with Semantic Search	Build intelligent search systems using embeddings, dense retrieval, and LLM-based reranking beyond keyword search.
Understanding and Applying Text Embeddings	Use Vertex AI text embeddings to power semantic search, classification, clustering, and LLM-based Q&A systems.
Functions, Tools and Agents with LangChain	Build advanced LLM agents using function calling and LangChain Expression Language (LCEL) for structured output and routing.
Building and Evaluating Advanced RAG Applications	Build and evaluate advanced RAG pipelines using improved retrieval methods and RAG-specific evaluation metrics.
Advanced Retrieval for AI with Chroma	Improve IR and RAG relevance using query expansion, cross-encoder reranking, and embedding adapters.
Building Applications with Vector Databases	Build AI applications with vector databases, including semantic search, RAG, recommendations, hybrid search, and anomaly detection.