15 Short Artificial Intelligence (AI) Courses on DeepLearning.AI

DeepLearning AI offers a variety of short courses designed to boost your skills in generative AI and other AI technologies. These courses are crafted to provide learners with the right knowledge, tools, and techniques required to excel in AI. Here’s a look at the most relevant short courses available:

Red Teaming LLM Applications
This course offers an essential guide to enhancing the safety of LLM applications through red teaming. Participants will learn to spot and address vulnerabilities within LLM applications, applying cybersecurity methods to the AI domain. By utilizing Giskard’s open-source library, students will be equipped with the techniques to automate red teaming methods. Basic JavaScript knowledge is recommended, making this course suitable for beginners eager to contribute to developing safer AI applications.

JavaScript RAG Web Apps with LlamaIndex
Dive into the world of building interactive, full-stack web applications that leverage the power of Retrieval Augmented Generation (RAG) capabilities. Through this beginner-level course, you’ll learn to construct a RAG application in JavaScript, enabling intelligent agents to discern and pull information from various data sources to respond to user queries effectively. With a focus on creating an engaging front end that communicates seamlessly with your data, this course is perfect for those with basic JavaScript skills looking to expand their web development repertoire.

Efficiently Serving LLMs
This intermediate course provides a comprehensive understanding of how to deploy LLM applications efficiently in a production environment. Participants will explore techniques like KV caching to speed up text generation and delve into Low-Rank Adapters (LoRA) fundamentals and the LoRAX framework inference server. With a prerequisite of intermediate Python knowledge, this course is designed for those looking to scale their LLM applications effectively, catering to a large user base while balancing performance and speed.

Knowledge Graphs for RAG
Learners will get hands-on experience building and utilizing knowledge graph systems to supercharge their retrieval augmented generation applications. The course covers using Neo4j’s Cypher query language and constructing knowledge graph queries to provide LLMs with more relevant context. Recommended for those familiar with LangChain, this intermediate course bridges the gap between traditional databases and AI-driven query mechanisms.

Open Source Models with Hugging Face
Aimed at beginners, this course demystifies building AI applications with open-source models and tools from Hugging Face. From filtering models based on specific criteria to writing minimal lines of code for various tasks, students will learn how to leverage the transformers library effectively. Additionally, the course covers how to share and run AI applications easily using Gradio and Hugging Face Spaces, making it ideal for those new to the AI field.

Prompt Engineering with Llama 2
Discover the art of prompt engineering with Meta’s Llama 2 models. This beginner-friendly course teaches the best practices for prompting and selecting among different Llama 2 models, including Chat, Code, and Llama Guard. Participants will explore how to build safe and responsible AI applications, emphasizing the practical use of Llama 2 models in real-world scenarios.

Building Applications with Vector Databases
This beginner-level course is designed to teach how to develop applications powered by vector databases. Covering six different applications, including semantic search and image similarity search, students will learn to implement these using Pinecone. With basic knowledge of Python, machine learning, and LLMs required, this course offers a practical approach to the exciting possibilities of vector databases.

This course introduces the best practices of LLMOps, from designing to automating the process of tuning an LLM for specific tasks and deploying it. Participants will learn to adapt open-source pipelines for supervised fine-tuning, manage model versions, and preprocess datasets. Aimed at beginners with basic Python knowledge, this course is perfect for those looking to delve into the operational aspects of LLM deployment.

Automated Testing for LLMOps
This intermediate course focuses on developing automated testing frameworks for LLM applications and introduces continuous integration (CI) pipelines. Participants will learn how LLM-based testing differs from traditional software testing, implementing rules-based and model-graded evaluations. Basic Python knowledge and experience with LLM-based applications are prerequisites, making this course suitable for developers looking to enhance their testing strategies.

Build LLM Apps with LangChain.js
Expanding on using LangChain.js, this intermediate course provides insights into building powerful, context-aware applications. With a focus on orchestrating and chaining different modules, participants will learn essential data preparation and presentation techniques. Intermediate JavaScript knowledge is required, making this course ideal for developers aiming to enhance their LLM application development skills.

Reinforcement Learning from Human Feedback
This intermediate course offers a blend of conceptual understanding and hands-on practice. It covers tuning and evaluating LLMs using Reinforcement Learning from Human Feedback (RLHF). Participants will learn to fine-tune the Llama 2 model, assess performance, and understand the datasets required for RLHF.

Building and Evaluating Advanced RAG Applications
Step into the advanced domain of RAG with this beginner-friendly course. It delves into enhancing retrieval techniques and mastering evaluation metrics to optimize RAG applications’ performance. Learners will explore sentence-window retrieval and auto-merging retrieval techniques, focusing on evaluating the relevance and truthfulness of LLM responses through the RAG triad: Context Relevance, Groundedness, and Answer Relevance. Designed for those with a basic understanding of Python, this course equips you with the skills to develop robust RAG systems beyond the baseline iteratively.

Quality and Safety for LLM Applications
This course prioritizes the security and integrity of LLM applications and is designed for beginners with basic Python knowledge. Participants will learn to evaluate and enhance the safety of their LLM applications, focusing on monitoring security measures and identifying potential risks such as hallucinations, jailbreaks, and data leaks. By exploring real-world scenarios, the course prepares you to safeguard your LLM applications against evolving threats and vulnerabilities, ensuring a secure and reliable AI deployment.

Vector Databases: from Embeddings to Applications
This intermediate course unlocks the potential of vector databases for AI applications, bridging the gap between embeddings and practical, real-world applications. Designed for those with basic Python knowledge and an interest in data structures, learners will develop efficient, industry-ready applications. The course covers a broad spectrum of applications, including hybrid and multilingual searches, emphasizing using vector databases to develop GenAI applications without requiring extensive training or fine-tuning of LLMs. 

Functions, Tools, and Agents with LangChain
Delve into the latest advancements in LLM APIs and learn to use LangChain Expression Language (LCEL) for faster chain and agent composition. This intermediate course, suitable for individuals with basic Python knowledge and familiarity with LLM prompts, offers a hands-on approach to utilizing LLMs as developer tools. Through practical exercises, learners will understand how to apply these capabilities to build conversational agents, enhancing their ability to create more sophisticated and interactive AI applications.

Each course is designed with a specific skill level, from beginner to intermediate, ensuring learners can find courses that match their current abilities and help them progress. Whether you’re looking to build safer LLM applications, create AI-powered web apps, or dive into vector databases, DeepLearning.AI’s short courses provide a comprehensive learning path tailored to your needs. For those interested in advancing their AI skills quickly and efficiently, these courses offer an excellent opportunity to learn cutting-edge AI technologies.

Hello, My name is Adnan Hassan. I am a consulting intern at Marktechpost and soon to be a management trainee at American Express. I am currently pursuing a dual degree at the Indian Institute of Technology, Kharagpur. I am passionate about technology and want to create new products that make a difference.