About this course
Study retrieval-augmented generation through five structured learning journeys. The course starts with knowledge retrieval, then examines retrieval system design, vector index scaling, multimodal data, and application scenarios. It is useful for developers planning how an AI application will find reliable supporting information.
What you can learn
- Explain the retrieval stage of RAG
- Design a retrieval system and vector index
- Consider index scale and multimodal data
- Match retrieval choices to application scenarios
Course at a glance
| Provider | Microsoft |
|---|---|
| Platform | YouTube · Microsoft Developer |
| Access | Free Video |
| Level | Intermediate — WikiFree audience assessment |
| Language | English |
| Selected lessons | 5 |
| Video duration | 2h 43m · allow extra time for reflection and practice |
| Details checked | 9 October 2026 |
Try this learning exercise
Design a retrieval plan for ten fictional help articles. Decide how to divide them into passages, what metadata to keep, and how to check whether a retrieved passage actually supports an answer.
How to follow the course
Choose a lesson from the list or search for a specific topic. Use Previous and Next to continue, and mark lessons complete as you go. Progress is saved in this browser without a WikiFree account.
Each course retains its relevant lessons, including videos also used in another course. Numbered series follow their original lesson or part order. Only reviewed advertisements, unrelated items and identical repeated playlist entries are excluded. Source recordings may have been made at different times.
Free access, tools and certificates
The selected public YouTube videos are free to watch. No paid subscription, payment card, examination, or software purchase is required for this video learning path. This listing does not include a Microsoft certification, assessed assignment, or instructor feedback.
The learning exercise above can be completed as a written plan without provisioning services. Reproducing demonstrations with Azure, hosted models, enterprise products, hardware, or optional software may require an account, separate access, or paid resources. Those activities are not required to complete the video course. Recorded interfaces and commands may differ from current versions.
Official Microsoft Developer playlist source ↗
Use this course in a learning path
Related courses for your next step
- Compare another approachFree RAG Course: Retrieval, Vector Search and AI Agents
Focus: Retrieval-augmented generation · Sparse and dense retrieval
Intermediate - Compare another approachFree Azure AI Course: Multimodal Content Understanding
Focus: Understand the Content Understanding workflow · Explore retrieval over video content
Intermediate - Compare another approachFree AI App Development Course: Local LLMs and RAG
Focus: Local LLM inference · RAG application patterns
Intermediate
Compare course focus, level and study time
| Course | Level | Focus | Study time |
|---|---|---|---|
| This course — Free RAG Course: Retrieval, Vector Search and Multimodal Data | Intermediate | Explain the retrieval stage of RAG · Design a retrieval system and vector index · Consider index scale and multimodal data | 2h 43m of video; practice time is additional |
| Free RAG Course: Retrieval, Vector Search and AI Agents | Intermediate | Retrieval-augmented generation · Sparse and dense retrieval · Hybrid search | 3h 22m of video; practice time is additional |
| Free Azure AI Course: Multimodal Content Understanding | Intermediate | Understand the Content Understanding workflow · Explore retrieval over video content · Review a post-call analytics scenario | 21m of video; practice time is additional |
| Free AI App Development Course: Local LLMs and RAG | Intermediate | Local LLM inference · RAG application patterns · AI tool calling | 8h 7m of video; practice time is additional |
Provider: Microsoft. Videos play from the Microsoft Developer channel on YouTube.
Report a correction
Questions & discussion
Share a useful question or correction. Comments appear after moderation. Please avoid personal or sensitive information.