Track 5: RAG: Retrieval-Augmented Generation
Advanced RAG: Vector Databases, Hybrid Search, GraphRAG & Agentic RAG
45 lessons
Track 15: Frontier and Advanced, Reasoning Models and Inference
Long Context vs RAG: Measure Cost and Accuracy
Measure when to stuff the context and when to retrieve.
Get notified on YouTube Udemy certificate: coming soon
Course
Advanced RAG: Vector Databases, Hybrid Search, GraphRAG & Agentic RAG
Udemy: coming soon
Tools
- Gemini API (freemium)
- Chroma (open-source, free)
Watch first
- RAG vs Fine-Tuning vs Long Context (and Cache-Augmented Generation)
- Reasoning Models in Production: When They Pay Off
In this module
- Reasoning Models in Production: When They Pay Off
- Thinking Budgets: Cost, Latency and Quality
- Long Context vs RAG: Measure Cost and Accuracy
- Small and On-Device Models: Laptops, Phones and Browsers
- Inference Optimisation: KV Cache and Prefix Caching
- Speculative Decoding and Continuous Batching
- Project: Benchmark Your Model Serving Stack
The course this lesson belongs to