This module was recorded in 2024 and has not been updated since then. It is optional, but still useful to give you an idea of what you need to implement for a course project.
We walk through building a complete RAG project from scratch: a fitness assistant with search, evaluation, an API, monitoring, and Docker containerization.
The final project is at alexeygrigorev/fitness-assistant.
- Intro - Generating data, setting up the project, initial RAG flow
- Evaluating Retrieval - Ground truth data, Hit Rate, MRR, boosting
- Evaluating RAG - LLM-as-a-Judge, comparing models
- Interface and Ingestion - Flask API, ingestion pipeline, project structure
- Monitoring and Containerization - Docker Compose, PostgreSQL logging, Grafana
- Summary - Final result, cost analysis, tips for your project
- Chunking for Longer Texts - Different chunking strategies for articles, transcripts, slides
Note: check the final result - it's been improved beyond what we show in the videos with better README, code readability, and automated Grafana provisioning.
- [Cohort|2025] RAG Evaluation FAQ by Nitin Gupta (https://github.com/niting9881/llm-zoomcamp-project3/blob/main/RAG_EVALUATION_FAQ.md)
- Did you take notes? Add them above this line (Send a PR with links to your notes)