Advanced RAG Techniques

I was the sole implementer for this coursework module: scoped requirements, wrote the code and experiments for “Advanced RAG Techniques,” and produced the write-up with metrics and limitations.

Course lab for “Advanced RAG Techniques”: short deadlines, public or synthetic data, and rubrics that reward reproducible notebooks and honest limitations.

Produce a small credible artifact—clean repo or notebook—with baselines, evaluation, and a crisp story of what would change in production.

Implemented end-to-end (HyDE, rerankers, and metadata filters on one corpus with ablations showing which knob moved groundedness vs latency the most.), logged experiments, compared alternatives, and documented dependencies plus failure cases.

Submitted a runnable deliverable with metrics, repeatable setup commands, and a trade-off section suitable for extending to real systems.