Skip to content
InfratoApp

NVIDIA · Course

Evaluating RAG and Semantic Search Systems (self-paced)

Evaluating RAG and Semantic Search Systems is a hands-on, self-paced NVIDIA course on how to evaluate retrieval-augmented generation and semantic search in enterprise settings, from keyword search and BM25 to vector stores, with test sets and LLM-as-a-Judge techniques.

Open at NVIDIA ↗Common questions

Who it suits

  • Engineers who run RAG or search systems and need a rigorous way to measure them.
  • Teams working under compliance or changing-information requirements.

What it covers

  • The challenges of deploying RAG and semantic search in enterprise settings, including legacy and modern retrieval together.
  • Evaluation frameworks such as Ragas, and LLM-as-a-Judge for metric-based and qualitative assessment.
  • Generating, customising and validating synthetic test sets that reflect realistic user queries.
  • The evolution from keyword-based search and BM25 ranking to vector stores and semantic retrieval.

Common questions about Evaluating RAG and Semantic Search Systems (self-paced)

What will I be able to do?
NVIDIA says you will be equipped to design, implement and continuously improve evaluation workflows for RAG and search systems.
Does it cost anything?
NVIDIA sells the self-paced course with Buy Now and Redeem Code options, and says online purchase is supported in select locations. Its page states the price, which changes, so check it.
Is it hands-on?
Yes. NVIDIA describes it as a comprehensive, hands-on introduction.

More like this

Keep learning on Infrato

Where this comes from

Written from NVIDIA’s own pages, read on 2026-10-14. Content, prices and availability change, so the provider’s page is the source. We are not affiliated with NVIDIA and this is not an endorsement.