Advanced RAG
Upgrade a naive RAG pipeline with metadata filters, hybrid retrieval, reranking, query rewriting, and measurable retrieval improvements.
Production project
Production Support Knowledge Assistant
A support team has old and current runbooks, product-specific docs, and noisy knowledge-base articles. Basic vector search often returns broad or stale evidence.
Who this is for
- •Engineers whose RAG prototype works sometimes but fails unpredictably
- •Teams preparing an internal knowledge assistant for real users
How this helps
- •You can improve RAG using evidence instead of prompt tweaking
- •You learn the retrieval patterns commonly needed beyond demos
What you will learn
The capabilities, not just the keywords.
- •Diagnose retrieval failure separately from generation failure
- •Apply metadata filters and query rewriting
- •Combine lexical and semantic retrieval strategies
- •Use reranking to improve evidence selection
- •Compare baseline and improved retrieval behavior
Real production project
Production Support Knowledge Assistant
A support team has old and current runbooks, product-specific docs, and noisy knowledge-base articles. Basic vector search often returns broad or stale evidence.
What we build
- •Baseline retriever
- •metadata-aware retrieval
- •hybrid search path
- •reranking step
- •comparison harness
Stack
- •Python
- •vector store
- •lexical search
- •reranker
- •LLM API
Production concerns
- •Freshness
- •permissions
- •stale evidence
- •retrieval latency
- •fallbacks
- •observability
Finished deliverables
- •Improved RAG pipeline
- •before/after test set
- •retrieval diagnostics
- •production architecture notes
Prerequisites
Required
- •Understand a basic RAG pipeline
Helpful, but optional
- •Complete AI05 or bring an existing RAG project
Before the session
Come ready to build.
- •Bring your RAG project or use the provided baseline
- •Python environment
- •LLM/embedding access
What to expect
What you get
Something useful after the call ends.
- •Source code
- •retrieval evaluation sheet
- •architecture diagram
- •debugging checklist
Where to go next
RAG Fundamentals → Retrieval Quality → Production RAG
Every session can be booked independently. If you already know the prerequisite material, skip ahead.
Useful before this
Teaching proof
Review the evidence first.
See workshop delivery, technical projects, and teaching proof before booking.
Ready?
Request AI06: Advanced RAG
Share your current level and what you want to build. The session can be adapted without changing its core outcome.
Request this sessionFAQ
Can I book only this session?
Yes. Every session is designed to work independently.
Can I bring my own project?
Yes, when it fits the session outcome. We can map the concepts onto your project instead of the default example.
What if I already know part of the topic?
We can move faster through familiar material and spend more time on implementation, failure modes, and production trade-offs.
Is the session recorded?
Recording is not promised by default. Confirm this before the session if you need it.
What should I install?
The preparation section above lists the default setup. You will receive any session-specific setup notes before the call.
Are API or cloud charges included?
No. Any third-party API or cloud usage is paid directly through your own account unless explicitly agreed otherwise.