RAG From Scratch
Build a complete retrieval-augmented generation pipeline that answers from technical documents with source evidence.
Production project
Internal Engineering Knowledge Assistant
An engineering team needs answers from runbooks, architecture notes, API docs, and troubleshooting guides without manually searching multiple folders.
Who this is for
- •Developers building internal knowledge assistants
- •AI engineers who want to understand the full RAG data path
How this helps
- •You can build and debug a basic RAG system end to end
- •You understand where retrieval quality affects answer quality
What you will learn
The capabilities, not just the keywords.
- •Explain the ingestion-to-answer RAG pipeline
- •Chunk documents based on retrieval needs
- •Create embeddings and semantic retrieval
- •Assemble grounded context for generation
- •Return useful source references with answers
Real production project
Internal Engineering Knowledge Assistant
An engineering team needs answers from runbooks, architecture notes, API docs, and troubleshooting guides without manually searching multiple folders.
What we build
- •Document ingestion
- •chunking
- •embedding index
- •retriever
- •grounded prompt
- •source references
Stack
- •Python
- •LLM API
- •embedding model
- •vector store
Production concerns
- •Source quality
- •chunk boundaries
- •permissions
- •freshness
- •citation quality
- •unsupported questions
Finished deliverables
- •Working RAG application
- •sample document corpus
- •retrieval debug checklist
- •architecture diagram
Prerequisites
Required
- •Basic Python
- •Basic understanding of APIs
Helpful, but optional
- •Embeddings concept
- •LLM API experience
Before the session
Come ready to build.
- •Python 3.11+
- •LLM/embedding API access or agreed local alternative
- •Git
What to expect
What you get
Something useful after the call ends.
- •Source code
- •architecture diagram
- •RAG checklist
- •test questions
- •next-step roadmap
Where to go next
LLM Engineering → RAG → Production Knowledge Systems
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 AI05: RAG From Scratch
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.