← Tech Station
03 — Architecture

RAG

Chunking, embeddings, vector search, and fixing hallucinations in production.

13 guides in this track·1.4h reading·Intermediate
What you'll learn

Design retrieval systems that actually reduce hallucination — chunking, embeddings, hybrid search, re-ranking, and the production concerns most tutorials skip.

Who this is for

Engineers building any product where the model has to answer from your data — not just its training data.

How to use it

The guides are numbered — read in order for the curriculum path, or jump straight to the one you need. Each card is self-contained.

The guides

Ordered by recommended reading path
01
What Is RAG & Why It Matters

Grounding LLMs in your own data; the open-book analogy.

6 minRead →
02
Embeddings & Semantic Search Explained

How meaning-based retrieval beats keyword search.

5 minRead →
03
Vector Databases: How They Work & How to Choose

Storing/searching vectors; comparing the main options.

6 minRead →
04
Chunking Strategies That Make or Break RAG

Chunk size, overlap, structure-aware splitting.

6 minRead →
05
Building Your First RAG Pipeline (Concept)

The indexing + retrieval-generation flow end to end.

6 minRead →
06
Retrieval: Similarity, Top-k & Metadata Filtering

Tuning what gets fetched and how much.

6 minRead →
07
Why Your RAG Pipeline Keeps Hallucinating

Diagnosing retrieval vs generation failures.

7 minRead →
08
Re-Ranking: The Biggest Quality Lever

Retrieve-broad-then-rerank for precision.

6 minRead →
09
Hybrid Search: Semantic + Keyword

Catching exact terms, codes and names embeddings miss.

6 minRead →
10
Advanced RAG: Query Rewriting & Multi-Step Retrieval

Reformulation and multi-hop questions.

6 minRead →
11
Agentic RAG: Retrieval With a Brain

Letting the model decide whether/what/how to retrieve.

6 minRead →
12
Evaluating RAG Systems

Measuring retrieval and answer quality objectively.

7 minRead →
13
RAG in Production: Cost, Latency & Monitoring

Operating a RAG system reliably at scale.

8 minRead →

Related tracks

Continue in the same group
01 — Start hereAI PrimerThe concepts every LLM practitioner needs before writing a single prompt.02 — Core skillPrompt EngineeringZero-shot to few-shot, chain-of-thought, and structured output patterns.04 — LLMOpsLLM Fine-Tuning & LLMOpsWhen to fine-tune vs. prompt, LoRA, QLoRA, evaluation, and deployment.05 — AdvancedAgentic AIPlanning loops, tool use, memory, and multi-agent coordination.