Primers

The core concepts

• 01

  Primer: Databases

  A primer on the main database technologies and how they relate to LLMs
• 02

  RAG & MCP 101

  A quick 101 to RAG & MCP - two key concepts for this series
• 03

  Chunking for RAG

  How to break documents into chunks ready for embedding, and how to tune your chunking strategy
• 04

  pgvector Setup for Airline RAG

  A practical guide to setting up pgvector on Neon and running your first similarity query
• 05

  Embedding for RAG

  How we make our chunks searchable and usable by our LLM.

Code Examples

Practical implementations and walkthroughs

• 06

  Chunking in Practice

  A working chunker built from scratch. Three examples that progressively add metadata and token boundaries

Perspectives

Longer-form analysis and takes on AI in practice

Coming soon