AI engineering glossary · Prompt context engineering
What is map-reduce summarisation?
Map-reduce summarisation: A method for texts too long for one prompt: split it into chunks, summarise each chunk separately (map), then combine those summaries into a final summary (reduce). Chunks can be handled in parallel.
Map-reduce summarisation: an example
A 300-page report is split into 30 chunks, each summarised in 100 words, and the 30 summaries are merged into one page.
Related terms
More Prompt context engineering terms
- Markdown formatting in prompts
- Max tokens
- Message roles
- Meta-prompting
- Multi-turn conversation
- Needle in a haystack test
- One-shot prompting
- Outlines library
Where you learn it
Map-reduce summarisation is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.