Long context prompting

A method for augmenting an AI prompt with personally¹ contextualised data that is unknown to a Large Language Model. Documents are directly added to the prompt as context before sending to the LLM.

flowchart TD
	Input@{ shape: lean-r, label: "User Prompt" }
	Input -->|adds| Document@{ shape: docs, label: "Documents, Images, etc." }
	Document -->|contextualising| Context(Final Prompt)
	Context --> LLM

Retrieval Augmented Generation is an alternative to Long context prompting

Source: Is RAG Still Needed? Choosing the Best Approach for LLMs - YouTube

Footnotes

1. Personal as in not publicly known outside of an individual, family or business. ↩